xieyao/opencode-mobile
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix(cua): do not press back after typing — adb input text does not show keyboard, back navigates away

Browse Source
This commit is contained in:
Dennis V
2026-06-22 20:20:44 +00:00
parent 19b656aae8
commit ea22d06f61
25 changed files with 7339 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

662
.agents/skills/app-store-optimization/scripts/ab_test_planner.py Normal file
View File

@@ -0,0 +1,662 @@
"""
A/B testing module for App Store Optimization.
Plans and tracks A/B tests for metadata and visual assets.
"""
from typing import Dict, List, Any, Optional
import math
class ABTestPlanner:
"""Plans and tracks A/B tests for ASO elements."""
# Minimum detectable effect sizes (conservative estimates)
MIN_EFFECT_SIZES = {
'icon': 0.10, # 10% conversion improvement
'screenshot': 0.08, # 8% conversion improvement
'title': 0.05, # 5% conversion improvement
'description': 0.03 # 3% conversion improvement
}
# Statistical confidence levels
CONFIDENCE_LEVELS = {
'high': 0.95, # 95% confidence
'standard': 0.90, # 90% confidence
'exploratory': 0.80 # 80% confidence
}
def __init__(self):
"""Initialize A/B test planner."""
self.active_tests = []
def design_test(
self,
test_type: str,
variant_a: Dict[str, Any],
variant_b: Dict[str, Any],
hypothesis: str,
success_metric: str = 'conversion_rate'
) -> Dict[str, Any]:
"""
Design an A/B test with hypothesis and variables.
Args:
test_type: Type of test ('icon', 'screenshot', 'title', 'description')
variant_a: Control variant details
variant_b: Test variant details
hypothesis: Expected outcome hypothesis
success_metric: Metric to optimize
Returns:
Test design with configuration
"""
test_design = {
'test_id': self._generate_test_id(test_type),
'test_type': test_type,
'hypothesis': hypothesis,
'variants': {
'a': {
'name': 'Control',
'details': variant_a,
'traffic_split': 0.5
},
'b': {
'name': 'Variation',
'details': variant_b,
'traffic_split': 0.5
}
},
'success_metric': success_metric,
'secondary_metrics': self._get_secondary_metrics(test_type),
'minimum_effect_size': self.MIN_EFFECT_SIZES.get(test_type, 0.05),
'recommended_confidence': 'standard',
'best_practices': self._get_test_best_practices(test_type)
}
self.active_tests.append(test_design)
return test_design
def calculate_sample_size(
self,
baseline_conversion: float,
minimum_detectable_effect: float,
confidence_level: str = 'standard',
power: float = 0.80
) -> Dict[str, Any]:
"""
Calculate required sample size for statistical significance.
Args:
baseline_conversion: Current conversion rate (0-1)
minimum_detectable_effect: Minimum effect size to detect (0-1)
confidence_level: 'high', 'standard', or 'exploratory'
power: Statistical power (typically 0.80 or 0.90)
Returns:
Sample size calculation with duration estimates
"""
alpha = 1 - self.CONFIDENCE_LEVELS[confidence_level]
beta = 1 - power
# Expected conversion for variant B
expected_conversion_b = baseline_conversion * (1 + minimum_detectable_effect)
# Z-scores for alpha and beta
z_alpha = self._get_z_score(1 - alpha / 2) # Two-tailed test
z_beta = self._get_z_score(power)
# Pooled standard deviation
p_pooled = (baseline_conversion + expected_conversion_b) / 2
sd_pooled = math.sqrt(2 * p_pooled * (1 - p_pooled))
# Sample size per variant
n_per_variant = math.ceil(
((z_alpha + z_beta) ** 2 * sd_pooled ** 2) /
((expected_conversion_b - baseline_conversion) ** 2)
)
total_sample_size = n_per_variant * 2
# Estimate duration based on typical traffic
duration_estimates = self._estimate_test_duration(
total_sample_size,
baseline_conversion
)
return {
'sample_size_per_variant': n_per_variant,
'total_sample_size': total_sample_size,
'baseline_conversion': baseline_conversion,
'expected_conversion_improvement': minimum_detectable_effect,
'expected_conversion_b': expected_conversion_b,
'confidence_level': confidence_level,
'statistical_power': power,
'duration_estimates': duration_estimates,
'recommendations': self._generate_sample_size_recommendations(
n_per_variant,
duration_estimates
)
}
def calculate_significance(
self,
variant_a_conversions: int,
variant_a_visitors: int,
variant_b_conversions: int,
variant_b_visitors: int
) -> Dict[str, Any]:
"""
Calculate statistical significance of test results.
Args:
variant_a_conversions: Conversions for control
variant_a_visitors: Visitors for control
variant_b_conversions: Conversions for variation
variant_b_visitors: Visitors for variation
Returns:
Significance analysis with decision recommendation
"""
# Calculate conversion rates
rate_a = variant_a_conversions / variant_a_visitors if variant_a_visitors > 0 else 0
rate_b = variant_b_conversions / variant_b_visitors if variant_b_visitors > 0 else 0
# Calculate improvement
if rate_a > 0:
relative_improvement = (rate_b - rate_a) / rate_a
else:
relative_improvement = 0
absolute_improvement = rate_b - rate_a
# Calculate standard error
se_a = math.sqrt(rate_a * (1 - rate_a) / variant_a_visitors) if variant_a_visitors > 0 else 0
se_b = math.sqrt(rate_b * (1 - rate_b) / variant_b_visitors) if variant_b_visitors > 0 else 0
se_diff = math.sqrt(se_a**2 + se_b**2)
# Calculate z-score
z_score = absolute_improvement / se_diff if se_diff > 0 else 0
# Calculate p-value (two-tailed)
p_value = 2 * (1 - self._standard_normal_cdf(abs(z_score)))
# Determine significance
is_significant_95 = p_value < 0.05
is_significant_90 = p_value < 0.10
# Generate decision
decision = self._generate_test_decision(
relative_improvement,
is_significant_95,
is_significant_90,
variant_a_visitors + variant_b_visitors
)
return {
'variant_a': {
'conversions': variant_a_conversions,
'visitors': variant_a_visitors,
'conversion_rate': round(rate_a, 4)
},
'variant_b': {
'conversions': variant_b_conversions,
'visitors': variant_b_visitors,
'conversion_rate': round(rate_b, 4)
},
'improvement': {
'absolute': round(absolute_improvement, 4),
'relative_percentage': round(relative_improvement * 100, 2)
},
'statistical_analysis': {
'z_score': round(z_score, 3),
'p_value': round(p_value, 4),
'is_significant_95': is_significant_95,
'is_significant_90': is_significant_90,
'confidence_level': '95%' if is_significant_95 else ('90%' if is_significant_90 else 'Not significant')
},
'decision': decision
}
def track_test_results(
self,
test_id: str,
results_data: Dict[str, Any]
) -> Dict[str, Any]:
"""
Track ongoing test results and provide recommendations.
Args:
test_id: Test identifier
results_data: Current test results
Returns:
Test tracking report with next steps
"""
# Find test
test = next((t for t in self.active_tests if t['test_id'] == test_id), None)
if not test:
return {'error': f'Test {test_id} not found'}
# Calculate significance
significance = self.calculate_significance(
results_data['variant_a_conversions'],
results_data['variant_a_visitors'],
results_data['variant_b_conversions'],
results_data['variant_b_visitors']
)
# Calculate test progress
total_visitors = results_data['variant_a_visitors'] + results_data['variant_b_visitors']
required_sample = results_data.get('required_sample_size', 10000)
progress_percentage = min((total_visitors / required_sample) * 100, 100)
# Generate recommendations
recommendations = self._generate_tracking_recommendations(
significance,
progress_percentage,
test['test_type']
)
return {
'test_id': test_id,
'test_type': test['test_type'],
'progress': {
'total_visitors': total_visitors,
'required_sample_size': required_sample,
'progress_percentage': round(progress_percentage, 1),
'is_complete': progress_percentage >= 100
},
'current_results': significance,
'recommendations': recommendations,
'next_steps': self._determine_next_steps(
significance,
progress_percentage
)
}
def generate_test_report(
self,
test_id: str,
final_results: Dict[str, Any]
) -> Dict[str, Any]:
"""
Generate final test report with insights and recommendations.
Args:
test_id: Test identifier
final_results: Final test results
Returns:
Comprehensive test report
"""
test = next((t for t in self.active_tests if t['test_id'] == test_id), None)
if not test:
return {'error': f'Test {test_id} not found'}
significance = self.calculate_significance(
final_results['variant_a_conversions'],
final_results['variant_a_visitors'],
final_results['variant_b_conversions'],
final_results['variant_b_visitors']
)
# Generate insights
insights = self._generate_test_insights(
test,
significance,
final_results
)
# Implementation plan
implementation_plan = self._create_implementation_plan(
test,
significance
)
return {
'test_summary': {
'test_id': test_id,
'test_type': test['test_type'],
'hypothesis': test['hypothesis'],
'duration_days': final_results.get('duration_days', 'N/A')
},
'results': significance,
'insights': insights,
'implementation_plan': implementation_plan,
'learnings': self._extract_learnings(test, significance)
}
def _generate_test_id(self, test_type: str) -> str:
"""Generate unique test ID."""
import time
timestamp = int(time.time())
return f"{test_type}_{timestamp}"
def _get_secondary_metrics(self, test_type: str) -> List[str]:
"""Get secondary metrics to track for test type."""
metrics_map = {
'icon': ['tap_through_rate', 'impression_count', 'brand_recall'],
'screenshot': ['tap_through_rate', 'time_on_page', 'scroll_depth'],
'title': ['impression_count', 'tap_through_rate', 'search_visibility'],
'description': ['time_on_page', 'scroll_depth', 'tap_through_rate']
}
return metrics_map.get(test_type, ['tap_through_rate'])
def _get_test_best_practices(self, test_type: str) -> List[str]:
"""Get best practices for specific test type."""
practices_map = {
'icon': [
'Test only one element at a time (color vs. style vs. symbolism)',
'Ensure icon is recognizable at small sizes (60x60px)',
'Consider cultural context for global audience',
'Test against top competitor icons'
],
'screenshot': [
'Test order of screenshots (users see first 2-3)',
'Use captions to tell story',
'Show key features and benefits',
'Test with and without device frames'
],
'title': [
'Test keyword variations, not major rebrand',
'Keep brand name consistent',
'Ensure title fits within character limits',
'Test on both search and browse contexts'
],
'description': [
'Test structure (bullet points vs. paragraphs)',
'Test call-to-action placement',
'Test feature vs. benefit focus',
'Maintain keyword density'
]
}
return practices_map.get(test_type, ['Test one variable at a time'])
def _estimate_test_duration(
self,
required_sample_size: int,
baseline_conversion: float
) -> Dict[str, Any]:
"""Estimate test duration based on typical traffic levels."""
# Assume different daily traffic scenarios
traffic_scenarios = {
'low': 100, # 100 page views/day
'medium': 1000, # 1000 page views/day
'high': 10000 # 10000 page views/day
}
estimates = {}
for scenario, daily_views in traffic_scenarios.items():
days = math.ceil(required_sample_size / daily_views)
estimates[scenario] = {
'daily_page_views': daily_views,
'estimated_days': days,
'estimated_weeks': round(days / 7, 1)
}
return estimates
def _generate_sample_size_recommendations(
self,
sample_size: int,
duration_estimates: Dict[str, Any]
) -> List[str]:
"""Generate recommendations based on sample size."""
recommendations = []
if sample_size > 50000:
recommendations.append(
"Large sample size required - consider testing smaller effect size or increasing traffic"
)
if duration_estimates['medium']['estimated_days'] > 30:
recommendations.append(
"Long test duration - consider higher minimum detectable effect or focus on high-impact changes"
)
if duration_estimates['low']['estimated_days'] > 60:
recommendations.append(
"Insufficient traffic for reliable testing - consider user acquisition or broader targeting"
)
if not recommendations:
recommendations.append("Sample size and duration are reasonable for this test")
return recommendations
def _get_z_score(self, percentile: float) -> float:
"""Get z-score for given percentile (approximation)."""
# Common z-scores
z_scores = {
0.80: 0.84,
0.85: 1.04,
0.90: 1.28,
0.95: 1.645,
0.975: 1.96,
0.99: 2.33
}
return z_scores.get(percentile, 1.96)
def _standard_normal_cdf(self, z: float) -> float:
"""Approximate standard normal cumulative distribution function."""
# Using error function approximation
t = 1.0 / (1.0 + 0.2316419 * abs(z))
d = 0.3989423 * math.exp(-z * z / 2.0)
p = d * t * (0.3193815 + t * (-0.3565638 + t * (1.781478 + t * (-1.821256 + t * 1.330274))))
if z > 0:
return 1.0 - p
else:
return p
def _generate_test_decision(
self,
improvement: float,
is_significant_95: bool,
is_significant_90: bool,
total_visitors: int
) -> Dict[str, Any]:
"""Generate test decision and recommendation."""
if total_visitors < 1000:
return {
'decision': 'continue',
'rationale': 'Insufficient data - continue test to reach minimum sample size',
'action': 'Keep test running'
}
if is_significant_95:
if improvement > 0:
return {
'decision': 'implement_b',
'rationale': f'Variant B shows {improvement*100:.1f}% improvement with 95% confidence',
'action': 'Implement Variant B'
}
else:
return {
'decision': 'keep_a',
'rationale': 'Variant A performs better with 95% confidence',
'action': 'Keep current version (A)'
}
elif is_significant_90:
if improvement > 0:
return {
'decision': 'implement_b_cautiously',
'rationale': f'Variant B shows {improvement*100:.1f}% improvement with 90% confidence',
'action': 'Consider implementing B, monitor closely'
}
else:
return {
'decision': 'keep_a',
'rationale': 'Variant A performs better with 90% confidence',
'action': 'Keep current version (A)'
}
else:
return {
'decision': 'inconclusive',
'rationale': 'No statistically significant difference detected',
'action': 'Either keep A or test different hypothesis'
}
def _generate_tracking_recommendations(
self,
significance: Dict[str, Any],
progress: float,
test_type: str
) -> List[str]:
"""Generate recommendations for ongoing test."""
recommendations = []
if progress < 50:
recommendations.append(
f"Test is {progress:.0f}% complete - continue collecting data"
)
if progress >= 100:
if significance['statistical_analysis']['is_significant_95']:
recommendations.append(
"Sufficient data collected with significant results - ready to conclude test"
)
else:
recommendations.append(
"Sample size reached but no significant difference - consider extending test or concluding"
)
return recommendations
def _determine_next_steps(
self,
significance: Dict[str, Any],
progress: float
) -> str:
"""Determine next steps for test."""
if progress < 100:
return f"Continue test until reaching 100% sample size (currently {progress:.0f}%)"
decision = significance.get('decision', {}).get('decision', 'inconclusive')
if decision == 'implement_b':
return "Implement Variant B and monitor metrics for 2 weeks"
elif decision == 'keep_a':
return "Keep Variant A and design new test with different hypothesis"
else:
return "Test inconclusive - either keep A or design new test"
def _generate_test_insights(
self,
test: Dict[str, Any],
significance: Dict[str, Any],
results: Dict[str, Any]
) -> List[str]:
"""Generate insights from test results."""
insights = []
improvement = significance['improvement']['relative_percentage']
if significance['statistical_analysis']['is_significant_95']:
insights.append(
f"Strong evidence: Variant B {'improved' if improvement > 0 else 'decreased'} "
f"conversion by {abs(improvement):.1f}% with 95% confidence"
)
insights.append(
f"Tested {test['test_type']} changes: {test['hypothesis']}"
)
# Add context-specific insights
if test['test_type'] == 'icon' and improvement > 5:
insights.append(
"Icon change had substantial impact - visual first impression is critical"
)
return insights
def _create_implementation_plan(
self,
test: Dict[str, Any],
significance: Dict[str, Any]
) -> List[Dict[str, str]]:
"""Create implementation plan for winning variant."""
plan = []
if significance.get('decision', {}).get('decision') == 'implement_b':
plan.append({
'step': '1. Update store listing',
'details': f"Replace {test['test_type']} with Variant B across all platforms"
})
plan.append({
'step': '2. Monitor metrics',
'details': 'Track conversion rate for 2 weeks to confirm sustained improvement'
})
plan.append({
'step': '3. Document learnings',
'details': 'Record insights for future optimization'
})
return plan
def _extract_learnings(
self,
test: Dict[str, Any],
significance: Dict[str, Any]
) -> List[str]:
"""Extract key learnings from test."""
learnings = []
improvement = significance['improvement']['relative_percentage']
learnings.append(
f"Testing {test['test_type']} can yield {abs(improvement):.1f}% conversion change"
)
if test['test_type'] == 'title':
learnings.append(
"Title changes affect search visibility and user perception"
)
elif test['test_type'] == 'screenshot':
learnings.append(
"First 2-3 screenshots are critical for conversion"
)
return learnings
def plan_ab_test(
test_type: str,
variant_a: Dict[str, Any],
variant_b: Dict[str, Any],
hypothesis: str,
baseline_conversion: float
) -> Dict[str, Any]:
"""
Convenience function to plan an A/B test.
Args:
test_type: Type of test
variant_a: Control variant
variant_b: Test variant
hypothesis: Test hypothesis
baseline_conversion: Current conversion rate
Returns:
Complete test plan
"""
planner = ABTestPlanner()
test_design = planner.design_test(
test_type,
variant_a,
variant_b,
hypothesis
)
sample_size = planner.calculate_sample_size(
baseline_conversion,
planner.MIN_EFFECT_SIZES.get(test_type, 0.05)
)
return {
'test_design': test_design,
'sample_size_requirements': sample_size
}

482
.agents/skills/app-store-optimization/scripts/aso_scorer.py Normal file
View File

@@ -0,0 +1,482 @@
"""
ASO scoring module for App Store Optimization.
Calculates comprehensive ASO health score across multiple dimensions.
"""
from typing import Dict, List, Any, Optional
class ASOScorer:
"""Calculates overall ASO health score and provides recommendations."""
# Score weights for different components (total = 100)
WEIGHTS = {
'metadata_quality': 25,
'ratings_reviews': 25,
'keyword_performance': 25,
'conversion_metrics': 25
}
# Benchmarks for scoring
BENCHMARKS = {
'title_keyword_usage': {'min': 1, 'target': 2},
'description_length': {'min': 500, 'target': 2000},
'keyword_density': {'min': 2, 'optimal': 5, 'max': 8},
'average_rating': {'min': 3.5, 'target': 4.5},
'ratings_count': {'min': 100, 'target': 5000},
'keywords_top_10': {'min': 2, 'target': 10},
'keywords_top_50': {'min': 5, 'target': 20},
'conversion_rate': {'min': 0.02, 'target': 0.10}
}
def __init__(self):
"""Initialize ASO scorer."""
self.score_breakdown = {}
def calculate_overall_score(
self,
metadata: Dict[str, Any],
ratings: Dict[str, Any],
keyword_performance: Dict[str, Any],
conversion: Dict[str, Any]
) -> Dict[str, Any]:
"""
Calculate comprehensive ASO score (0-100).
Args:
metadata: Title, description quality metrics
ratings: Rating average and count
keyword_performance: Keyword ranking data
conversion: Impression-to-install metrics
Returns:
Overall score with detailed breakdown
"""
# Calculate component scores
metadata_score = self.score_metadata_quality(metadata)
ratings_score = self.score_ratings_reviews(ratings)
keyword_score = self.score_keyword_performance(keyword_performance)
conversion_score = self.score_conversion_metrics(conversion)
# Calculate weighted overall score
overall_score = (
metadata_score * (self.WEIGHTS['metadata_quality'] / 100) +
ratings_score * (self.WEIGHTS['ratings_reviews'] / 100) +
keyword_score * (self.WEIGHTS['keyword_performance'] / 100) +
conversion_score * (self.WEIGHTS['conversion_metrics'] / 100)
)
# Store breakdown
self.score_breakdown = {
'metadata_quality': {
'score': metadata_score,
'weight': self.WEIGHTS['metadata_quality'],
'weighted_contribution': round(metadata_score * (self.WEIGHTS['metadata_quality'] / 100), 1)
},
'ratings_reviews': {
'score': ratings_score,
'weight': self.WEIGHTS['ratings_reviews'],
'weighted_contribution': round(ratings_score * (self.WEIGHTS['ratings_reviews'] / 100), 1)
},
'keyword_performance': {
'score': keyword_score,
'weight': self.WEIGHTS['keyword_performance'],
'weighted_contribution': round(keyword_score * (self.WEIGHTS['keyword_performance'] / 100), 1)
},
'conversion_metrics': {
'score': conversion_score,
'weight': self.WEIGHTS['conversion_metrics'],
'weighted_contribution': round(conversion_score * (self.WEIGHTS['conversion_metrics'] / 100), 1)
}
}
# Generate recommendations
recommendations = self.generate_recommendations(
metadata_score,
ratings_score,
keyword_score,
conversion_score
)
# Assess overall health
health_status = self._assess_health_status(overall_score)
return {
'overall_score': round(overall_score, 1),
'health_status': health_status,
'score_breakdown': self.score_breakdown,
'recommendations': recommendations,
'priority_actions': self._prioritize_actions(recommendations),
'strengths': self._identify_strengths(self.score_breakdown),
'weaknesses': self._identify_weaknesses(self.score_breakdown)
}
def score_metadata_quality(self, metadata: Dict[str, Any]) -> float:
"""
Score metadata quality (0-100).
Evaluates:
- Title optimization
- Description quality
- Keyword usage
"""
scores = []
# Title score (0-35 points)
title_keywords = metadata.get('title_keyword_count', 0)
title_length = metadata.get('title_length', 0)
title_score = 0
if title_keywords >= self.BENCHMARKS['title_keyword_usage']['target']:
title_score = 35
elif title_keywords >= self.BENCHMARKS['title_keyword_usage']['min']:
title_score = 25
else:
title_score = 10
# Adjust for title length usage
if title_length > 25: # Using most of available space
title_score += 0
else:
title_score -= 5
scores.append(min(title_score, 35))
# Description score (0-35 points)
desc_length = metadata.get('description_length', 0)
desc_quality = metadata.get('description_quality', 0.0) # 0-1 scale
desc_score = 0
if desc_length >= self.BENCHMARKS['description_length']['target']:
desc_score = 25
elif desc_length >= self.BENCHMARKS['description_length']['min']:
desc_score = 15
else:
desc_score = 5
# Add quality bonus
desc_score += desc_quality * 10
scores.append(min(desc_score, 35))
# Keyword density score (0-30 points)
keyword_density = metadata.get('keyword_density', 0.0)
if self.BENCHMARKS['keyword_density']['min'] <= keyword_density <= self.BENCHMARKS['keyword_density']['optimal']:
density_score = 30
elif keyword_density < self.BENCHMARKS['keyword_density']['min']:
# Too low - proportional scoring
density_score = (keyword_density / self.BENCHMARKS['keyword_density']['min']) * 20
else:
# Too high (keyword stuffing) - penalty
excess = keyword_density - self.BENCHMARKS['keyword_density']['optimal']
density_score = max(30 - (excess * 5), 0)
scores.append(density_score)
return round(sum(scores), 1)
def score_ratings_reviews(self, ratings: Dict[str, Any]) -> float:
"""
Score ratings and reviews (0-100).
Evaluates:
- Average rating
- Total ratings count
- Review velocity
"""
average_rating = ratings.get('average_rating', 0.0)
total_ratings = ratings.get('total_ratings', 0)
recent_ratings = ratings.get('recent_ratings_30d', 0)
# Rating quality score (0-50 points)
if average_rating >= self.BENCHMARKS['average_rating']['target']:
rating_quality_score = 50
elif average_rating >= self.BENCHMARKS['average_rating']['min']:
# Proportional scoring between min and target
proportion = (average_rating - self.BENCHMARKS['average_rating']['min']) / \
(self.BENCHMARKS['average_rating']['target'] - self.BENCHMARKS['average_rating']['min'])
rating_quality_score = 30 + (proportion * 20)
elif average_rating >= 3.0:
rating_quality_score = 20
else:
rating_quality_score = 10
# Rating volume score (0-30 points)
if total_ratings >= self.BENCHMARKS['ratings_count']['target']:
rating_volume_score = 30
elif total_ratings >= self.BENCHMARKS['ratings_count']['min']:
# Proportional scoring
proportion = (total_ratings - self.BENCHMARKS['ratings_count']['min']) / \
(self.BENCHMARKS['ratings_count']['target'] - self.BENCHMARKS['ratings_count']['min'])
rating_volume_score = 15 + (proportion * 15)
else:
# Very low volume
rating_volume_score = (total_ratings / self.BENCHMARKS['ratings_count']['min']) * 15
# Rating velocity score (0-20 points)
if recent_ratings > 100:
velocity_score = 20
elif recent_ratings > 50:
velocity_score = 15
elif recent_ratings > 10:
velocity_score = 10
else:
velocity_score = 5
total_score = rating_quality_score + rating_volume_score + velocity_score
return round(min(total_score, 100), 1)
def score_keyword_performance(self, keyword_performance: Dict[str, Any]) -> float:
"""
Score keyword ranking performance (0-100).
Evaluates:
- Top 10 rankings
- Top 50 rankings
- Ranking trends
"""
top_10_count = keyword_performance.get('top_10', 0)
top_50_count = keyword_performance.get('top_50', 0)
top_100_count = keyword_performance.get('top_100', 0)
improving_keywords = keyword_performance.get('improving_keywords', 0)
# Top 10 score (0-50 points) - most valuable rankings
if top_10_count >= self.BENCHMARKS['keywords_top_10']['target']:
top_10_score = 50
elif top_10_count >= self.BENCHMARKS['keywords_top_10']['min']:
proportion = (top_10_count - self.BENCHMARKS['keywords_top_10']['min']) / \
(self.BENCHMARKS['keywords_top_10']['target'] - self.BENCHMARKS['keywords_top_10']['min'])
top_10_score = 25 + (proportion * 25)
else:
top_10_score = (top_10_count / self.BENCHMARKS['keywords_top_10']['min']) * 25
# Top 50 score (0-30 points)
if top_50_count >= self.BENCHMARKS['keywords_top_50']['target']:
top_50_score = 30
elif top_50_count >= self.BENCHMARKS['keywords_top_50']['min']:
proportion = (top_50_count - self.BENCHMARKS['keywords_top_50']['min']) / \
(self.BENCHMARKS['keywords_top_50']['target'] - self.BENCHMARKS['keywords_top_50']['min'])
top_50_score = 15 + (proportion * 15)
else:
top_50_score = (top_50_count / self.BENCHMARKS['keywords_top_50']['min']) * 15
# Coverage score (0-10 points) - based on top 100
coverage_score = min((top_100_count / 30) * 10, 10)
# Trend score (0-10 points) - are rankings improving?
if improving_keywords > 5:
trend_score = 10
elif improving_keywords > 0:
trend_score = 5
else:
trend_score = 0
total_score = top_10_score + top_50_score + coverage_score + trend_score
return round(min(total_score, 100), 1)
def score_conversion_metrics(self, conversion: Dict[str, Any]) -> float:
"""
Score conversion performance (0-100).
Evaluates:
- Impression-to-install conversion rate
- Download velocity
"""
conversion_rate = conversion.get('impression_to_install', 0.0)
downloads_30d = conversion.get('downloads_last_30_days', 0)
downloads_trend = conversion.get('downloads_trend', 'stable') # 'up', 'stable', 'down'
# Conversion rate score (0-70 points)
if conversion_rate >= self.BENCHMARKS['conversion_rate']['target']:
conversion_score = 70
elif conversion_rate >= self.BENCHMARKS['conversion_rate']['min']:
proportion = (conversion_rate - self.BENCHMARKS['conversion_rate']['min']) / \
(self.BENCHMARKS['conversion_rate']['target'] - self.BENCHMARKS['conversion_rate']['min'])
conversion_score = 35 + (proportion * 35)
else:
conversion_score = (conversion_rate / self.BENCHMARKS['conversion_rate']['min']) * 35
# Download velocity score (0-20 points)
if downloads_30d > 10000:
velocity_score = 20
elif downloads_30d > 1000:
velocity_score = 15
elif downloads_30d > 100:
velocity_score = 10
else:
velocity_score = 5
# Trend bonus (0-10 points)
if downloads_trend == 'up':
trend_score = 10
elif downloads_trend == 'stable':
trend_score = 5
else:
trend_score = 0
total_score = conversion_score + velocity_score + trend_score
return round(min(total_score, 100), 1)
def generate_recommendations(
self,
metadata_score: float,
ratings_score: float,
keyword_score: float,
conversion_score: float
) -> List[Dict[str, Any]]:
"""Generate prioritized recommendations based on scores."""
recommendations = []
# Metadata recommendations
if metadata_score < 60:
recommendations.append({
'category': 'metadata_quality',
'priority': 'high',
'action': 'Optimize app title and description',
'details': 'Add more keywords to title, expand description to 1500-2000 characters, improve keyword density to 3-5%',
'expected_impact': 'Improve discoverability and ranking potential'
})
elif metadata_score < 80:
recommendations.append({
'category': 'metadata_quality',
'priority': 'medium',
'action': 'Refine metadata for better keyword targeting',
'details': 'Test variations of title/subtitle, optimize keyword field for Apple',
'expected_impact': 'Incremental ranking improvements'
})
# Ratings recommendations
if ratings_score < 60:
recommendations.append({
'category': 'ratings_reviews',
'priority': 'high',
'action': 'Improve rating quality and volume',
'details': 'Address top user complaints, implement in-app rating prompts, respond to negative reviews',
'expected_impact': 'Better conversion rates and trust signals'
})
elif ratings_score < 80:
recommendations.append({
'category': 'ratings_reviews',
'priority': 'medium',
'action': 'Increase rating velocity',
'details': 'Optimize timing of rating requests, encourage satisfied users to rate',
'expected_impact': 'Sustained rating quality'
})
# Keyword performance recommendations
if keyword_score < 60:
recommendations.append({
'category': 'keyword_performance',
'priority': 'high',
'action': 'Improve keyword rankings',
'details': 'Target long-tail keywords with lower competition, update metadata with high-potential keywords, build backlinks',
'expected_impact': 'Significant improvement in organic visibility'
})
elif keyword_score < 80:
recommendations.append({
'category': 'keyword_performance',
'priority': 'medium',
'action': 'Expand keyword coverage',
'details': 'Target additional related keywords, test seasonal keywords, localize for new markets',
'expected_impact': 'Broader reach and more discovery opportunities'
})
# Conversion recommendations
if conversion_score < 60:
recommendations.append({
'category': 'conversion_metrics',
'priority': 'high',
'action': 'Optimize store listing for conversions',
'details': 'Improve screenshots and icon, strengthen value proposition in description, add video preview',
'expected_impact': 'Higher impression-to-install conversion'
})
elif conversion_score < 80:
recommendations.append({
'category': 'conversion_metrics',
'priority': 'medium',
'action': 'Test visual asset variations',
'details': 'A/B test different icon designs and screenshot sequences',
'expected_impact': 'Incremental conversion improvements'
})
return recommendations
def _assess_health_status(self, overall_score: float) -> str:
"""Assess overall ASO health status."""
if overall_score >= 80:
return "Excellent - Top-tier ASO performance"
elif overall_score >= 65:
return "Good - Competitive ASO with room for improvement"
elif overall_score >= 50:
return "Fair - Needs strategic improvements"
else:
return "Poor - Requires immediate ASO overhaul"
def _prioritize_actions(
self,
recommendations: List[Dict[str, Any]]
) -> List[Dict[str, Any]]:
"""Prioritize actions by impact and urgency."""
# Sort by priority (high first) and expected impact
priority_order = {'high': 0, 'medium': 1, 'low': 2}
sorted_recommendations = sorted(
recommendations,
key=lambda x: priority_order[x['priority']]
)
return sorted_recommendations[:3] # Top 3 priority actions
def _identify_strengths(self, score_breakdown: Dict[str, Any]) -> List[str]:
"""Identify areas of strength (scores >= 75)."""
strengths = []
for category, data in score_breakdown.items():
if data['score'] >= 75:
strengths.append(
f"{category.replace('_', ' ').title()}: {data['score']}/100"
)
return strengths if strengths else ["Focus on building strengths across all areas"]
def _identify_weaknesses(self, score_breakdown: Dict[str, Any]) -> List[str]:
"""Identify areas needing improvement (scores < 60)."""
weaknesses = []
for category, data in score_breakdown.items():
if data['score'] < 60:
weaknesses.append(
f"{category.replace('_', ' ').title()}: {data['score']}/100 - needs improvement"
)
return weaknesses if weaknesses else ["All areas performing adequately"]
def calculate_aso_score(
metadata: Dict[str, Any],
ratings: Dict[str, Any],
keyword_performance: Dict[str, Any],
conversion: Dict[str, Any]
) -> Dict[str, Any]:
"""
Convenience function to calculate ASO score.
Args:
metadata: Metadata quality metrics
ratings: Ratings data
keyword_performance: Keyword ranking data
conversion: Conversion metrics
Returns:
Complete ASO score report
"""
scorer = ASOScorer()
return scorer.calculate_overall_score(
metadata,
ratings,
keyword_performance,
conversion
)

577
.agents/skills/app-store-optimization/scripts/competitor_analyzer.py Normal file
View File

@@ -0,0 +1,577 @@
"""
Competitor analysis module for App Store Optimization.
Analyzes top competitors' ASO strategies and identifies opportunities.
"""
from typing import Dict, List, Any, Optional
from collections import Counter
import re
class CompetitorAnalyzer:
"""Analyzes competitor apps to identify ASO opportunities."""
def __init__(self, category: str, platform: str = 'apple'):
"""
Initialize competitor analyzer.
Args:
category: App category (e.g., "Productivity", "Games")
platform: 'apple' or 'google'
"""
self.category = category
self.platform = platform
self.competitors = []
def analyze_competitor(
self,
app_data: Dict[str, Any]
) -> Dict[str, Any]:
"""
Analyze a single competitor's ASO strategy.
Args:
app_data: Dictionary with app_name, title, description, rating, ratings_count, keywords
Returns:
Comprehensive competitor analysis
"""
app_name = app_data.get('app_name', '')
title = app_data.get('title', '')
description = app_data.get('description', '')
rating = app_data.get('rating', 0.0)
ratings_count = app_data.get('ratings_count', 0)
keywords = app_data.get('keywords', [])
analysis = {
'app_name': app_name,
'title_analysis': self._analyze_title(title),
'description_analysis': self._analyze_description(description),
'keyword_strategy': self._extract_keyword_strategy(title, description, keywords),
'rating_metrics': {
'rating': rating,
'ratings_count': ratings_count,
'rating_quality': self._assess_rating_quality(rating, ratings_count)
},
'competitive_strength': self._calculate_competitive_strength(
rating,
ratings_count,
len(description)
),
'key_differentiators': self._identify_differentiators(description)
}
self.competitors.append(analysis)
return analysis
def compare_competitors(
self,
competitors_data: List[Dict[str, Any]]
) -> Dict[str, Any]:
"""
Compare multiple competitors and identify patterns.
Args:
competitors_data: List of competitor data dictionaries
Returns:
Comparative analysis with insights
"""
# Analyze each competitor
analyses = []
for comp_data in competitors_data:
analysis = self.analyze_competitor(comp_data)
analyses.append(analysis)
# Extract common keywords across competitors
all_keywords = []
for analysis in analyses:
all_keywords.extend(analysis['keyword_strategy']['primary_keywords'])
common_keywords = self._find_common_keywords(all_keywords)
# Identify keyword gaps (used by some but not all)
keyword_gaps = self._identify_keyword_gaps(analyses)
# Rank competitors by strength
ranked_competitors = sorted(
analyses,
key=lambda x: x['competitive_strength'],
reverse=True
)
# Analyze rating distribution
rating_analysis = self._analyze_rating_distribution(analyses)
# Identify best practices
best_practices = self._identify_best_practices(ranked_competitors)
return {
'category': self.category,
'platform': self.platform,
'competitors_analyzed': len(analyses),
'ranked_competitors': ranked_competitors,
'common_keywords': common_keywords,
'keyword_gaps': keyword_gaps,
'rating_analysis': rating_analysis,
'best_practices': best_practices,
'opportunities': self._identify_opportunities(
analyses,
common_keywords,
keyword_gaps
)
}
def identify_gaps(
self,
your_app_data: Dict[str, Any],
competitors_data: List[Dict[str, Any]]
) -> Dict[str, Any]:
"""
Identify gaps between your app and competitors.
Args:
your_app_data: Your app's data
competitors_data: List of competitor data
Returns:
Gap analysis with actionable recommendations
"""
# Analyze your app
your_analysis = self.analyze_competitor(your_app_data)
# Analyze competitors
competitor_comparison = self.compare_competitors(competitors_data)
# Identify keyword gaps
your_keywords = set(your_analysis['keyword_strategy']['primary_keywords'])
competitor_keywords = set(competitor_comparison['common_keywords'])
missing_keywords = competitor_keywords - your_keywords
# Identify rating gap
avg_competitor_rating = competitor_comparison['rating_analysis']['average_rating']
rating_gap = avg_competitor_rating - your_analysis['rating_metrics']['rating']
# Identify description length gap
avg_competitor_desc_length = sum(
len(comp['description_analysis']['text'])
for comp in competitor_comparison['ranked_competitors']
) / len(competitor_comparison['ranked_competitors'])
your_desc_length = len(your_analysis['description_analysis']['text'])
desc_length_gap = avg_competitor_desc_length - your_desc_length
return {
'your_app': your_analysis,
'keyword_gaps': {
'missing_keywords': list(missing_keywords)[:10],
'recommendations': self._generate_keyword_recommendations(missing_keywords)
},
'rating_gap': {
'your_rating': your_analysis['rating_metrics']['rating'],
'average_competitor_rating': avg_competitor_rating,
'gap': round(rating_gap, 2),
'action_items': self._generate_rating_improvement_actions(rating_gap)
},
'content_gap': {
'your_description_length': your_desc_length,
'average_competitor_length': int(avg_competitor_desc_length),
'gap': int(desc_length_gap),
'recommendations': self._generate_content_recommendations(desc_length_gap)
},
'competitive_positioning': self._assess_competitive_position(
your_analysis,
competitor_comparison
)
}
def _analyze_title(self, title: str) -> Dict[str, Any]:
"""Analyze title structure and keyword usage."""
parts = re.split(r'[-:|]', title)
return {
'title': title,
'length': len(title),
'has_brand': len(parts) > 0,
'has_keywords': len(parts) > 1,
'components': [part.strip() for part in parts],
'word_count': len(title.split()),
'strategy': 'brand_plus_keywords' if len(parts) > 1 else 'brand_only'
}
def _analyze_description(self, description: str) -> Dict[str, Any]:
"""Analyze description structure and content."""
lines = description.split('\n')
word_count = len(description.split())
# Check for structural elements
has_bullet_points = '•' in description or '*' in description
has_sections = any(line.isupper() for line in lines if len(line) > 0)
has_call_to_action = any(
cta in description.lower()
for cta in ['download', 'try', 'get', 'start', 'join']
)
# Extract features mentioned
features = self._extract_features(description)
return {
'text': description,
'length': len(description),
'word_count': word_count,
'structure': {
'has_bullet_points': has_bullet_points,
'has_sections': has_sections,
'has_call_to_action': has_call_to_action
},
'features_mentioned': features,
'readability': 'good' if 50 <= word_count <= 300 else 'needs_improvement'
}
def _extract_keyword_strategy(
self,
title: str,
description: str,
explicit_keywords: List[str]
) -> Dict[str, Any]:
"""Extract keyword strategy from metadata."""
# Extract keywords from title
title_keywords = [word.lower() for word in title.split() if len(word) > 3]
# Extract frequently used words from description
desc_words = re.findall(r'\b\w{4,}\b', description.lower())
word_freq = Counter(desc_words)
frequent_words = [word for word, count in word_freq.most_common(15) if count > 2]
# Combine with explicit keywords
all_keywords = list(set(title_keywords + frequent_words + explicit_keywords))
return {
'primary_keywords': title_keywords,
'description_keywords': frequent_words[:10],
'explicit_keywords': explicit_keywords,
'total_unique_keywords': len(all_keywords),
'keyword_focus': self._assess_keyword_focus(title_keywords, frequent_words)
}
def _assess_rating_quality(self, rating: float, ratings_count: int) -> str:
"""Assess the quality of ratings."""
if ratings_count < 100:
return 'insufficient_data'
elif rating >= 4.5 and ratings_count > 1000:
return 'excellent'
elif rating >= 4.0 and ratings_count > 500:
return 'good'
elif rating >= 3.5:
return 'average'
else:
return 'poor'
def _calculate_competitive_strength(
self,
rating: float,
ratings_count: int,
description_length: int
) -> float:
"""
Calculate overall competitive strength (0-100).
Factors:
- Rating quality (40%)
- Rating volume (30%)
- Metadata quality (30%)
"""
# Rating quality score (0-40)
rating_score = (rating / 5.0) * 40
# Rating volume score (0-30)
volume_score = min((ratings_count / 10000) * 30, 30)
# Metadata quality score (0-30)
metadata_score = min((description_length / 2000) * 30, 30)
total_score = rating_score + volume_score + metadata_score
return round(total_score, 1)
def _identify_differentiators(self, description: str) -> List[str]:
"""Identify key differentiators from description."""
differentiator_keywords = [
'unique', 'only', 'first', 'best', 'leading', 'exclusive',
'revolutionary', 'innovative', 'patent', 'award'
]
differentiators = []
sentences = description.split('.')
for sentence in sentences:
sentence_lower = sentence.lower()
if any(keyword in sentence_lower for keyword in differentiator_keywords):
differentiators.append(sentence.strip())
return differentiators[:5]
def _find_common_keywords(self, all_keywords: List[str]) -> List[str]:
"""Find keywords used by multiple competitors."""
keyword_counts = Counter(all_keywords)
# Return keywords used by at least 2 competitors
common = [kw for kw, count in keyword_counts.items() if count >= 2]
return sorted(common, key=lambda x: keyword_counts[x], reverse=True)[:20]
def _identify_keyword_gaps(self, analyses: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
"""Identify keywords used by some competitors but not others."""
all_keywords_by_app = {}
for analysis in analyses:
app_name = analysis['app_name']
keywords = analysis['keyword_strategy']['primary_keywords']
all_keywords_by_app[app_name] = set(keywords)
# Find keywords used by some but not all
all_keywords_set = set()
for keywords in all_keywords_by_app.values():
all_keywords_set.update(keywords)
gaps = []
for keyword in all_keywords_set:
using_apps = [
app for app, keywords in all_keywords_by_app.items()
if keyword in keywords
]
if 1 < len(using_apps) < len(analyses):
gaps.append({
'keyword': keyword,
'used_by': using_apps,
'usage_percentage': round(len(using_apps) / len(analyses) * 100, 1)
})
return sorted(gaps, key=lambda x: x['usage_percentage'], reverse=True)[:15]
def _analyze_rating_distribution(self, analyses: List[Dict[str, Any]]) -> Dict[str, Any]:
"""Analyze rating distribution across competitors."""
ratings = [a['rating_metrics']['rating'] for a in analyses]
ratings_counts = [a['rating_metrics']['ratings_count'] for a in analyses]
return {
'average_rating': round(sum(ratings) / len(ratings), 2),
'highest_rating': max(ratings),
'lowest_rating': min(ratings),
'average_ratings_count': int(sum(ratings_counts) / len(ratings_counts)),
'total_ratings_in_category': sum(ratings_counts)
}
def _identify_best_practices(self, ranked_competitors: List[Dict[str, Any]]) -> List[str]:
"""Identify best practices from top competitors."""
if not ranked_competitors:
return []
top_competitor = ranked_competitors[0]
practices = []
# Title strategy
title_analysis = top_competitor['title_analysis']
if title_analysis['has_keywords']:
practices.append(
f"Title Strategy: Include primary keyword in title (e.g., '{title_analysis['title']}')"
)
# Description structure
desc_analysis = top_competitor['description_analysis']
if desc_analysis['structure']['has_bullet_points']:
practices.append("Description: Use bullet points to highlight key features")
if desc_analysis['structure']['has_sections']:
practices.append("Description: Organize content with clear section headers")
# Rating strategy
rating_quality = top_competitor['rating_metrics']['rating_quality']
if rating_quality in ['excellent', 'good']:
practices.append(
f"Ratings: Maintain high rating quality ({top_competitor['rating_metrics']['rating']}★) "
f"with significant volume ({top_competitor['rating_metrics']['ratings_count']} ratings)"
)
return practices[:5]
def _identify_opportunities(
self,
analyses: List[Dict[str, Any]],
common_keywords: List[str],
keyword_gaps: List[Dict[str, Any]]
) -> List[str]:
"""Identify ASO opportunities based on competitive analysis."""
opportunities = []
# Keyword opportunities from gaps
if keyword_gaps:
underutilized_keywords = [
gap['keyword'] for gap in keyword_gaps
if gap['usage_percentage'] < 50
]
if underutilized_keywords:
opportunities.append(
f"Target underutilized keywords: {', '.join(underutilized_keywords[:5])}"
)
# Rating opportunity
avg_rating = sum(a['rating_metrics']['rating'] for a in analyses) / len(analyses)
if avg_rating < 4.5:
opportunities.append(
f"Category average rating is {avg_rating:.1f} - opportunity to differentiate with higher ratings"
)
# Content depth opportunity
avg_desc_length = sum(
a['description_analysis']['length'] for a in analyses
) / len(analyses)
if avg_desc_length < 1500:
opportunities.append(
"Competitors have relatively short descriptions - opportunity to provide more comprehensive information"
)
return opportunities[:5]
def _extract_features(self, description: str) -> List[str]:
"""Extract feature mentions from description."""
# Look for bullet points or numbered lists
lines = description.split('\n')
features = []
for line in lines:
line = line.strip()
# Check if line starts with bullet or number
if line and (line[0] in ['•', '*', '-', '✓'] or line[0].isdigit()):
# Clean the line
cleaned = re.sub(r'^[•*\-✓\d.)\s]+', '', line)
if cleaned:
features.append(cleaned)
return features[:10]
def _assess_keyword_focus(
self,
title_keywords: List[str],
description_keywords: List[str]
) -> str:
"""Assess keyword focus strategy."""
overlap = set(title_keywords) & set(description_keywords)
if len(overlap) >= 3:
return 'consistent_focus'
elif len(overlap) >= 1:
return 'moderate_focus'
else:
return 'broad_focus'
def _generate_keyword_recommendations(self, missing_keywords: set) -> List[str]:
"""Generate recommendations for missing keywords."""
if not missing_keywords:
return ["Your keyword coverage is comprehensive"]
recommendations = []
missing_list = list(missing_keywords)[:5]
recommendations.append(
f"Consider adding these competitor keywords: {', '.join(missing_list)}"
)
recommendations.append(
"Test keyword variations in subtitle/promotional text first"
)
recommendations.append(
"Monitor competitor keyword changes monthly"
)
return recommendations
def _generate_rating_improvement_actions(self, rating_gap: float) -> List[str]:
"""Generate actions to improve ratings."""
actions = []
if rating_gap > 0.5:
actions.append("CRITICAL: Significant rating gap - prioritize user satisfaction improvements")
actions.append("Analyze negative reviews to identify top issues")
actions.append("Implement in-app rating prompts after positive experiences")
actions.append("Respond to all negative reviews professionally")
elif rating_gap > 0.2:
actions.append("Focus on incremental improvements to close rating gap")
actions.append("Optimize timing of rating requests")
else:
actions.append("Ratings are competitive - maintain quality and continue improvements")
return actions
def _generate_content_recommendations(self, desc_length_gap: int) -> List[str]:
"""Generate content recommendations based on length gap."""
recommendations = []
if desc_length_gap > 500:
recommendations.append(
"Expand description to match competitor detail level"
)
recommendations.append(
"Add use case examples and success stories"
)
recommendations.append(
"Include more feature explanations and benefits"
)
elif desc_length_gap < -500:
recommendations.append(
"Consider condensing description for better readability"
)
recommendations.append(
"Focus on most important features first"
)
else:
recommendations.append(
"Description length is competitive"
)
return recommendations
def _assess_competitive_position(
self,
your_analysis: Dict[str, Any],
competitor_comparison: Dict[str, Any]
) -> str:
"""Assess your competitive position."""
your_strength = your_analysis['competitive_strength']
competitors = competitor_comparison['ranked_competitors']
if not competitors:
return "No comparison data available"
# Find where you'd rank
better_than_count = sum(
1 for comp in competitors
if your_strength > comp['competitive_strength']
)
position_percentage = (better_than_count / len(competitors)) * 100
if position_percentage >= 75:
return "Strong Position: Top quartile in competitive strength"
elif position_percentage >= 50:
return "Competitive Position: Above average, opportunities for improvement"
elif position_percentage >= 25:
return "Challenging Position: Below average, requires strategic improvements"
else:
return "Weak Position: Bottom quartile, major ASO overhaul needed"
def analyze_competitor_set(
category: str,
competitors_data: List[Dict[str, Any]],
platform: str = 'apple'
) -> Dict[str, Any]:
"""
Convenience function to analyze a set of competitors.
Args:
category: App category
competitors_data: List of competitor data
platform: 'apple' or 'google'
Returns:
Complete competitive analysis
"""
analyzer = CompetitorAnalyzer(category, platform)
return analyzer.compare_competitors(competitors_data)

406
.agents/skills/app-store-optimization/scripts/keyword_analyzer.py Normal file
View File

@@ -0,0 +1,406 @@
"""
Keyword analysis module for App Store Optimization.
Analyzes keyword search volume, competition, and relevance for app discovery.
"""
from typing import Dict, List, Any, Optional, Tuple
import re
from collections import Counter
class KeywordAnalyzer:
"""Analyzes keywords for ASO effectiveness."""
# Competition level thresholds (based on number of competing apps)
COMPETITION_THRESHOLDS = {
'low': 1000,
'medium': 5000,
'high': 10000
}
# Search volume categories (monthly searches estimate)
VOLUME_CATEGORIES = {
'very_low': 1000,
'low': 5000,
'medium': 20000,
'high': 100000,
'very_high': 500000
}
def __init__(self):
"""Initialize keyword analyzer."""
self.analyzed_keywords = {}
def analyze_keyword(
self,
keyword: str,
search_volume: int = 0,
competing_apps: int = 0,
relevance_score: float = 0.0
) -> Dict[str, Any]:
"""
Analyze a single keyword for ASO potential.
Args:
keyword: The keyword to analyze
search_volume: Estimated monthly search volume
competing_apps: Number of apps competing for this keyword
relevance_score: Relevance to your app (0.0-1.0)
Returns:
Dictionary with keyword analysis
"""
competition_level = self._calculate_competition_level(competing_apps)
volume_category = self._categorize_search_volume(search_volume)
difficulty_score = self._calculate_keyword_difficulty(
search_volume,
competing_apps
)
# Calculate potential score (0-100)
potential_score = self._calculate_potential_score(
search_volume,
competing_apps,
relevance_score
)
analysis = {
'keyword': keyword,
'search_volume': search_volume,
'volume_category': volume_category,
'competing_apps': competing_apps,
'competition_level': competition_level,
'relevance_score': relevance_score,
'difficulty_score': difficulty_score,
'potential_score': potential_score,
'recommendation': self._generate_recommendation(
potential_score,
difficulty_score,
relevance_score
),
'keyword_length': len(keyword.split()),
'is_long_tail': len(keyword.split()) >= 3
}
self.analyzed_keywords[keyword] = analysis
return analysis
def compare_keywords(self, keywords_data: List[Dict[str, Any]]) -> Dict[str, Any]:
"""
Compare multiple keywords and rank by potential.
Args:
keywords_data: List of dicts with keyword, search_volume, competing_apps, relevance_score
Returns:
Comparison report with ranked keywords
"""
analyses = []
for kw_data in keywords_data:
analysis = self.analyze_keyword(
keyword=kw_data['keyword'],
search_volume=kw_data.get('search_volume', 0),
competing_apps=kw_data.get('competing_apps', 0),
relevance_score=kw_data.get('relevance_score', 0.0)
)
analyses.append(analysis)
# Sort by potential score (descending)
ranked_keywords = sorted(
analyses,
key=lambda x: x['potential_score'],
reverse=True
)
# Categorize keywords
primary_keywords = [
kw for kw in ranked_keywords
if kw['potential_score'] >= 70 and kw['relevance_score'] >= 0.8
]
secondary_keywords = [
kw for kw in ranked_keywords
if 50 <= kw['potential_score'] < 70 and kw['relevance_score'] >= 0.6
]
long_tail_keywords = [
kw for kw in ranked_keywords
if kw['is_long_tail'] and kw['relevance_score'] >= 0.7
]
return {
'total_keywords_analyzed': len(analyses),
'ranked_keywords': ranked_keywords,
'primary_keywords': primary_keywords[:5], # Top 5
'secondary_keywords': secondary_keywords[:10], # Top 10
'long_tail_keywords': long_tail_keywords[:10], # Top 10
'summary': self._generate_comparison_summary(
primary_keywords,
secondary_keywords,
long_tail_keywords
)
}
def find_long_tail_opportunities(
self,
base_keyword: str,
modifiers: List[str]
) -> List[Dict[str, Any]]:
"""
Generate long-tail keyword variations.
Args:
base_keyword: Core keyword (e.g., "task manager")
modifiers: List of modifiers (e.g., ["free", "simple", "team"])
Returns:
List of long-tail keyword suggestions
"""
long_tail_keywords = []
# Generate combinations
for modifier in modifiers:
# Modifier + base
variation1 = f"{modifier} {base_keyword}"
long_tail_keywords.append({
'keyword': variation1,
'pattern': 'modifier_base',
'estimated_competition': 'low',
'rationale': f"Less competitive variation of '{base_keyword}'"
})
# Base + modifier
variation2 = f"{base_keyword} {modifier}"
long_tail_keywords.append({
'keyword': variation2,
'pattern': 'base_modifier',
'estimated_competition': 'low',
'rationale': f"Specific use-case variation of '{base_keyword}'"
})
# Add question-based long-tail
question_words = ['how', 'what', 'best', 'top']
for q_word in question_words:
question_keyword = f"{q_word} {base_keyword}"
long_tail_keywords.append({
'keyword': question_keyword,
'pattern': 'question_based',
'estimated_competition': 'very_low',
'rationale': f"Informational search query"
})
return long_tail_keywords
def extract_keywords_from_text(
self,
text: str,
min_word_length: int = 3
) -> List[Tuple[str, int]]:
"""
Extract potential keywords from text (descriptions, reviews).
Args:
text: Text to analyze
min_word_length: Minimum word length to consider
Returns:
List of (keyword, frequency) tuples
"""
# Clean and normalize text
text = text.lower()
text = re.sub(r'[^\w\s]', ' ', text)
# Extract words
words = text.split()
# Filter by length
words = [w for w in words if len(w) >= min_word_length]
# Remove common stop words
stop_words = {
'the', 'and', 'for', 'with', 'this', 'that', 'from', 'have',
'but', 'not', 'you', 'all', 'can', 'are', 'was', 'were', 'been'
}
words = [w for w in words if w not in stop_words]
# Count frequency
word_counts = Counter(words)
# Extract 2-word phrases
phrases = []
for i in range(len(words) - 1):
phrase = f"{words[i]} {words[i+1]}"
phrases.append(phrase)
phrase_counts = Counter(phrases)
# Combine and sort
all_keywords = list(word_counts.items()) + list(phrase_counts.items())
all_keywords.sort(key=lambda x: x[1], reverse=True)
return all_keywords[:50] # Top 50
def calculate_keyword_density(
self,
text: str,
target_keywords: List[str]
) -> Dict[str, float]:
"""
Calculate keyword density in text.
Args:
text: Text to analyze (title, description)
target_keywords: Keywords to check density for
Returns:
Dictionary of keyword: density (percentage)
"""
text_lower = text.lower()
total_words = len(text_lower.split())
densities = {}
for keyword in target_keywords:
keyword_lower = keyword.lower()
occurrences = text_lower.count(keyword_lower)
density = (occurrences / total_words) * 100 if total_words > 0 else 0
densities[keyword] = round(density, 2)
return densities
def _calculate_competition_level(self, competing_apps: int) -> str:
"""Determine competition level based on number of competing apps."""
if competing_apps < self.COMPETITION_THRESHOLDS['low']:
return 'low'
elif competing_apps < self.COMPETITION_THRESHOLDS['medium']:
return 'medium'
elif competing_apps < self.COMPETITION_THRESHOLDS['high']:
return 'high'
else:
return 'very_high'
def _categorize_search_volume(self, search_volume: int) -> str:
"""Categorize search volume."""
if search_volume < self.VOLUME_CATEGORIES['very_low']:
return 'very_low'
elif search_volume < self.VOLUME_CATEGORIES['low']:
return 'low'
elif search_volume < self.VOLUME_CATEGORIES['medium']:
return 'medium'
elif search_volume < self.VOLUME_CATEGORIES['high']:
return 'high'
else:
return 'very_high'
def _calculate_keyword_difficulty(
self,
search_volume: int,
competing_apps: int
) -> float:
"""
Calculate keyword difficulty score (0-100).
Higher score = harder to rank.
"""
if competing_apps == 0:
return 0.0
# Competition factor (0-1)
competition_factor = min(competing_apps / 50000, 1.0)
# Volume factor (0-1) - higher volume = more difficulty
volume_factor = min(search_volume / 1000000, 1.0)
# Difficulty score (weighted average)
difficulty = (competition_factor * 0.7 + volume_factor * 0.3) * 100
return round(difficulty, 1)
def _calculate_potential_score(
self,
search_volume: int,
competing_apps: int,
relevance_score: float
) -> float:
"""
Calculate overall keyword potential (0-100).
Higher score = better opportunity.
"""
# Volume score (0-40 points)
volume_score = min((search_volume / 100000) * 40, 40)
# Competition score (0-30 points) - inverse relationship
if competing_apps > 0:
competition_score = max(30 - (competing_apps / 500), 0)
else:
competition_score = 30
# Relevance score (0-30 points)
relevance_points = relevance_score * 30
total_score = volume_score + competition_score + relevance_points
return round(min(total_score, 100), 1)
def _generate_recommendation(
self,
potential_score: float,
difficulty_score: float,
relevance_score: float
) -> str:
"""Generate actionable recommendation for keyword."""
if relevance_score < 0.5:
return "Low relevance - avoid targeting"
if potential_score >= 70:
return "High priority - target immediately"
elif potential_score >= 50:
if difficulty_score < 50:
return "Good opportunity - include in metadata"
else:
return "Competitive - use in description, not title"
elif potential_score >= 30:
return "Secondary keyword - use for long-tail variations"
else:
return "Low potential - deprioritize"
def _generate_comparison_summary(
self,
primary_keywords: List[Dict[str, Any]],
secondary_keywords: List[Dict[str, Any]],
long_tail_keywords: List[Dict[str, Any]]
) -> str:
"""Generate summary of keyword comparison."""
summary_parts = []
summary_parts.append(
f"Identified {len(primary_keywords)} high-priority primary keywords."
)
if primary_keywords:
top_keyword = primary_keywords[0]['keyword']
summary_parts.append(
f"Top recommendation: '{top_keyword}' (potential score: {primary_keywords[0]['potential_score']})."
)
summary_parts.append(
f"Found {len(secondary_keywords)} secondary keywords for description and metadata."
)
summary_parts.append(
f"Discovered {len(long_tail_keywords)} long-tail opportunities with lower competition."
)
return " ".join(summary_parts)
def analyze_keyword_set(keywords_data: List[Dict[str, Any]]) -> Dict[str, Any]:
"""
Convenience function to analyze a set of keywords.
Args:
keywords_data: List of keyword data dictionaries
Returns:
Complete analysis report
"""
analyzer = KeywordAnalyzer()
return analyzer.compare_keywords(keywords_data)

739
.agents/skills/app-store-optimization/scripts/launch_checklist.py Normal file
View File

@@ -0,0 +1,739 @@
"""
Launch checklist module for App Store Optimization.
Generates comprehensive pre-launch and update checklists.
"""
from typing import Dict, List, Any, Optional
from datetime import datetime, timedelta
class LaunchChecklistGenerator:
"""Generates comprehensive checklists for app launches and updates."""
def __init__(self, platform: str = 'both'):
"""
Initialize checklist generator.
Args:
platform: 'apple', 'google', or 'both'
"""
if platform not in ['apple', 'google', 'both']:
raise ValueError("Platform must be 'apple', 'google', or 'both'")
self.platform = platform
def generate_prelaunch_checklist(
self,
app_info: Dict[str, Any],
launch_date: Optional[str] = None
) -> Dict[str, Any]:
"""
Generate comprehensive pre-launch checklist.
Args:
app_info: App information (name, category, target_audience)
launch_date: Target launch date (YYYY-MM-DD)
Returns:
Complete pre-launch checklist
"""
checklist = {
'app_info': app_info,
'launch_date': launch_date,
'checklists': {}
}
# Generate platform-specific checklists
if self.platform in ['apple', 'both']:
checklist['checklists']['apple'] = self._generate_apple_checklist(app_info)
if self.platform in ['google', 'both']:
checklist['checklists']['google'] = self._generate_google_checklist(app_info)
# Add universal checklist items
checklist['checklists']['universal'] = self._generate_universal_checklist(app_info)
# Generate timeline
if launch_date:
checklist['timeline'] = self._generate_launch_timeline(launch_date)
# Calculate completion status
checklist['summary'] = self._calculate_checklist_summary(checklist['checklists'])
return checklist
def validate_app_store_compliance(
self,
app_data: Dict[str, Any],
platform: str = 'apple'
) -> Dict[str, Any]:
"""
Validate compliance with app store guidelines.
Args:
app_data: App data including metadata, privacy policy, etc.
platform: 'apple' or 'google'
Returns:
Compliance validation report
"""
validation_results = {
'platform': platform,
'is_compliant': True,
'errors': [],
'warnings': [],
'recommendations': []
}
if platform == 'apple':
self._validate_apple_compliance(app_data, validation_results)
elif platform == 'google':
self._validate_google_compliance(app_data, validation_results)
# Determine overall compliance
validation_results['is_compliant'] = len(validation_results['errors']) == 0
return validation_results
def create_update_plan(
self,
current_version: str,
planned_features: List[str],
update_frequency: str = 'monthly'
) -> Dict[str, Any]:
"""
Create update cadence and feature rollout plan.
Args:
current_version: Current app version
planned_features: List of planned features
update_frequency: 'weekly', 'biweekly', 'monthly', 'quarterly'
Returns:
Update plan with cadence and feature schedule
"""
# Calculate next versions
next_versions = self._calculate_next_versions(
current_version,
update_frequency,
len(planned_features)
)
# Distribute features across versions
feature_schedule = self._distribute_features(
planned_features,
next_versions
)
# Generate "What's New" templates
whats_new_templates = [
self._generate_whats_new_template(version_data)
for version_data in feature_schedule
]
return {
'current_version': current_version,
'update_frequency': update_frequency,
'planned_updates': len(feature_schedule),
'feature_schedule': feature_schedule,
'whats_new_templates': whats_new_templates,
'recommendations': self._generate_update_recommendations(update_frequency)
}
def optimize_launch_timing(
self,
app_category: str,
target_audience: str,
current_date: Optional[str] = None
) -> Dict[str, Any]:
"""
Recommend optimal launch timing.
Args:
app_category: App category
target_audience: Target audience description
current_date: Current date (YYYY-MM-DD), defaults to today
Returns:
Launch timing recommendations
"""
if not current_date:
current_date = datetime.now().strftime('%Y-%m-%d')
# Analyze launch timing factors
day_of_week_rec = self._recommend_day_of_week(app_category)
seasonal_rec = self._recommend_seasonal_timing(app_category, current_date)
competitive_rec = self._analyze_competitive_timing(app_category)
# Calculate optimal dates
optimal_dates = self._calculate_optimal_dates(
current_date,
day_of_week_rec,
seasonal_rec
)
return {
'current_date': current_date,
'optimal_launch_dates': optimal_dates,
'day_of_week_recommendation': day_of_week_rec,
'seasonal_considerations': seasonal_rec,
'competitive_timing': competitive_rec,
'final_recommendation': self._generate_timing_recommendation(
optimal_dates,
seasonal_rec
)
}
def plan_seasonal_campaigns(
self,
app_category: str,
current_month: int = None
) -> Dict[str, Any]:
"""
Identify seasonal opportunities for ASO campaigns.
Args:
app_category: App category
current_month: Current month (1-12), defaults to current
Returns:
Seasonal campaign opportunities
"""
if not current_month:
current_month = datetime.now().month
# Identify relevant seasonal events
seasonal_opportunities = self._identify_seasonal_opportunities(
app_category,
current_month
)
# Generate campaign ideas
campaigns = [
self._generate_seasonal_campaign(opportunity)
for opportunity in seasonal_opportunities
]
return {
'current_month': current_month,
'category': app_category,
'seasonal_opportunities': seasonal_opportunities,
'campaign_ideas': campaigns,
'implementation_timeline': self._create_seasonal_timeline(campaigns)
}
def _generate_apple_checklist(self, app_info: Dict[str, Any]) -> List[Dict[str, Any]]:
"""Generate Apple App Store specific checklist."""
return [
{
'category': 'App Store Connect Setup',
'items': [
{'task': 'App Store Connect account created', 'status': 'pending'},
{'task': 'App bundle ID registered', 'status': 'pending'},
{'task': 'App Privacy declarations completed', 'status': 'pending'},
{'task': 'Age rating questionnaire completed', 'status': 'pending'}
]
},
{
'category': 'Metadata (Apple)',
'items': [
{'task': 'App title (30 chars max)', 'status': 'pending'},
{'task': 'Subtitle (30 chars max)', 'status': 'pending'},
{'task': 'Promotional text (170 chars max)', 'status': 'pending'},
{'task': 'Description (4000 chars max)', 'status': 'pending'},
{'task': 'Keywords (100 chars, comma-separated)', 'status': 'pending'},
{'task': 'Category selection (primary + secondary)', 'status': 'pending'}
]
},
{
'category': 'Visual Assets (Apple)',
'items': [
{'task': 'App icon (1024x1024px)', 'status': 'pending'},
{'task': 'Screenshots (iPhone 6.7" required)', 'status': 'pending'},
{'task': 'Screenshots (iPhone 5.5" required)', 'status': 'pending'},
{'task': 'Screenshots (iPad Pro 12.9" if iPad app)', 'status': 'pending'},
{'task': 'App preview video (optional but recommended)', 'status': 'pending'}
]
},
{
'category': 'Technical Requirements (Apple)',
'items': [
{'task': 'Build uploaded to App Store Connect', 'status': 'pending'},
{'task': 'TestFlight testing completed', 'status': 'pending'},
{'task': 'App tested on required iOS versions', 'status': 'pending'},
{'task': 'Crash-free rate > 99%', 'status': 'pending'},
{'task': 'All links in app/metadata working', 'status': 'pending'}
]
},
{
'category': 'Legal & Privacy (Apple)',
'items': [
{'task': 'Privacy Policy URL provided', 'status': 'pending'},
{'task': 'Terms of Service URL (if applicable)', 'status': 'pending'},
{'task': 'Data collection declarations accurate', 'status': 'pending'},
{'task': 'Third-party SDKs disclosed', 'status': 'pending'}
]
}
]
def _generate_google_checklist(self, app_info: Dict[str, Any]) -> List[Dict[str, Any]]:
"""Generate Google Play Store specific checklist."""
return [
{
'category': 'Play Console Setup',
'items': [
{'task': 'Google Play Console account created', 'status': 'pending'},
{'task': 'Developer profile completed', 'status': 'pending'},
{'task': 'Payment merchant account linked (if paid app)', 'status': 'pending'},
{'task': 'Content rating questionnaire completed', 'status': 'pending'}
]
},
{
'category': 'Metadata (Google)',
'items': [
{'task': 'App title (50 chars max)', 'status': 'pending'},
{'task': 'Short description (80 chars max)', 'status': 'pending'},
{'task': 'Full description (4000 chars max)', 'status': 'pending'},
{'task': 'Category selection', 'status': 'pending'},
{'task': 'Tags (up to 5)', 'status': 'pending'}
]
},
{
'category': 'Visual Assets (Google)',
'items': [
{'task': 'App icon (512x512px)', 'status': 'pending'},
{'task': 'Feature graphic (1024x500px)', 'status': 'pending'},
{'task': 'Screenshots (2-8 required, phone)', 'status': 'pending'},
{'task': 'Screenshots (tablet, if applicable)', 'status': 'pending'},
{'task': 'Promo video (YouTube link, optional)', 'status': 'pending'}
]
},
{
'category': 'Technical Requirements (Google)',
'items': [
{'task': 'APK/AAB uploaded to Play Console', 'status': 'pending'},
{'task': 'Internal testing completed', 'status': 'pending'},
{'task': 'App tested on required Android versions', 'status': 'pending'},
{'task': 'Target API level meets requirements', 'status': 'pending'},
{'task': 'All permissions justified', 'status': 'pending'}
]
},
{
'category': 'Legal & Privacy (Google)',
'items': [
{'task': 'Privacy Policy URL provided', 'status': 'pending'},
{'task': 'Data safety section completed', 'status': 'pending'},
{'task': 'Ads disclosure (if applicable)', 'status': 'pending'},
{'task': 'In-app purchase disclosure (if applicable)', 'status': 'pending'}
]
}
]
def _generate_universal_checklist(self, app_info: Dict[str, Any]) -> List[Dict[str, Any]]:
"""Generate universal (both platforms) checklist."""
return [
{
'category': 'Pre-Launch Marketing',
'items': [
{'task': 'Landing page created', 'status': 'pending'},
{'task': 'Social media accounts setup', 'status': 'pending'},
{'task': 'Press kit prepared', 'status': 'pending'},
{'task': 'Beta tester feedback collected', 'status': 'pending'},
{'task': 'Launch announcement drafted', 'status': 'pending'}
]
},
{
'category': 'ASO Preparation',
'items': [
{'task': 'Keyword research completed', 'status': 'pending'},
{'task': 'Competitor analysis done', 'status': 'pending'},
{'task': 'A/B test plan created for post-launch', 'status': 'pending'},
{'task': 'Analytics tracking configured', 'status': 'pending'}
]
},
{
'category': 'Quality Assurance',
'items': [
{'task': 'All core features tested', 'status': 'pending'},
{'task': 'User flows validated', 'status': 'pending'},
{'task': 'Performance testing completed', 'status': 'pending'},
{'task': 'Accessibility features tested', 'status': 'pending'},
{'task': 'Security audit completed', 'status': 'pending'}
]
},
{
'category': 'Support Infrastructure',
'items': [
{'task': 'Support email/system setup', 'status': 'pending'},
{'task': 'FAQ page created', 'status': 'pending'},
{'task': 'Documentation for users prepared', 'status': 'pending'},
{'task': 'Team trained on handling reviews', 'status': 'pending'}
]
}
]
def _generate_launch_timeline(self, launch_date: str) -> List[Dict[str, Any]]:
"""Generate timeline with milestones leading to launch."""
launch_dt = datetime.strptime(launch_date, '%Y-%m-%d')
milestones = [
{
'date': (launch_dt - timedelta(days=90)).strftime('%Y-%m-%d'),
'milestone': '90 days before: Complete keyword research and competitor analysis'
},
{
'date': (launch_dt - timedelta(days=60)).strftime('%Y-%m-%d'),
'milestone': '60 days before: Finalize metadata and visual assets'
},
{
'date': (launch_dt - timedelta(days=45)).strftime('%Y-%m-%d'),
'milestone': '45 days before: Begin beta testing program'
},
{
'date': (launch_dt - timedelta(days=30)).strftime('%Y-%m-%d'),
'milestone': '30 days before: Submit app for review (Apple typically takes 1-2 days, Google instant)'
},
{
'date': (launch_dt - timedelta(days=14)).strftime('%Y-%m-%d'),
'milestone': '14 days before: Prepare launch marketing materials'
},
{
'date': (launch_dt - timedelta(days=7)).strftime('%Y-%m-%d'),
'milestone': '7 days before: Set up analytics and monitoring'
},
{
'date': launch_dt.strftime('%Y-%m-%d'),
'milestone': 'Launch Day: Release app and execute marketing plan'
},
{
'date': (launch_dt + timedelta(days=7)).strftime('%Y-%m-%d'),
'milestone': '7 days after: Monitor metrics, respond to reviews, address critical issues'
},
{
'date': (launch_dt + timedelta(days=30)).strftime('%Y-%m-%d'),
'milestone': '30 days after: Analyze launch metrics, plan first update'
}
]
return milestones
def _calculate_checklist_summary(self, checklists: Dict[str, List[Dict[str, Any]]]) -> Dict[str, Any]:
"""Calculate completion summary."""
total_items = 0
completed_items = 0
for platform, categories in checklists.items():
for category in categories:
for item in category['items']:
total_items += 1
if item['status'] == 'completed':
completed_items += 1
completion_percentage = (completed_items / total_items * 100) if total_items > 0 else 0
return {
'total_items': total_items,
'completed_items': completed_items,
'pending_items': total_items - completed_items,
'completion_percentage': round(completion_percentage, 1),
'is_ready_to_launch': completion_percentage == 100
}
def _validate_apple_compliance(
self,
app_data: Dict[str, Any],
validation_results: Dict[str, Any]
) -> None:
"""Validate Apple App Store compliance."""
# Check for required fields
if not app_data.get('privacy_policy_url'):
validation_results['errors'].append("Privacy Policy URL is required")
if not app_data.get('app_icon'):
validation_results['errors'].append("App icon (1024x1024px) is required")
# Check metadata character limits
title = app_data.get('title', '')
if len(title) > 30:
validation_results['errors'].append(f"Title exceeds 30 characters ({len(title)})")
# Warnings for best practices
subtitle = app_data.get('subtitle', '')
if not subtitle:
validation_results['warnings'].append("Subtitle is empty - consider adding for better discoverability")
keywords = app_data.get('keywords', '')
if len(keywords) < 80:
validation_results['warnings'].append(
f"Keywords field underutilized ({len(keywords)}/100 chars) - add more keywords"
)
def _validate_google_compliance(
self,
app_data: Dict[str, Any],
validation_results: Dict[str, Any]
) -> None:
"""Validate Google Play Store compliance."""
# Check for required fields
if not app_data.get('privacy_policy_url'):
validation_results['errors'].append("Privacy Policy URL is required")
if not app_data.get('feature_graphic'):
validation_results['errors'].append("Feature graphic (1024x500px) is required")
# Check metadata character limits
title = app_data.get('title', '')
if len(title) > 50:
validation_results['errors'].append(f"Title exceeds 50 characters ({len(title)})")
short_desc = app_data.get('short_description', '')
if len(short_desc) > 80:
validation_results['errors'].append(f"Short description exceeds 80 characters ({len(short_desc)})")
# Warnings
if not short_desc:
validation_results['warnings'].append("Short description is empty")
def _calculate_next_versions(
self,
current_version: str,
update_frequency: str,
feature_count: int
) -> List[str]:
"""Calculate next version numbers."""
# Parse current version (assume semantic versioning)
parts = current_version.split('.')
major, minor, patch = int(parts[0]), int(parts[1]), int(parts[2] if len(parts) > 2 else 0)
versions = []
for i in range(feature_count):
if update_frequency == 'weekly':
patch += 1
elif update_frequency == 'biweekly':
patch += 1
elif update_frequency == 'monthly':
minor += 1
patch = 0
else: # quarterly
minor += 1
patch = 0
versions.append(f"{major}.{minor}.{patch}")
return versions
def _distribute_features(
self,
features: List[str],
versions: List[str]
) -> List[Dict[str, Any]]:
"""Distribute features across versions."""
features_per_version = max(1, len(features) // len(versions))
schedule = []
for i, version in enumerate(versions):
start_idx = i * features_per_version
end_idx = start_idx + features_per_version if i < len(versions) - 1 else len(features)
schedule.append({
'version': version,
'features': features[start_idx:end_idx],
'release_priority': 'high' if i == 0 else ('medium' if i < len(versions) // 2 else 'low')
})
return schedule
def _generate_whats_new_template(self, version_data: Dict[str, Any]) -> Dict[str, str]:
"""Generate What's New template for version."""
features_list = '\n'.join([f"• {feature}" for feature in version_data['features']])
template = f"""Version {version_data['version']}
{features_list}
We're constantly improving your experience. Thanks for using [App Name]!
Have feedback? Contact us at support@[company].com"""
return {
'version': version_data['version'],
'template': template
}
def _generate_update_recommendations(self, update_frequency: str) -> List[str]:
"""Generate recommendations for update strategy."""
recommendations = []
if update_frequency == 'weekly':
recommendations.append("Weekly updates show active development but ensure quality doesn't suffer")
elif update_frequency == 'monthly':
recommendations.append("Monthly updates are optimal for most apps - balance features and stability")
recommendations.extend([
"Include bug fixes in every update",
"Update 'What's New' section with each release",
"Respond to reviews mentioning fixed issues"
])
return recommendations
def _recommend_day_of_week(self, app_category: str) -> Dict[str, Any]:
"""Recommend best day of week to launch."""
# General recommendations based on category
if app_category.lower() in ['games', 'entertainment']:
return {
'recommended_day': 'Thursday',
'rationale': 'People download entertainment apps before weekend'
}
elif app_category.lower() in ['productivity', 'business']:
return {
'recommended_day': 'Tuesday',
'rationale': 'Business users most active mid-week'
}
else:
return {
'recommended_day': 'Wednesday',
'rationale': 'Mid-week provides good balance and review potential'
}
def _recommend_seasonal_timing(self, app_category: str, current_date: str) -> Dict[str, Any]:
"""Recommend seasonal timing considerations."""
current_dt = datetime.strptime(current_date, '%Y-%m-%d')
month = current_dt.month
# Avoid certain periods
avoid_periods = []
if month == 12:
avoid_periods.append("Late December - low user engagement during holidays")
if month in [7, 8]:
avoid_periods.append("Summer months - some categories see lower engagement")
# Recommend periods
good_periods = []
if month in [1, 9]:
good_periods.append("New Year/Back-to-school - high user engagement")
if month in [10, 11]:
good_periods.append("Pre-holiday season - good for shopping/gift apps")
return {
'current_month': month,
'avoid_periods': avoid_periods,
'good_periods': good_periods
}
def _analyze_competitive_timing(self, app_category: str) -> Dict[str, str]:
"""Analyze competitive timing considerations."""
return {
'recommendation': 'Research competitor launch schedules in your category',
'strategy': 'Avoid launching same week as major competitor updates'
}
def _calculate_optimal_dates(
self,
current_date: str,
day_rec: Dict[str, Any],
seasonal_rec: Dict[str, Any]
) -> List[str]:
"""Calculate optimal launch dates."""
current_dt = datetime.strptime(current_date, '%Y-%m-%d')
# Find next occurrence of recommended day
target_day = day_rec['recommended_day']
days_map = {'Monday': 0, 'Tuesday': 1, 'Wednesday': 2, 'Thursday': 3, 'Friday': 4}
target_day_num = days_map.get(target_day, 2)
days_ahead = (target_day_num - current_dt.weekday()) % 7
if days_ahead == 0:
days_ahead = 7
next_target_date = current_dt + timedelta(days=days_ahead)
optimal_dates = [
next_target_date.strftime('%Y-%m-%d'),
(next_target_date + timedelta(days=7)).strftime('%Y-%m-%d'),
(next_target_date + timedelta(days=14)).strftime('%Y-%m-%d')
]
return optimal_dates
def _generate_timing_recommendation(
self,
optimal_dates: List[str],
seasonal_rec: Dict[str, Any]
) -> str:
"""Generate final timing recommendation."""
if seasonal_rec['avoid_periods']:
return f"Consider launching in {optimal_dates[1]} to avoid {seasonal_rec['avoid_periods'][0]}"
elif seasonal_rec['good_periods']:
return f"Launch on {optimal_dates[0]} to capitalize on {seasonal_rec['good_periods'][0]}"
else:
return f"Recommended launch date: {optimal_dates[0]}"
def _identify_seasonal_opportunities(
self,
app_category: str,
current_month: int
) -> List[Dict[str, Any]]:
"""Identify seasonal opportunities for category."""
opportunities = []
# Universal opportunities
if current_month == 1:
opportunities.append({
'event': 'New Year Resolutions',
'dates': 'January 1-31',
'relevance': 'high' if app_category.lower() in ['health', 'fitness', 'productivity'] else 'medium'
})
if current_month in [11, 12]:
opportunities.append({
'event': 'Holiday Shopping Season',
'dates': 'November-December',
'relevance': 'high' if app_category.lower() in ['shopping', 'gifts'] else 'low'
})
# Category-specific
if app_category.lower() == 'education' and current_month in [8, 9]:
opportunities.append({
'event': 'Back to School',
'dates': 'August-September',
'relevance': 'high'
})
return opportunities
def _generate_seasonal_campaign(self, opportunity: Dict[str, Any]) -> Dict[str, Any]:
"""Generate campaign idea for seasonal opportunity."""
return {
'event': opportunity['event'],
'campaign_idea': f"Create themed visuals and messaging for {opportunity['event']}",
'metadata_updates': 'Update app description and screenshots with seasonal themes',
'promotion_strategy': 'Consider limited-time features or discounts'
}
def _create_seasonal_timeline(self, campaigns: List[Dict[str, Any]]) -> List[str]:
"""Create implementation timeline for campaigns."""
return [
f"30 days before: Plan {campaign['event']} campaign strategy"
for campaign in campaigns
]
def generate_launch_checklist(
platform: str,
app_info: Dict[str, Any],
launch_date: Optional[str] = None
) -> Dict[str, Any]:
"""
Convenience function to generate launch checklist.
Args:
platform: Platform ('apple', 'google', or 'both')
app_info: App information
launch_date: Target launch date
Returns:
Complete launch checklist
"""
generator = LaunchChecklistGenerator(platform)
return generator.generate_prelaunch_checklist(app_info, launch_date)

588
.agents/skills/app-store-optimization/scripts/localization_helper.py Normal file
View File

@@ -0,0 +1,588 @@
"""
Localization helper module for App Store Optimization.
Manages multi-language ASO optimization strategies.
"""
from typing import Dict, List, Any, Optional, Tuple
class LocalizationHelper:
"""Helps manage multi-language ASO optimization."""
# Priority markets by language (based on app store revenue and user base)
PRIORITY_MARKETS = {
'tier_1': [
{'language': 'en-US', 'market': 'United States', 'revenue_share': 0.25},
{'language': 'zh-CN', 'market': 'China', 'revenue_share': 0.20},
{'language': 'ja-JP', 'market': 'Japan', 'revenue_share': 0.10},
{'language': 'de-DE', 'market': 'Germany', 'revenue_share': 0.08},
{'language': 'en-GB', 'market': 'United Kingdom', 'revenue_share': 0.06}
],
'tier_2': [
{'language': 'fr-FR', 'market': 'France', 'revenue_share': 0.05},
{'language': 'ko-KR', 'market': 'South Korea', 'revenue_share': 0.05},
{'language': 'es-ES', 'market': 'Spain', 'revenue_share': 0.03},
{'language': 'it-IT', 'market': 'Italy', 'revenue_share': 0.03},
{'language': 'pt-BR', 'market': 'Brazil', 'revenue_share': 0.03}
],
'tier_3': [
{'language': 'ru-RU', 'market': 'Russia', 'revenue_share': 0.02},
{'language': 'es-MX', 'market': 'Mexico', 'revenue_share': 0.02},
{'language': 'nl-NL', 'market': 'Netherlands', 'revenue_share': 0.02},
{'language': 'sv-SE', 'market': 'Sweden', 'revenue_share': 0.01},
{'language': 'pl-PL', 'market': 'Poland', 'revenue_share': 0.01}
]
}
# Character limit multipliers by language (some languages need more/less space)
CHAR_MULTIPLIERS = {
'en': 1.0,
'zh': 0.6, # Chinese characters are more compact
'ja': 0.7, # Japanese uses kanji
'ko': 0.8, # Korean is relatively compact
'de': 1.3, # German words are typically longer
'fr': 1.2, # French tends to be longer
'es': 1.1, # Spanish slightly longer
'pt': 1.1, # Portuguese similar to Spanish
'ru': 1.1, # Russian similar length
'ar': 1.0, # Arabic varies
'it': 1.1 # Italian similar to Spanish
}
def __init__(self, app_category: str = 'general'):
"""
Initialize localization helper.
Args:
app_category: App category to prioritize relevant markets
"""
self.app_category = app_category
self.localization_plans = []
def identify_target_markets(
self,
current_market: str = 'en-US',
budget_level: str = 'medium',
target_market_count: int = 5
) -> Dict[str, Any]:
"""
Recommend priority markets for localization.
Args:
current_market: Current/primary market
budget_level: 'low', 'medium', or 'high'
target_market_count: Number of markets to target
Returns:
Prioritized market recommendations
"""
# Determine tier priorities based on budget
if budget_level == 'low':
priority_tiers = ['tier_1']
max_markets = min(target_market_count, 3)
elif budget_level == 'medium':
priority_tiers = ['tier_1', 'tier_2']
max_markets = min(target_market_count, 8)
else: # high budget
priority_tiers = ['tier_1', 'tier_2', 'tier_3']
max_markets = target_market_count
# Collect markets from priority tiers
recommended_markets = []
for tier in priority_tiers:
for market in self.PRIORITY_MARKETS[tier]:
if market['language'] != current_market:
recommended_markets.append({
**market,
'tier': tier,
'estimated_translation_cost': self._estimate_translation_cost(
market['language']
)
})
# Sort by revenue share and limit
recommended_markets.sort(key=lambda x: x['revenue_share'], reverse=True)
recommended_markets = recommended_markets[:max_markets]
# Calculate potential ROI
total_potential_revenue_share = sum(m['revenue_share'] for m in recommended_markets)
return {
'recommended_markets': recommended_markets,
'total_markets': len(recommended_markets),
'estimated_total_revenue_lift': f"{total_potential_revenue_share*100:.1f}%",
'estimated_cost': self._estimate_total_localization_cost(recommended_markets),
'implementation_priority': self._prioritize_implementation(recommended_markets)
}
def translate_metadata(
self,
source_metadata: Dict[str, str],
source_language: str,
target_language: str,
platform: str = 'apple'
) -> Dict[str, Any]:
"""
Generate localized metadata with character limit considerations.
Args:
source_metadata: Original metadata (title, description, etc.)
source_language: Source language code (e.g., 'en')
target_language: Target language code (e.g., 'es')
platform: 'apple' or 'google'
Returns:
Localized metadata with character limit validation
"""
# Get character multiplier
target_lang_code = target_language.split('-')[0]
char_multiplier = self.CHAR_MULTIPLIERS.get(target_lang_code, 1.0)
# Platform-specific limits
if platform == 'apple':
limits = {'title': 30, 'subtitle': 30, 'description': 4000, 'keywords': 100}
else:
limits = {'title': 50, 'short_description': 80, 'description': 4000}
localized_metadata = {}
warnings = []
for field, text in source_metadata.items():
if field not in limits:
continue
# Estimate target length
estimated_length = int(len(text) * char_multiplier)
limit = limits[field]
localized_metadata[field] = {
'original_text': text,
'original_length': len(text),
'estimated_target_length': estimated_length,
'character_limit': limit,
'fits_within_limit': estimated_length <= limit,
'translation_notes': self._get_translation_notes(
field,
target_language,
estimated_length,
limit
)
}
if estimated_length > limit:
warnings.append(
f"{field}: Estimated length ({estimated_length}) may exceed limit ({limit}) - "
f"condensing may be required"
)
return {
'source_language': source_language,
'target_language': target_language,
'platform': platform,
'localized_fields': localized_metadata,
'character_multiplier': char_multiplier,
'warnings': warnings,
'recommendations': self._generate_translation_recommendations(
target_language,
warnings
)
}
def adapt_keywords(
self,
source_keywords: List[str],
source_language: str,
target_language: str,
target_market: str
) -> Dict[str, Any]:
"""
Adapt keywords for target market (not just direct translation).
Args:
source_keywords: Original keywords
source_language: Source language code
target_language: Target language code
target_market: Target market (e.g., 'France', 'Japan')
Returns:
Adapted keyword recommendations
"""
# Cultural adaptation considerations
cultural_notes = self._get_cultural_keyword_considerations(target_market)
# Search behavior differences
search_patterns = self._get_search_patterns(target_market)
adapted_keywords = []
for keyword in source_keywords:
adapted_keywords.append({
'source_keyword': keyword,
'adaptation_strategy': self._determine_adaptation_strategy(
keyword,
target_market
),
'cultural_considerations': cultural_notes.get(keyword, []),
'priority': 'high' if keyword in source_keywords[:3] else 'medium'
})
return {
'source_language': source_language,
'target_language': target_language,
'target_market': target_market,
'adapted_keywords': adapted_keywords,
'search_behavior_notes': search_patterns,
'recommendations': [
'Use native speakers for keyword research',
'Test keywords with local users before finalizing',
'Consider local competitors\' keyword strategies',
'Monitor search trends in target market'
]
}
def validate_translations(
self,
translated_metadata: Dict[str, str],
target_language: str,
platform: str = 'apple'
) -> Dict[str, Any]:
"""
Validate translated metadata for character limits and quality.
Args:
translated_metadata: Translated text fields
target_language: Target language code
platform: 'apple' or 'google'
Returns:
Validation report
"""
# Platform limits
if platform == 'apple':
limits = {'title': 30, 'subtitle': 30, 'description': 4000, 'keywords': 100}
else:
limits = {'title': 50, 'short_description': 80, 'description': 4000}
validation_results = {
'is_valid': True,
'field_validations': {},
'errors': [],
'warnings': []
}
for field, text in translated_metadata.items():
if field not in limits:
continue
actual_length = len(text)
limit = limits[field]
is_within_limit = actual_length <= limit
validation_results['field_validations'][field] = {
'text': text,
'length': actual_length,
'limit': limit,
'is_valid': is_within_limit,
'usage_percentage': round((actual_length / limit) * 100, 1)
}
if not is_within_limit:
validation_results['is_valid'] = False
validation_results['errors'].append(
f"{field} exceeds limit: {actual_length}/{limit} characters"
)
# Quality checks
quality_issues = self._check_translation_quality(
translated_metadata,
target_language
)
validation_results['quality_checks'] = quality_issues
if quality_issues:
validation_results['warnings'].extend(
[f"Quality issue: {issue}" for issue in quality_issues]
)
return validation_results
def calculate_localization_roi(
self,
target_markets: List[str],
current_monthly_downloads: int,
localization_cost: float,
expected_lift_percentage: float = 0.15
) -> Dict[str, Any]:
"""
Estimate ROI of localization investment.
Args:
target_markets: List of market codes
current_monthly_downloads: Current monthly downloads
localization_cost: Total cost to localize
expected_lift_percentage: Expected download increase (default 15%)
Returns:
ROI analysis
"""
# Estimate market-specific lift
market_data = []
total_expected_lift = 0
for market_code in target_markets:
# Find market in priority lists
market_info = None
for tier_name, markets in self.PRIORITY_MARKETS.items():
for m in markets:
if m['language'] == market_code:
market_info = m
break
if not market_info:
continue
# Estimate downloads from this market
market_downloads = int(current_monthly_downloads * market_info['revenue_share'])
expected_increase = int(market_downloads * expected_lift_percentage)
total_expected_lift += expected_increase
market_data.append({
'market': market_info['market'],
'current_monthly_downloads': market_downloads,
'expected_increase': expected_increase,
'revenue_potential': market_info['revenue_share']
})
# Calculate payback period (assuming $2 revenue per download)
revenue_per_download = 2.0
monthly_additional_revenue = total_expected_lift * revenue_per_download
payback_months = (localization_cost / monthly_additional_revenue) if monthly_additional_revenue > 0 else float('inf')
return {
'markets_analyzed': len(market_data),
'market_breakdown': market_data,
'total_expected_monthly_lift': total_expected_lift,
'expected_monthly_revenue_increase': f"${monthly_additional_revenue:,.2f}",
'localization_cost': f"${localization_cost:,.2f}",
'payback_period_months': round(payback_months, 1) if payback_months != float('inf') else 'N/A',
'annual_roi': f"{((monthly_additional_revenue * 12 - localization_cost) / localization_cost * 100):.1f}%" if payback_months != float('inf') else 'Negative',
'recommendation': self._generate_roi_recommendation(payback_months)
}
def _estimate_translation_cost(self, language: str) -> Dict[str, float]:
"""Estimate translation cost for a language."""
# Base cost per word (professional translation)
base_cost_per_word = 0.12
# Language-specific multipliers
multipliers = {
'zh-CN': 1.5, # Chinese requires specialist
'ja-JP': 1.5, # Japanese requires specialist
'ko-KR': 1.3,
'ar-SA': 1.4, # Arabic (right-to-left)
'default': 1.0
}
multiplier = multipliers.get(language, multipliers['default'])
# Typical word counts for app store metadata
typical_word_counts = {
'title': 5,
'subtitle': 5,
'description': 300,
'keywords': 20,
'screenshots': 50 # Caption text
}
total_words = sum(typical_word_counts.values())
estimated_cost = total_words * base_cost_per_word * multiplier
return {
'cost_per_word': base_cost_per_word * multiplier,
'total_words': total_words,
'estimated_cost': round(estimated_cost, 2)
}
def _estimate_total_localization_cost(self, markets: List[Dict[str, Any]]) -> str:
"""Estimate total cost for multiple markets."""
total = sum(m['estimated_translation_cost']['estimated_cost'] for m in markets)
return f"${total:,.2f}"
def _prioritize_implementation(self, markets: List[Dict[str, Any]]) -> List[Dict[str, str]]:
"""Create phased implementation plan."""
phases = []
# Phase 1: Top revenue markets
phase_1 = [m for m in markets[:3]]
if phase_1:
phases.append({
'phase': 'Phase 1 (First 30 days)',
'markets': ', '.join([m['market'] for m in phase_1]),
'rationale': 'Highest revenue potential markets'
})
# Phase 2: Remaining tier 1 and top tier 2
phase_2 = [m for m in markets[3:6]]
if phase_2:
phases.append({
'phase': 'Phase 2 (Days 31-60)',
'markets': ', '.join([m['market'] for m in phase_2]),
'rationale': 'Strong revenue markets with good ROI'
})
# Phase 3: Remaining markets
phase_3 = [m for m in markets[6:]]
if phase_3:
phases.append({
'phase': 'Phase 3 (Days 61-90)',
'markets': ', '.join([m['market'] for m in phase_3]),
'rationale': 'Complete global coverage'
})
return phases
def _get_translation_notes(
self,
field: str,
target_language: str,
estimated_length: int,
limit: int
) -> List[str]:
"""Get translation-specific notes for field."""
notes = []
if estimated_length > limit:
notes.append(f"Condensing required - aim for {limit - 10} characters to allow buffer")
if field == 'title' and target_language.startswith('zh'):
notes.append("Chinese characters convey more meaning - may need fewer characters")
if field == 'keywords' and target_language.startswith('de'):
notes.append("German compound words may be longer - prioritize shorter keywords")
return notes
def _generate_translation_recommendations(
self,
target_language: str,
warnings: List[str]
) -> List[str]:
"""Generate translation recommendations."""
recommendations = [
"Use professional native speakers for translation",
"Test translations with local users before finalizing"
]
if warnings:
recommendations.append("Work with translator to condense text while preserving meaning")
if target_language.startswith('zh') or target_language.startswith('ja'):
recommendations.append("Consider cultural context and local idioms")
return recommendations
def _get_cultural_keyword_considerations(self, target_market: str) -> Dict[str, List[str]]:
"""Get cultural considerations for keywords by market."""
# Simplified example - real implementation would be more comprehensive
considerations = {
'China': ['Avoid politically sensitive terms', 'Consider local alternatives to blocked services'],
'Japan': ['Honorific language important', 'Technical terms often use katakana'],
'Germany': ['Privacy and security terms resonate', 'Efficiency and quality valued'],
'France': ['French language protection laws', 'Prefer French terms over English'],
'default': ['Research local search behavior', 'Test with native speakers']
}
return considerations.get(target_market, considerations['default'])
def _get_search_patterns(self, target_market: str) -> List[str]:
"""Get search pattern notes for market."""
patterns = {
'China': ['Use both simplified characters and romanization', 'Brand names often romanized'],
'Japan': ['Mix of kanji, hiragana, and katakana', 'English words common in tech'],
'Germany': ['Compound words common', 'Specific technical terminology'],
'default': ['Research local search trends', 'Monitor competitor keywords']
}
return patterns.get(target_market, patterns['default'])
def _determine_adaptation_strategy(self, keyword: str, target_market: str) -> str:
"""Determine how to adapt keyword for market."""
# Simplified logic
if target_market in ['China', 'Japan', 'Korea']:
return 'full_localization' # Complete translation needed
elif target_market in ['Germany', 'France', 'Spain']:
return 'adapt_and_translate' # Some adaptation needed
else:
return 'direct_translation' # Direct translation usually sufficient
def _check_translation_quality(
self,
translated_metadata: Dict[str, str],
target_language: str
) -> List[str]:
"""Basic quality checks for translations."""
issues = []
# Check for untranslated placeholders
for field, text in translated_metadata.items():
if '[' in text or '{' in text or 'TODO' in text.upper():
issues.append(f"{field} contains placeholder text")
# Check for excessive punctuation
for field, text in translated_metadata.items():
if text.count('!') > 3:
issues.append(f"{field} has excessive exclamation marks")
return issues
def _generate_roi_recommendation(self, payback_months: float) -> str:
"""Generate ROI recommendation."""
if payback_months <= 3:
return "Excellent ROI - proceed immediately"
elif payback_months <= 6:
return "Good ROI - recommended investment"
elif payback_months <= 12:
return "Moderate ROI - consider if strategic market"
else:
return "Low ROI - reconsider or focus on higher-priority markets first"
def plan_localization_strategy(
current_market: str,
budget_level: str,
monthly_downloads: int
) -> Dict[str, Any]:
"""
Convenience function to plan localization strategy.
Args:
current_market: Current market code
budget_level: Budget level
monthly_downloads: Current monthly downloads
Returns:
Complete localization plan
"""
helper = LocalizationHelper()
target_markets = helper.identify_target_markets(
current_market=current_market,
budget_level=budget_level
)
# Extract market codes
market_codes = [m['language'] for m in target_markets['recommended_markets']]
# Calculate ROI
estimated_cost = float(target_markets['estimated_cost'].replace('$', '').replace(',', ''))
roi_analysis = helper.calculate_localization_roi(
market_codes,
monthly_downloads,
estimated_cost
)
return {
'target_markets': target_markets,
'roi_analysis': roi_analysis
}

581
.agents/skills/app-store-optimization/scripts/metadata_optimizer.py Normal file
View File

@@ -0,0 +1,581 @@
"""
Metadata optimization module for App Store Optimization.
Optimizes titles, descriptions, and keyword fields with platform-specific character limit validation.
"""
from typing import Dict, List, Any, Optional, Tuple
import re
class MetadataOptimizer:
"""Optimizes app store metadata for maximum discoverability and conversion."""
# Platform-specific character limits
CHAR_LIMITS = {
'apple': {
'title': 30,
'subtitle': 30,
'promotional_text': 170,
'description': 4000,
'keywords': 100,
'whats_new': 4000
},
'google': {
'title': 50,
'short_description': 80,
'full_description': 4000
}
}
def __init__(self, platform: str = 'apple'):
"""
Initialize metadata optimizer.
Args:
platform: 'apple' or 'google'
"""
if platform not in ['apple', 'google']:
raise ValueError("Platform must be 'apple' or 'google'")
self.platform = platform
self.limits = self.CHAR_LIMITS[platform]
def optimize_title(
self,
app_name: str,
target_keywords: List[str],
include_brand: bool = True
) -> Dict[str, Any]:
"""
Optimize app title with keyword integration.
Args:
app_name: Your app's brand name
target_keywords: List of keywords to potentially include
include_brand: Whether to include brand name
Returns:
Optimized title options with analysis
"""
max_length = self.limits['title']
title_options = []
# Option 1: Brand name only
if include_brand:
option1 = app_name[:max_length]
title_options.append({
'title': option1,
'length': len(option1),
'remaining_chars': max_length - len(option1),
'keywords_included': [],
'strategy': 'brand_only',
'pros': ['Maximum brand recognition', 'Clean and simple'],
'cons': ['No keyword targeting', 'Lower discoverability']
})
# Option 2: Brand + Primary Keyword
if target_keywords:
primary_keyword = target_keywords[0]
option2 = self._build_title_with_keywords(
app_name,
[primary_keyword],
max_length
)
if option2:
title_options.append({
'title': option2,
'length': len(option2),
'remaining_chars': max_length - len(option2),
'keywords_included': [primary_keyword],
'strategy': 'brand_plus_primary',
'pros': ['Targets main keyword', 'Maintains brand identity'],
'cons': ['Limited keyword coverage']
})
# Option 3: Brand + Multiple Keywords (if space allows)
if len(target_keywords) > 1:
option3 = self._build_title_with_keywords(
app_name,
target_keywords[:2],
max_length
)
if option3:
title_options.append({
'title': option3,
'length': len(option3),
'remaining_chars': max_length - len(option3),
'keywords_included': target_keywords[:2],
'strategy': 'brand_plus_multiple',
'pros': ['Multiple keyword targets', 'Better discoverability'],
'cons': ['May feel cluttered', 'Less brand focus']
})
# Option 4: Keyword-first approach (for new apps)
if target_keywords and not include_brand:
option4 = " ".join(target_keywords[:2])[:max_length]
title_options.append({
'title': option4,
'length': len(option4),
'remaining_chars': max_length - len(option4),
'keywords_included': target_keywords[:2],
'strategy': 'keyword_first',
'pros': ['Maximum SEO benefit', 'Clear functionality'],
'cons': ['No brand recognition', 'Generic appearance']
})
return {
'platform': self.platform,
'max_length': max_length,
'options': title_options,
'recommendation': self._recommend_title_option(title_options)
}
def optimize_description(
self,
app_info: Dict[str, Any],
target_keywords: List[str],
description_type: str = 'full'
) -> Dict[str, Any]:
"""
Optimize app description with keyword integration and conversion focus.
Args:
app_info: Dict with 'name', 'key_features', 'unique_value', 'target_audience'
target_keywords: List of keywords to integrate naturally
description_type: 'full', 'short' (Google), 'subtitle' (Apple)
Returns:
Optimized description with analysis
"""
if description_type == 'short' and self.platform == 'google':
return self._optimize_short_description(app_info, target_keywords)
elif description_type == 'subtitle' and self.platform == 'apple':
return self._optimize_subtitle(app_info, target_keywords)
else:
return self._optimize_full_description(app_info, target_keywords)
def optimize_keyword_field(
self,
target_keywords: List[str],
app_title: str = "",
app_description: str = ""
) -> Dict[str, Any]:
"""
Optimize Apple's 100-character keyword field.
Rules:
- No spaces between commas
- No plural forms if singular exists
- No duplicates
- Keywords in title/subtitle are already indexed
Args:
target_keywords: List of target keywords
app_title: Current app title (to avoid duplication)
app_description: Current description (to check coverage)
Returns:
Optimized keyword field (comma-separated, no spaces)
"""
if self.platform != 'apple':
return {'error': 'Keyword field optimization only applies to Apple App Store'}
max_length = self.limits['keywords']
# Extract words already in title (these don't need to be in keyword field)
title_words = set(app_title.lower().split()) if app_title else set()
# Process keywords
processed_keywords = []
for keyword in target_keywords:
keyword_lower = keyword.lower().strip()
# Skip if already in title
if keyword_lower in title_words:
continue
# Remove duplicates and process
words = keyword_lower.split()
for word in words:
if word not in processed_keywords and word not in title_words:
processed_keywords.append(word)
# Remove plurals if singular exists
deduplicated = self._remove_plural_duplicates(processed_keywords)
# Build keyword field within 100 character limit
keyword_field = self._build_keyword_field(deduplicated, max_length)
# Calculate keyword density in description
density = self._calculate_coverage(target_keywords, app_description)
return {
'keyword_field': keyword_field,
'length': len(keyword_field),
'remaining_chars': max_length - len(keyword_field),
'keywords_included': keyword_field.split(','),
'keywords_count': len(keyword_field.split(',')),
'keywords_excluded': [kw for kw in target_keywords if kw.lower() not in keyword_field],
'description_coverage': density,
'optimization_tips': [
'Keywords in title are auto-indexed - no need to repeat',
'Use singular forms only (Apple indexes plurals automatically)',
'No spaces between commas to maximize character usage',
'Update keyword field with each app update to test variations'
]
}
def validate_character_limits(
self,
metadata: Dict[str, str]
) -> Dict[str, Any]:
"""
Validate all metadata fields against platform character limits.
Args:
metadata: Dictionary of field_name: value
Returns:
Validation report with errors and warnings
"""
validation_results = {
'is_valid': True,
'errors': [],
'warnings': [],
'field_status': {}
}
for field_name, value in metadata.items():
if field_name not in self.limits:
validation_results['warnings'].append(
f"Unknown field '{field_name}' for {self.platform} platform"
)
continue
max_length = self.limits[field_name]
actual_length = len(value)
remaining = max_length - actual_length
field_status = {
'value': value,
'length': actual_length,
'limit': max_length,
'remaining': remaining,
'is_valid': actual_length <= max_length,
'usage_percentage': round((actual_length / max_length) * 100, 1)
}
validation_results['field_status'][field_name] = field_status
if actual_length > max_length:
validation_results['is_valid'] = False
validation_results['errors'].append(
f"'{field_name}' exceeds limit: {actual_length}/{max_length} chars"
)
elif remaining > max_length * 0.2: # More than 20% unused
validation_results['warnings'].append(
f"'{field_name}' under-utilizes space: {remaining} chars remaining"
)
return validation_results
def calculate_keyword_density(
self,
text: str,
target_keywords: List[str]
) -> Dict[str, Any]:
"""
Calculate keyword density in text.
Args:
text: Text to analyze
target_keywords: Keywords to check
Returns:
Density analysis
"""
text_lower = text.lower()
total_words = len(text_lower.split())
keyword_densities = {}
for keyword in target_keywords:
keyword_lower = keyword.lower()
count = text_lower.count(keyword_lower)
density = (count / total_words * 100) if total_words > 0 else 0
keyword_densities[keyword] = {
'occurrences': count,
'density_percentage': round(density, 2),
'status': self._assess_density(density)
}
# Overall assessment
total_keyword_occurrences = sum(kw['occurrences'] for kw in keyword_densities.values())
overall_density = (total_keyword_occurrences / total_words * 100) if total_words > 0 else 0
return {
'total_words': total_words,
'keyword_densities': keyword_densities,
'overall_keyword_density': round(overall_density, 2),
'assessment': self._assess_overall_density(overall_density),
'recommendations': self._generate_density_recommendations(keyword_densities)
}
def _build_title_with_keywords(
self,
app_name: str,
keywords: List[str],
max_length: int
) -> Optional[str]:
"""Build title combining app name and keywords within limit."""
separators = [' - ', ': ', ' | ']
for sep in separators:
for kw in keywords:
title = f"{app_name}{sep}{kw}"
if len(title) <= max_length:
return title
return None
def _optimize_short_description(
self,
app_info: Dict[str, Any],
target_keywords: List[str]
) -> Dict[str, Any]:
"""Optimize Google Play short description (80 chars)."""
max_length = self.limits['short_description']
# Focus on unique value proposition with primary keyword
unique_value = app_info.get('unique_value', '')
primary_keyword = target_keywords[0] if target_keywords else ''
# Template: [Primary Keyword] - [Unique Value]
short_desc = f"{primary_keyword.title()} - {unique_value}"[:max_length]
return {
'short_description': short_desc,
'length': len(short_desc),
'remaining_chars': max_length - len(short_desc),
'keywords_included': [primary_keyword] if primary_keyword in short_desc.lower() else [],
'strategy': 'keyword_value_proposition'
}
def _optimize_subtitle(
self,
app_info: Dict[str, Any],
target_keywords: List[str]
) -> Dict[str, Any]:
"""Optimize Apple App Store subtitle (30 chars)."""
max_length = self.limits['subtitle']
# Very concise - primary keyword or key feature
primary_keyword = target_keywords[0] if target_keywords else ''
key_feature = app_info.get('key_features', [''])[0] if app_info.get('key_features') else ''
options = [
primary_keyword[:max_length],
key_feature[:max_length],
f"{primary_keyword} App"[:max_length]
]
return {
'subtitle_options': [opt for opt in options if opt],
'max_length': max_length,
'recommendation': options[0] if options else ''
}
def _optimize_full_description(
self,
app_info: Dict[str, Any],
target_keywords: List[str]
) -> Dict[str, Any]:
"""Optimize full app description (4000 chars for both platforms)."""
max_length = self.limits.get('description', self.limits.get('full_description', 4000))
# Structure: Hook → Features → Benefits → Social Proof → CTA
sections = []
# Hook (with primary keyword)
primary_keyword = target_keywords[0] if target_keywords else ''
unique_value = app_info.get('unique_value', '')
hook = f"{unique_value} {primary_keyword.title()} that helps you achieve more.\n\n"
sections.append(hook)
# Features (with keywords naturally integrated)
features = app_info.get('key_features', [])
if features:
sections.append("KEY FEATURES:\n")
for i, feature in enumerate(features[:5], 1):
# Integrate keywords naturally
feature_text = f"• {feature}"
if i <= len(target_keywords):
keyword = target_keywords[i-1]
if keyword.lower() not in feature.lower():
feature_text = f"• {feature} with {keyword}"
sections.append(f"{feature_text}\n")
sections.append("\n")
# Benefits
target_audience = app_info.get('target_audience', 'users')
sections.append(f"PERFECT FOR:\n{target_audience}\n\n")
# Social proof placeholder
sections.append("WHY USERS LOVE US:\n")
sections.append("Join thousands of satisfied users who have transformed their workflow.\n\n")
# CTA
sections.append("Download now and start experiencing the difference!")
# Combine and validate length
full_description = "".join(sections)
if len(full_description) > max_length:
full_description = full_description[:max_length-3] + "..."
# Calculate keyword density
density = self.calculate_keyword_density(full_description, target_keywords)
return {
'full_description': full_description,
'length': len(full_description),
'remaining_chars': max_length - len(full_description),
'keyword_analysis': density,
'structure': {
'has_hook': True,
'has_features': len(features) > 0,
'has_benefits': True,
'has_cta': True
}
}
def _remove_plural_duplicates(self, keywords: List[str]) -> List[str]:
"""Remove plural forms if singular exists."""
deduplicated = []
singular_set = set()
for keyword in keywords:
if keyword.endswith('s') and len(keyword) > 1:
singular = keyword[:-1]
if singular not in singular_set:
deduplicated.append(singular)
singular_set.add(singular)
else:
if keyword not in singular_set:
deduplicated.append(keyword)
singular_set.add(keyword)
return deduplicated
def _build_keyword_field(self, keywords: List[str], max_length: int) -> str:
"""Build comma-separated keyword field within character limit."""
keyword_field = ""
for keyword in keywords:
test_field = f"{keyword_field},{keyword}" if keyword_field else keyword
if len(test_field) <= max_length:
keyword_field = test_field
else:
break
return keyword_field
def _calculate_coverage(self, keywords: List[str], text: str) -> Dict[str, int]:
"""Calculate how many keywords are covered in text."""
text_lower = text.lower()
coverage = {}
for keyword in keywords:
coverage[keyword] = text_lower.count(keyword.lower())
return coverage
def _assess_density(self, density: float) -> str:
"""Assess individual keyword density."""
if density < 0.5:
return "too_low"
elif density <= 2.5:
return "optimal"
else:
return "too_high"
def _assess_overall_density(self, density: float) -> str:
"""Assess overall keyword density."""
if density < 2:
return "Under-optimized: Consider adding more keyword variations"
elif density <= 5:
return "Optimal: Good keyword integration without stuffing"
elif density <= 8:
return "High: Approaching keyword stuffing - reduce keyword usage"
else:
return "Too High: Keyword stuffing detected - rewrite for natural flow"
def _generate_density_recommendations(
self,
keyword_densities: Dict[str, Dict[str, Any]]
) -> List[str]:
"""Generate recommendations based on keyword density analysis."""
recommendations = []
for keyword, data in keyword_densities.items():
if data['status'] == 'too_low':
recommendations.append(
f"Increase usage of '{keyword}' - currently only {data['occurrences']} times"
)
elif data['status'] == 'too_high':
recommendations.append(
f"Reduce usage of '{keyword}' - appears {data['occurrences']} times (keyword stuffing risk)"
)
if not recommendations:
recommendations.append("Keyword density is well-balanced")
return recommendations
def _recommend_title_option(self, options: List[Dict[str, Any]]) -> str:
"""Recommend best title option based on strategy."""
if not options:
return "No valid options available"
# Prefer brand_plus_primary for established apps
for option in options:
if option['strategy'] == 'brand_plus_primary':
return f"Recommended: '{option['title']}' (Balance of brand and SEO)"
# Fallback to first option
return f"Recommended: '{options[0]['title']}' ({options[0]['strategy']})"
def optimize_app_metadata(
platform: str,
app_info: Dict[str, Any],
target_keywords: List[str]
) -> Dict[str, Any]:
"""
Convenience function to optimize all metadata fields.
Args:
platform: 'apple' or 'google'
app_info: App information dictionary
target_keywords: Target keywords list
Returns:
Complete metadata optimization package
"""
optimizer = MetadataOptimizer(platform)
return {
'platform': platform,
'title': optimizer.optimize_title(
app_info['name'],
target_keywords
),
'description': optimizer.optimize_description(
app_info,
target_keywords,
'full'
),
'keyword_field': optimizer.optimize_keyword_field(
target_keywords
) if platform == 'apple' else None
}

714
.agents/skills/app-store-optimization/scripts/review_analyzer.py Normal file
View File

@@ -0,0 +1,714 @@
"""
Review analysis module for App Store Optimization.
Analyzes user reviews for sentiment, issues, and feature requests.
"""
from typing import Dict, List, Any, Optional, Tuple
from collections import Counter
import re
class ReviewAnalyzer:
"""Analyzes user reviews for actionable insights."""
# Sentiment keywords
POSITIVE_KEYWORDS = [
'great', 'awesome', 'excellent', 'amazing', 'love', 'best', 'perfect',
'fantastic', 'wonderful', 'brilliant', 'outstanding', 'superb'
]
NEGATIVE_KEYWORDS = [
'bad', 'terrible', 'awful', 'horrible', 'hate', 'worst', 'useless',
'broken', 'crash', 'bug', 'slow', 'disappointing', 'frustrating'
]
# Issue indicators
ISSUE_KEYWORDS = [
'crash', 'bug', 'error', 'broken', 'not working', 'doesnt work',
'freezes', 'slow', 'laggy', 'glitch', 'problem', 'issue', 'fail'
]
# Feature request indicators
FEATURE_REQUEST_KEYWORDS = [
'wish', 'would be nice', 'should add', 'need', 'want', 'hope',
'please add', 'missing', 'lacks', 'feature request'
]
def __init__(self, app_name: str):
"""
Initialize review analyzer.
Args:
app_name: Name of the app
"""
self.app_name = app_name
self.reviews = []
self.analysis_cache = {}
def analyze_sentiment(
self,
reviews: List[Dict[str, Any]]
) -> Dict[str, Any]:
"""
Analyze sentiment across reviews.
Args:
reviews: List of review dicts with 'text', 'rating', 'date'
Returns:
Sentiment analysis summary
"""
self.reviews = reviews
sentiment_counts = {
'positive': 0,
'neutral': 0,
'negative': 0
}
detailed_sentiments = []
for review in reviews:
text = review.get('text', '').lower()
rating = review.get('rating', 3)
# Calculate sentiment score
sentiment_score = self._calculate_sentiment_score(text, rating)
sentiment_category = self._categorize_sentiment(sentiment_score)
sentiment_counts[sentiment_category] += 1
detailed_sentiments.append({
'review_id': review.get('id', ''),
'rating': rating,
'sentiment_score': sentiment_score,
'sentiment': sentiment_category,
'text_preview': text[:100] + '...' if len(text) > 100 else text
})
# Calculate percentages
total = len(reviews)
sentiment_distribution = {
'positive': round((sentiment_counts['positive'] / total) * 100, 1) if total > 0 else 0,
'neutral': round((sentiment_counts['neutral'] / total) * 100, 1) if total > 0 else 0,
'negative': round((sentiment_counts['negative'] / total) * 100, 1) if total > 0 else 0
}
# Calculate average rating
avg_rating = sum(r.get('rating', 0) for r in reviews) / total if total > 0 else 0
return {
'total_reviews_analyzed': total,
'average_rating': round(avg_rating, 2),
'sentiment_distribution': sentiment_distribution,
'sentiment_counts': sentiment_counts,
'sentiment_trend': self._assess_sentiment_trend(sentiment_distribution),
'detailed_sentiments': detailed_sentiments[:50] # Limit output
}
def extract_common_themes(
self,
reviews: List[Dict[str, Any]],
min_mentions: int = 3
) -> Dict[str, Any]:
"""
Extract frequently mentioned themes and topics.
Args:
reviews: List of review dicts
min_mentions: Minimum mentions to be considered common
Returns:
Common themes analysis
"""
# Extract all words from reviews
all_words = []
all_phrases = []
for review in reviews:
text = review.get('text', '').lower()
# Clean text
text = re.sub(r'[^\w\s]', ' ', text)
words = text.split()
# Filter out common words
stop_words = {
'the', 'and', 'for', 'with', 'this', 'that', 'from', 'have',
'app', 'apps', 'very', 'really', 'just', 'but', 'not', 'you'
}
words = [w for w in words if w not in stop_words and len(w) > 3]
all_words.extend(words)
# Extract 2-3 word phrases
for i in range(len(words) - 1):
phrase = f"{words[i]} {words[i+1]}"
all_phrases.append(phrase)
# Count frequency
word_freq = Counter(all_words)
phrase_freq = Counter(all_phrases)
# Filter by min_mentions
common_words = [
{'word': word, 'mentions': count}
for word, count in word_freq.most_common(30)
if count >= min_mentions
]
common_phrases = [
{'phrase': phrase, 'mentions': count}
for phrase, count in phrase_freq.most_common(20)
if count >= min_mentions
]
# Categorize themes
themes = self._categorize_themes(common_words, common_phrases)
return {
'common_words': common_words,
'common_phrases': common_phrases,
'identified_themes': themes,
'insights': self._generate_theme_insights(themes)
}
def identify_issues(
self,
reviews: List[Dict[str, Any]],
rating_threshold: int = 3
) -> Dict[str, Any]:
"""
Identify bugs, crashes, and other issues from reviews.
Args:
reviews: List of review dicts
rating_threshold: Only analyze reviews at or below this rating
Returns:
Issue identification report
"""
issues = []
for review in reviews:
rating = review.get('rating', 5)
if rating > rating_threshold:
continue
text = review.get('text', '').lower()
# Check for issue keywords
mentioned_issues = []
for keyword in self.ISSUE_KEYWORDS:
if keyword in text:
mentioned_issues.append(keyword)
if mentioned_issues:
issues.append({
'review_id': review.get('id', ''),
'rating': rating,
'date': review.get('date', ''),
'issue_keywords': mentioned_issues,
'text': text[:200] + '...' if len(text) > 200 else text
})
# Group by issue type
issue_frequency = Counter()
for issue in issues:
for keyword in issue['issue_keywords']:
issue_frequency[keyword] += 1
# Categorize issues
categorized_issues = self._categorize_issues(issues)
# Calculate issue severity
severity_scores = self._calculate_issue_severity(
categorized_issues,
len(reviews)
)
return {
'total_issues_found': len(issues),
'issue_frequency': dict(issue_frequency.most_common(15)),
'categorized_issues': categorized_issues,
'severity_scores': severity_scores,
'top_issues': self._rank_issues_by_severity(severity_scores),
'recommendations': self._generate_issue_recommendations(
categorized_issues,
severity_scores
)
}
def find_feature_requests(
self,
reviews: List[Dict[str, Any]]
) -> Dict[str, Any]:
"""
Extract feature requests and desired improvements.
Args:
reviews: List of review dicts
Returns:
Feature request analysis
"""
feature_requests = []
for review in reviews:
text = review.get('text', '').lower()
rating = review.get('rating', 3)
# Check for feature request indicators
is_feature_request = any(
keyword in text
for keyword in self.FEATURE_REQUEST_KEYWORDS
)
if is_feature_request:
# Extract the specific request
request_text = self._extract_feature_request_text(text)
feature_requests.append({
'review_id': review.get('id', ''),
'rating': rating,
'date': review.get('date', ''),
'request_text': request_text,
'full_review': text[:200] + '...' if len(text) > 200 else text
})
# Cluster similar requests
clustered_requests = self._cluster_feature_requests(feature_requests)
# Prioritize based on frequency and rating context
prioritized_requests = self._prioritize_feature_requests(clustered_requests)
return {
'total_feature_requests': len(feature_requests),
'clustered_requests': clustered_requests,
'prioritized_requests': prioritized_requests,
'implementation_recommendations': self._generate_feature_recommendations(
prioritized_requests
)
}
def track_sentiment_trends(
self,
reviews_by_period: Dict[str, List[Dict[str, Any]]]
) -> Dict[str, Any]:
"""
Track sentiment changes over time.
Args:
reviews_by_period: Dict of period_name: reviews
Returns:
Trend analysis
"""
trends = []
for period, reviews in reviews_by_period.items():
sentiment = self.analyze_sentiment(reviews)
trends.append({
'period': period,
'total_reviews': len(reviews),
'average_rating': sentiment['average_rating'],
'positive_percentage': sentiment['sentiment_distribution']['positive'],
'negative_percentage': sentiment['sentiment_distribution']['negative']
})
# Calculate trend direction
if len(trends) >= 2:
first_period = trends[0]
last_period = trends[-1]
rating_change = last_period['average_rating'] - first_period['average_rating']
sentiment_change = last_period['positive_percentage'] - first_period['positive_percentage']
trend_direction = self._determine_trend_direction(
rating_change,
sentiment_change
)
else:
trend_direction = 'insufficient_data'
return {
'periods_analyzed': len(trends),
'trend_data': trends,
'trend_direction': trend_direction,
'insights': self._generate_trend_insights(trends, trend_direction)
}
def generate_response_templates(
self,
issue_category: str
) -> List[Dict[str, str]]:
"""
Generate response templates for common review scenarios.
Args:
issue_category: Category of issue ('crash', 'feature_request', 'positive', etc.)
Returns:
Response templates
"""
templates = {
'crash': [
{
'scenario': 'App crash reported',
'template': "Thank you for bringing this to our attention. We're sorry you experienced a crash. "
"Our team is investigating this issue. Could you please share more details about when "
"this occurred (device model, iOS/Android version) by contacting support@[company].com? "
"We're committed to fixing this quickly."
},
{
'scenario': 'Crash already fixed',
'template': "Thank you for your feedback. We've identified and fixed this crash issue in version [X.X]. "
"Please update to the latest version. If the problem persists, please reach out to "
"support@[company].com and we'll help you directly."
}
],
'bug': [
{
'scenario': 'Bug reported',
'template': "Thanks for reporting this bug. We take these issues seriously. Our team is looking into it "
"and we'll have a fix in an upcoming update. We appreciate your patience and will notify you "
"when it's resolved."
}
],
'feature_request': [
{
'scenario': 'Feature request received',
'template': "Thank you for this suggestion! We're always looking to improve [app_name]. We've added your "
"request to our roadmap and will consider it for a future update. Follow us @[social] for "
"updates on new features."
},
{
'scenario': 'Feature already planned',
'template': "Great news! This feature is already on our roadmap and we're working on it. Stay tuned for "
"updates in the coming months. Thanks for your feedback!"
}
],
'positive': [
{
'scenario': 'Positive review',
'template': "Thank you so much for your kind words! We're thrilled that you're enjoying [app_name]. "
"Reviews like yours motivate our team to keep improving. If you ever have suggestions, "
"we'd love to hear them!"
}
],
'negative_general': [
{
'scenario': 'General complaint',
'template': "We're sorry to hear you're not satisfied with your experience. We'd like to make this right. "
"Please contact us at support@[company].com so we can understand the issue better and help "
"you directly. Thank you for giving us a chance to improve."
}
]
}
return templates.get(issue_category, templates['negative_general'])
def _calculate_sentiment_score(self, text: str, rating: int) -> float:
"""Calculate sentiment score (-1 to 1)."""
# Start with rating-based score
rating_score = (rating - 3) / 2 # Convert 1-5 to -1 to 1
# Adjust based on text sentiment
positive_count = sum(1 for keyword in self.POSITIVE_KEYWORDS if keyword in text)
negative_count = sum(1 for keyword in self.NEGATIVE_KEYWORDS if keyword in text)
text_score = (positive_count - negative_count) / 10 # Normalize
# Weighted average (60% rating, 40% text)
final_score = (rating_score * 0.6) + (text_score * 0.4)
return max(min(final_score, 1.0), -1.0)
def _categorize_sentiment(self, score: float) -> str:
"""Categorize sentiment score."""
if score > 0.3:
return 'positive'
elif score < -0.3:
return 'negative'
else:
return 'neutral'
def _assess_sentiment_trend(self, distribution: Dict[str, float]) -> str:
"""Assess overall sentiment trend."""
positive = distribution['positive']
negative = distribution['negative']
if positive > 70:
return 'very_positive'
elif positive > 50:
return 'positive'
elif negative > 30:
return 'concerning'
elif negative > 50:
return 'critical'
else:
return 'mixed'
def _categorize_themes(
self,
common_words: List[Dict[str, Any]],
common_phrases: List[Dict[str, Any]]
) -> Dict[str, List[str]]:
"""Categorize themes from words and phrases."""
themes = {
'features': [],
'performance': [],
'usability': [],
'support': [],
'pricing': []
}
# Keywords for each category
feature_keywords = {'feature', 'functionality', 'option', 'tool'}
performance_keywords = {'fast', 'slow', 'crash', 'lag', 'speed', 'performance'}
usability_keywords = {'easy', 'difficult', 'intuitive', 'confusing', 'interface', 'design'}
support_keywords = {'support', 'help', 'customer', 'service', 'response'}
pricing_keywords = {'price', 'cost', 'expensive', 'cheap', 'subscription', 'free'}
for word_data in common_words:
word = word_data['word']
if any(kw in word for kw in feature_keywords):
themes['features'].append(word)
elif any(kw in word for kw in performance_keywords):
themes['performance'].append(word)
elif any(kw in word for kw in usability_keywords):
themes['usability'].append(word)
elif any(kw in word for kw in support_keywords):
themes['support'].append(word)
elif any(kw in word for kw in pricing_keywords):
themes['pricing'].append(word)
return {k: v for k, v in themes.items() if v} # Remove empty categories
def _generate_theme_insights(self, themes: Dict[str, List[str]]) -> List[str]:
"""Generate insights from themes."""
insights = []
for category, keywords in themes.items():
if keywords:
insights.append(
f"{category.title()}: Users frequently mention {', '.join(keywords[:3])}"
)
return insights[:5]
def _categorize_issues(self, issues: List[Dict[str, Any]]) -> Dict[str, List[Dict[str, Any]]]:
"""Categorize issues by type."""
categories = {
'crashes': [],
'bugs': [],
'performance': [],
'compatibility': []
}
for issue in issues:
keywords = issue['issue_keywords']
if 'crash' in keywords or 'freezes' in keywords:
categories['crashes'].append(issue)
elif 'bug' in keywords or 'error' in keywords or 'broken' in keywords:
categories['bugs'].append(issue)
elif 'slow' in keywords or 'laggy' in keywords:
categories['performance'].append(issue)
else:
categories['compatibility'].append(issue)
return {k: v for k, v in categories.items() if v}
def _calculate_issue_severity(
self,
categorized_issues: Dict[str, List[Dict[str, Any]]],
total_reviews: int
) -> Dict[str, Dict[str, Any]]:
"""Calculate severity scores for each issue category."""
severity_scores = {}
for category, issues in categorized_issues.items():
count = len(issues)
percentage = (count / total_reviews) * 100 if total_reviews > 0 else 0
# Calculate average rating of affected reviews
avg_rating = sum(i['rating'] for i in issues) / count if count > 0 else 0
# Severity score (0-100)
severity = min((percentage * 10) + ((5 - avg_rating) * 10), 100)
severity_scores[category] = {
'count': count,
'percentage': round(percentage, 2),
'average_rating': round(avg_rating, 2),
'severity_score': round(severity, 1),
'priority': 'critical' if severity > 70 else ('high' if severity > 40 else 'medium')
}
return severity_scores
def _rank_issues_by_severity(
self,
severity_scores: Dict[str, Dict[str, Any]]
) -> List[Dict[str, Any]]:
"""Rank issues by severity score."""
ranked = sorted(
[{'category': cat, **data} for cat, data in severity_scores.items()],
key=lambda x: x['severity_score'],
reverse=True
)
return ranked
def _generate_issue_recommendations(
self,
categorized_issues: Dict[str, List[Dict[str, Any]]],
severity_scores: Dict[str, Dict[str, Any]]
) -> List[str]:
"""Generate recommendations for addressing issues."""
recommendations = []
for category, score_data in severity_scores.items():
if score_data['priority'] == 'critical':
recommendations.append(
f"URGENT: Address {category} issues immediately - affecting {score_data['percentage']}% of reviews"
)
elif score_data['priority'] == 'high':
recommendations.append(
f"HIGH PRIORITY: Focus on {category} issues in next update"
)
return recommendations
def _extract_feature_request_text(self, text: str) -> str:
"""Extract the specific feature request from review text."""
# Simple extraction - find sentence with feature request keywords
sentences = text.split('.')
for sentence in sentences:
if any(keyword in sentence for keyword in self.FEATURE_REQUEST_KEYWORDS):
return sentence.strip()
return text[:100] # Fallback
def _cluster_feature_requests(
self,
feature_requests: List[Dict[str, Any]]
) -> List[Dict[str, Any]]:
"""Cluster similar feature requests."""
# Simplified clustering - group by common keywords
clusters = {}
for request in feature_requests:
text = request['request_text'].lower()
# Extract key words
words = [w for w in text.split() if len(w) > 4]
# Try to find matching cluster
matched = False
for cluster_key in clusters:
if any(word in cluster_key for word in words[:3]):
clusters[cluster_key].append(request)
matched = True
break
if not matched and words:
cluster_key = ' '.join(words[:2])
clusters[cluster_key] = [request]
return [
{'feature_theme': theme, 'request_count': len(requests), 'examples': requests[:3]}
for theme, requests in clusters.items()
]
def _prioritize_feature_requests(
self,
clustered_requests: List[Dict[str, Any]]
) -> List[Dict[str, Any]]:
"""Prioritize feature requests by frequency."""
return sorted(
clustered_requests,
key=lambda x: x['request_count'],
reverse=True
)[:10]
def _generate_feature_recommendations(
self,
prioritized_requests: List[Dict[str, Any]]
) -> List[str]:
"""Generate recommendations for feature requests."""
recommendations = []
if prioritized_requests:
top_request = prioritized_requests[0]
recommendations.append(
f"Most requested feature: {top_request['feature_theme']} "
f"({top_request['request_count']} mentions) - consider for next major release"
)
if len(prioritized_requests) > 1:
recommendations.append(
f"Also consider: {prioritized_requests[1]['feature_theme']}"
)
return recommendations
def _determine_trend_direction(
self,
rating_change: float,
sentiment_change: float
) -> str:
"""Determine overall trend direction."""
if rating_change > 0.2 and sentiment_change > 5:
return 'improving'
elif rating_change < -0.2 and sentiment_change < -5:
return 'declining'
else:
return 'stable'
def _generate_trend_insights(
self,
trends: List[Dict[str, Any]],
trend_direction: str
) -> List[str]:
"""Generate insights from trend analysis."""
insights = []
if trend_direction == 'improving':
insights.append("Positive trend: User satisfaction is increasing over time")
elif trend_direction == 'declining':
insights.append("WARNING: User satisfaction is declining - immediate action needed")
else:
insights.append("Sentiment is stable - maintain current quality")
# Review velocity insight
if len(trends) >= 2:
recent_reviews = trends[-1]['total_reviews']
previous_reviews = trends[-2]['total_reviews']
if recent_reviews > previous_reviews * 1.5:
insights.append("Review volume increasing - growing user base or recent controversy")
return insights
def analyze_reviews(
app_name: str,
reviews: List[Dict[str, Any]]
) -> Dict[str, Any]:
"""
Convenience function to perform comprehensive review analysis.
Args:
app_name: App name
reviews: List of review dictionaries
Returns:
Complete review analysis
"""
analyzer = ReviewAnalyzer(app_name)
return {
'sentiment_analysis': analyzer.analyze_sentiment(reviews),
'common_themes': analyzer.extract_common_themes(reviews),
'issues_identified': analyzer.identify_issues(reviews),
'feature_requests': analyzer.find_feature_requests(reviews)
}