AgentStack
SKILL verified MIT Self-run

Aso Reviews

skill-felixgraeber-claude-aso-audit-skill-aso-reviews · by FelixGraeber

>

No reviews yet
0 installs
10 views
0.0% view→install

Install

$ agentstack add skill-felixgraeber-claude-aso-audit-skill-aso-reviews

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Aso Reviews? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

ASO Reviews — Review & Rating Management

Capabilities

  1. Rating distribution and trend analysis
  2. Sentiment classification (positive/neutral/negative)
  3. Theme clustering (performance, UI, features, pricing, bugs, support)
  4. Keyword extraction from review text (Android: reviews are indexed!)
  5. Developer response strategy and templates
  6. Review velocity assessment

Process

  1. Fetch reviews (from listing data or user-provided JSON)
  2. Run sentiment analysis: uv run python scripts/review_analyzer.py --file reviews.json --json
  3. Extract keyword themes
  4. Analyze rating distribution
  5. Generate response templates for negative reviews

Scoring (0-100)

| Factor | Weight | Thresholds | |--------|--------|-----------| | Average rating | 30% | 1000=Strong | | Sentiment ratio | 20% | >70% positive=Good, 50-70%=Fair, 80%=Excellent, 50-80%=Good, Thank you for reporting this. We've identified the [specific issue] and our team is working on a fix for the next update. Please contact us at [email] if you need immediate help.

1-2 star (feature request): > We appreciate your feedback about [feature]. This is on our roadmap and we're actively working on it. We'll keep you updated.

3 star (mixed): > Thanks for the detailed feedback! We're glad [positive aspect] is working well. We hear you on [negative aspect] and are improving it in upcoming updates.

4-5 star: > Thank you for the kind words! We're thrilled you enjoy [specific feature]. Your support means a lot to our team.

Output Format

# Review Analysis: [App Name]

## Rating Health
- Average: X.X/5.0
- Distribution: [histogram]
- Volume: X total reviews
- Velocity: X reviews/week

## Sentiment Analysis
- Positive: X%
- Neutral: X%
- Negative: X%

## Top Themes
| Theme | Mentions | Sentiment | Key Quotes |
|-------|----------|-----------|------------|

## Keyword Opportunities (from reviews)
[Keywords frequently mentioned that could inform metadata]

## Recommended Response Actions
[Prioritized list of reviews to respond to]

Available Tools

Read, Bash, Write, Glob, Grep

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.