startup-review-mining
Systematic extraction of pain points, feature gaps, switching triggers, and opportunities from review sources (B2B review sites, app stores, forums, communities, issue trackers). Includes bias hygiene, taxonomy building, and turning insights into experiments.
npx skills add majiayu000/claude-skill-registry --skill startup-review-mining-vasilyu1983-ai-agents-public --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Review Mining Skill — Quick Reference This skill extracts recurring customer pain and constraints from reviews and testimonials, then converts them into product bets and experiments. Treat reviews as a biased sample; triangulate before betting. **Key Distinction from `software-ux-research`**: - `software-ux-research` = UI/UX pain points only - `startup-review-mining` (this skill) = ALL pain dimensions (pricing, support, integration, performance, onboarding, value gaps) **Modern Best Practices (Dec 2025)**: - Start with source hygiene: sampling plan, platform skews, and fake-review defenses. - Build a taxonomy (theme × segment × severity) before counting keywords. - Convert insights into bets with explicit success metrics and decision rules. - Handle customer/market data with purpose limitation, retention, and access controls. --- ## When to Use This Skill Invoke when users ask for: - Pain point extraction from reviews (any source) - Competitive weakness analysis - Feature gap identification - Switching trigger analysis (why customers leave competitors) - Market opportunity discovery through customer complaints - Review sentiment analysis across platforms - B2B software evaluation
- When to Use This Skill
- Quick Reference Table
- Review Source Hygiene (Dec 2025)
- Sampling and Bias Checklist
- Fake Review and Manipulation Defenses
- The 7 Pain Dimensions
- Decision Tree: Choosing Mining Approach
- Review Sources (Complete Guide)
- Tier 1: Very High Signal (Start Here)
- Tier 2: High Signal
- Tier 3: Medium Signal
- Navigation: Resources
- Extraction Methodology
- Analysis Frameworks
What does the startup-review-mining skill do?
Systematic extraction of pain points, feature gaps, switching triggers, and opportunities from review sources (B2B review sites, app stores, forums, communities, issue trackers). Includes bias hygiene, taxonomy building, and turning insights into experiments.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill startup-review-mining-vasilyu1983-ai-agents-public --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.