App review evidence research
Skill hijabcantic-dotcom/app-review-opportunity-research-template/app-review-evidence-research
Turn public App Store and Google Play reviews into an evidence brief, product hypothesis, and customer-interview questions. Use when evaluating a competitor, testing a mobile-app idea, preparing an ASO or product discovery brief, or deciding what to investigate before building.From its SKILL.md
npx -y skills add hijabcantic-dotcom/app-review-opportunity-research-template --skill app-review-evidence-researchAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.2 KB, 398 tokens by cl100k_base, as published. Nobody here has run it
App Review Evidence Research
Use public reviews as research leads, not proof of demand, willingness to pay, market size, or a roadmap.
Workflow
- Define one competitor and one customer job. Do not begin with a feature list.
- Collect 20 to 50 recent low-rating reviews from the App Store or Google Play. Record links or dates and redact personal data.
- Copy
../research-template.mdand preserve exact excerpts in the raw-evidence table. - Cluster reviews only when the user, job, failure, and consequence are materially the same. Keep the count and sample size beside each cluster.
- For every cluster, state what evidence would disprove it. Exclude vague ratings, one-off bugs, and complaints without a job or consequence.
- Repeat the check with two to four close alternatives. Distinguish a category-wide failure from one product's implementation issue.
- Write one narrow hypothesis and interview people who experience the job. Include a smallest test, success signal, and stop signal.
Evidence Rules
- Quote the review instead of rewriting it as a feature request.
- Separate observed facts from interpretation.
- Treat repetition as a reason to interview, not validation that people will pay.
- Do not invent review quotes, author names, dates, counts, ratings, or competitor comparisons.
- Do not recommend a build when the sample cannot show a specific job, failure, and consequence.
Deliverable
Return a concise evidence brief with:
- Scope and review sample
- Two to four repeated pain-point clusters with source evidence
- A cross-competitor check
- One falsifiable opportunity hypothesis
- Customer interview questions and a clear next decision
For a larger public-review sample, Review2Idea can group evidence into pain-point clusters: https://review2idea.com/en/free-app-review-analysis-tool?utm_source=github&utm_medium=referral&utm_campaign=app_review_evidence_research_skill
What ships with it: 1 file
249 B alongside SKILL.md
agents/
- openai.yaml249 B