review-analysis
Skill1 starsChanged 46 days agoMITView on GitHub
Summarise what users love and hate about an app from its App Store or Google Play reviews, with themes, frequencies, short quotes and version-specific issues. Use when the user asks about complaints, feature requests, user sentiment or reviews of an app. Needs the ASOSpy MCP server.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- AppKittie/aso-mcp-skillstheir own version, first seen Nov 8, 2026
- fitlab-ai/agent-infratheir own version, first seen Oct 27, 2026
- Nirusan/claude-configtheir own version, first seen Oct 13, 2026
- liangdabiao/amazon-sorftime-research-MCP-skilltheir own version, first seen Oct 13, 2026
- trysonar/skillstheir own version, first seen Oct 1, 2026
- Ethan-paseya/amazon-sellersprite-research-MCP-skilltheir own version, first seen Jul 13, 2026
Used with
Projects with it also use revenue-analysis.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
trysonarSkillrevenue-analysis
When the user wants to estimate or benchmark app revenue and downloads — validating an app idea, sizing a niche, comparing monetization across apps, or reading their own App Store Connect sales on the App Store or Google Play. Also use when the user mentions "how much does this app make", "revenue estimate", "app downloads estimate", "market size", "is this niche profitable", or "my sales". For finding the apps to benchmark, see market-discovery. For full competitor teardowns, see competitor-analysis.
Also in 3 projects that use this
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- liangdabiao/amazon-sorftime-research-MCP-skill★ 1.1ksame name
- fitlab-ai/agent-infra★ 87same name
- AppKittie/aso-mcp-skills★ 8same name
- Nirusan/claude-config★ 7same name
- Ethan-paseya/amazon-sellersprite-research-MCP-skill★ 2same name
- trysonar/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- app-discoverySkill
- aso-auditSkill
- competitor-analysisSkill
- growth-analysisSkill
- keyword-researchSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
After a rating drop, to find the cause.
- Distinctive: line 35
Check whether a theme is tied to one version or date.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Review analysis
When to use
- "What do users complain about in X?", "what do people like about X?", "what are the top feature requests?".
- After a rating drop, to find the cause.
- To mine competitors' reviews for product ideas.
Inputs
| Input | Default | Notes |
| App | required | Any identifier. |
| Country | all | Optional two-letter filter; many reviews have no country. |
| Focus | none | Optional topic, e.g. "pricing", "crashes", "sync". |
Tools
get_app_reviews—sort:most_recent,highest_ratedorlowest_rated;rating1–5 filter;limitup to 50 per page withcursor.get_app_detail— current version and rating.get_app_historicals—metrics: ["score", "ratings"]for the rating trend.
Workflow
get_app_detail: current version,ratingScore,ratingsCount.get_app_reviewswithsort: "lowest_rated",limit: 50, then one more page withcursor.get_app_reviewswithsort: "highest_rated",limit: 50.get_app_reviewswithsort: "most_recent",limit: 50.- Group the reviews into themes (bugs, pricing, missing features, UX, support, ads...). Count each theme and pick one short quote.
- Check whether a theme is tied to one version or date.
get_app_historicalswithmetrics: ["score", "ratings"]to see whether the rating moved.
Output
- Top complaints and top praises: theme, count in the sample, one short quote (under 20 words).
- Version- or date-specific issues.
- Five prioritised fixes or product ideas.
- State the sample size ("based on 200 reviews"). This is a sample, not every review.
Limitations
- There are no developer replies and no "helpful" votes in the data.
- The sample is what the tool returns for each sort, not a statistically random sample.
- Quote briefly; do not paste long reviews.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.