fbfa3aece7
Replaces the AppBrain scraper (Cloudflare-blocked 403, confirmed dead).
play.google.com server-rendered chart HTML works: live-validated, real
Android packages + names + ratings from both /store/apps/top and
/store/apps/category/<CAT>. CLI: <top|category> [--category CAT]
[--region R] [--limit N] [--html-file F]; output source:"google-play",
entries {rank,name,package,rating}. Package link is the stable field;
title (Epkrse class) and rating are best-effort.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| .claude-plugin | ||
| commands | ||
| skills/market-research | ||
| tests | ||
| README.md | ||
README.md
market-research
A Claude Code plugin that autonomously researches the app/game market and surfaces
scored, non-repeating clone candidates, then hands user-chosen candidates to the
clone-app plugin for feasibility analysis.
What it does
/market-research runs a 6-phase workflow:
- Seed rotation — pick varied search angles (category × region × niche) so runs differ.
- Gather — App Store RSS chart data (
fetch-charts.py) + free web search for trends. - Synthesize — cluster findings into ≥10 distinct app/game ideas.
- Score — composite score: cloneability + market opportunity + monetization fit.
- Dedup — exclude anything already in
./work/market-research/history.json. - Present + handoff — show the ranked table; chosen candidates flow into
clone-app.
State
Written under ./work/market-research/ in your current directory:
history.json— every past suggestion; the non-repeat memory.research-<date>.md— the full report for a run.
Scripts
scripts/fetch-charts.py— fetch App Store RSS chart feeds → normalized JSON.scripts/history.py— read / append / dedup the suggestion history.
Python is stdlib-only. Tests run offline against tests/fixtures/:
bash plugins/market-research/tests/run-all.sh
Effort convention
Effort is measured in AI Sprints (one focused Claude session), never calendar time.