Copycat Scout

Turn an app seed or idea into a compact, deduplicated iOS/Android shortlist. Discovery stops before review collection so the user can choose which apps merit a spike.

Scout

1. Resolve <skill-dir> as the directory containing this SKILL.md.

2. Ask for target markets when the user has not supplied them. Run one of these modes; omit --root to use <workspace>/.copycat/scout:

   python3 <skill-dir>/scripts/scout_competitors.py --markets <us,de,...|worldwide> <apple-or-google-url-or-id> [...]
   python3 <skill-dir>/scripts/scout_competitors.py --markets <...> --query "<free-text app idea>" [--query "..."]
   

   --input <json-md-or-text-file> may supplement either mode. Every seed searches both stores, while same-store recommendations add a stronger signal. CLI default worldwide is a bounded adaptive sample when an unattended caller omits scope.

3. Read <output-root>/portfolio-shortlist.md, not the raw candidate corpus. --shortlist is a global portfolio bound even when multiple seeds are supplied. Inspect an origin's <origin-folder>/shortlist.md only when origin-specific evidence matters.

4. Present the shortlist and ask the user which apps to spike. After selection, pass only those URLs to copycat-reviews; review-urls.txt is a compact candidate menu, not authorization to collect reviews.

Evidence boundaries