scoutlisted

Competitive reconnaissance for your project — what do the repos solving this same problem do better, and what's worth adopting? Finds peer repos (ranked by activity, downloads, dependents — never raw stars), mines what their users beg for — issue reactions, releases, docs claims, every finding with a locator — and verdicts each candidate feature ADOPT/ADAPT/SKIP/WATCH, where SKIP is the default and "a competitor has it" is never a reason. ADOPT items become ready seeds for feature or autopilot; verdicts persist in out/scout/tracker.md so repeat runs open with what changed. Keyless. Use for "what are similar projects doing", "compare us to X", "what are we missing" — e.g. "/scout", "/scout <owner/repo>", "/scout deep <repo>". For X-vs-Y tech choices use verdict; for community buzz use pulse.
duthaho/skillhub · ★ 6 · AI & Automation · score 75

Install: claude install-skill duthaho/skillhub

# scout — know the neighbors before building blind `/scout` — find peer projects, then reconnoiter them `/scout <owner/repo> [...]` — reconnoiter exactly these peers `/scout deep <owner/repo>` — one peer, source-level (clone + file:line evidence) Answer one question: **what have the projects solving this same problem learned that we haven't — and which of those lessons deserves to exist here?** Both halves matter: a scout that only returns "features to copy" is just an automated parity trap. The deliverable is judgment: adopt this, skip that, and the evidence either way. ## Step 0 — Know thyself first Recon of others starts with a fix on your own position: - Read this repo's `AGENTS.md` (the map skill writes it), `README`, and its own issue tracker's top-reacted open requests. Distill: **the project's job in one sentence**, and its **differentiation axis** — the thing it does that peers don't, which every later verdict is judged against. - Read `out/scout/tracker.md` if it exists: peers already scouted, verdicts already made. A feature SKIPped with a reason isn't re-litigated unless the evidence changed; repeat runs open with **"Since last scout"** — new releases, new high-reaction requests, verdicts due for revisit. - "Similar" means **same problem, not same tech stack** — a peer in another language that owns your problem space teaches more than a same-framework neighbor that doesn't. ## Step 1 — Find the peers (skip when the user names them) Discover