{"slug":"repo-doctor","title":"repo-doctor","description":"repo-doctor diagnoses README \"shape problems\" — the hero never lands, install-to-first-success buries the lede, the \"what is this\" sentence assumes prior context, the badge row is louder than the content — and produces a prioritized punch list a maintainer can act on in an afternoon. Read-only by default; opens a PR only when the user explicitly asks.\n\nKey features:\n- 9-criterion rubric scored 1–5 with cited line numbers and one-line fixes\n- Rubric weighting adapts to inferred repo category: library, CLI, framework, app, spec, or personal project\n- Audience inference (working developers, newcomers, maintainers, mixed) — catches the most common shape problem: README pitched at the wrong audience for its category\n- Punch list grouped P0 (blocking) / P1 (high-leverage) / P2 (nice-to-have)\n- Three operating modes (Auto / Semi-auto / Manual) with the same conversational density tradeoff as repo-visuals\n- Optional upstream PR with the punch list as the description; never auto-applies edits","developer":"livlign","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-10T06:11:22.678Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/livlign/claude-skills.git","web_data":{},"github_data":{},"catalog_sources":{"community":[{"name":"repo-doctor","source":{"ref":"main","sha":"7f66ce9d577e51456260e6b4062bcc9c488d9224","url":"https://github.com/livlign/claude-skills.git","path":"plugins/repo-doctor","source":"git-subdir"},"homepage":"https://github.com/livlign/claude-skills/tree/main/plugins/repo-doctor","description":"repo-doctor diagnoses README \"shape problems\" — the hero never lands, install-to-first-success buries the lede, the \"what is this\" sentence assumes prior context, the badge row is louder than the content — and produces a prioritized punch list a maintainer can act on in an afternoon. Read-only by default; opens a PR only when the user explicitly asks.\n\nKey features:\n- 9-criterion rubric scored 1–5 with cited line numbers and one-line fixes\n- Rubric weighting adapts to inferred repo category: library, CLI, framework, app, spec, or personal project\n- Audience inference (working developers, newcomers, maintainers, mixed) — catches the most common shape problem: README pitched at the wrong audience for its category\n- Punch list grouped P0 (blocking) / P1 (high-leverage) / P2 (nice-to-have)\n- Three operating modes (Auto / Semi-auto / Manual) with the same conversational density tradeoff as repo-visuals\n- Optional upstream PR with the punch list as the description; never auto-applies edits"}]},"manifest":{"url":"https://raw.githubusercontent.com/livlign/claude-skills/7f66ce9d577e51456260e6b4062bcc9c488d9224/plugins/repo-doctor/.claude-plugin/plugin.json","payload":{"name":"repo-doctor","author":{"name":"livlign"},"version":"0.1.0","homepage":"https://github.com/livlign/claude-skills","keywords":["readme","readme-review","readme-audit","documentation","github","open-source","maintainer-tools"],"repository":"https://github.com/livlign/claude-skills","description":"Diagnostic skills for GitHub repos. Currently ships readme-doctor — a structured review of a repo's README against best-practice patterns (hero presence, install-to-first-success length, audience match, drift signals), output as a prioritized punch list."},"observed_at":"2026-11-06T10:48:24Z"}}