[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ENHM3W1A0MY44ZD8D4NWVF":3,"skill-same:01M6ENHM3W1A0MY44ZD8D4NWVF":64},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M6ENHM3W1A0MY44ZD8D4NWVF","dev-review",null,"Post-coding exhaustive review — catches integration bugs, runtime crashes, performance issues, and convention drift across all changed files","launchpathventures\u002Fditto-os","launchpathventures","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F248658966?v=4","01M6ENF40K8DMPD2Q4YBJX3EWK","01M6ENF4541FAB13MQFNS8RMK8",1,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Flaunchpathventures\u002Fditto-os\u002Fblob\u002Fmain\u002F.catalyst\u002Fskills\u002Fdev-review\u002FSKILL.md",[],[18,19,20,21,22,23,24,25,26,27,28,29,30],"review","dev","dev review","performance","issues","integration","coding","fix","files","drift","across","runtime","post","2026-11-10 10:12:30",false,"---\nname: dev-review\ndescription: Post-coding exhaustive review — catches integration bugs, runtime crashes, performance issues, and convention drift across all changed files\nargument-hint: \"[--fix]\"\n---\n\n## Why This Skill Exists\n\nAI coding sessions produce code that compiles but hides integration bugs, runtime crashes, performance traps, and convention drift. These issues compound across sessions and are invisible without systematic review. `\u002Fdev-review` runs a multi-pass audit on every file changed in the current session, catching the bugs that `pnpm run type-check` and linters miss.\n\nThis skill was born from a real session where **five consecutive \"looks clean\" reviews** each found critical bugs — wrong database table queries, N+1 API calls, unstable React dependencies, missing auth checks, ownership bugs, and silent data flow failures. The lesson: static code reading catches ~40% of bugs. You need progressive depth — imports, then integration, then runtime paths, then performance, then UX edge cases.\n\n## Repo Context\n\n- Read `@AGENTS.md` — repo conventions (container queries, core components, route helpers, etc.)\n- Read `@catalyst\u002FLEARNINGS.md` — known AI mistake patterns\n\n## How It Works\n\nThe review runs **five sequential passes** at increasing depth. Each pass catches a different class of bug. Do NOT skip passes or combine them — the layered approach is the point.\n\nRun on all files changed since the last commit (or since branch diverged from base):\n\n```bash\ngit diff --name-only HEAD  # uncommitted changes\ngit diff --name-only origin\u002Fmain...HEAD  # full branch diff\n```\n\nIf `$ARGUMENTS` contains `--fix`, fix issues as you find them. Otherwise, report only.\n\n## Routing\n\n→ See [dev-review-checklist.md](references\u002Fdev-review-checklist.md)\n\n## Guardrails\n\n- Review ONLY files that were changed — don't audit the entire codebase\n- Report issues with file path and line number\n- Don't fix issues unless `--fix` is passed — document them clearly\n- Run `pnpm run type-check` at the end to confirm no regressions\n- If you find >10 issues, stop after Pass 3 and ask the user if they want to continue\n","## Why This Skill Exists\n\nAI coding sessions produce code that compiles but hides integration bugs, runtime crashes, performance traps, and convention drift. These issues compound across sessions and are invisible without systematic review. `\u002Fdev-review` runs a multi-pass audit on every file changed in the current session, catching the bugs that `pnpm run type-check` and linters miss.\n\nThis skill was born from a real session where **five consecutive \"looks clean\" reviews** each found critical bugs — wrong database table queries, N+1 API calls, unstable React dependencies, missing auth checks, ownership bugs, and silent data flow failures. The lesson: static code reading catches ~40% of bugs. You need progressive depth — imports, then integration, then runtime paths, then performance, then UX edge cases.\n\n## Repo Context\n\n- Read `@AGENTS.md` — repo conventions (container queries, core components, route helpers, etc.)\n- Read `@catalyst\u002FLEARNINGS.md` — known AI mistake patterns\n\n## How It Works\n\nThe review runs **five sequential passes** at increasing depth. Each pass catches a different class of bug. Do NOT skip passes or combine them — the layered approach is the point.\n\nRun on all files changed since the last commit (or since branch diverged from base):\n\n```bash\ngit diff --name-only HEAD  # uncommitted changes\ngit diff --name-only origin\u002Fmain...HEAD  # full branch diff\n```\n\nIf `$ARGUMENTS` contains `--fix`, fix issues as you find them. Otherwise, report only.\n\n## Routing\n\n→ See [dev-review-checklist.md](references\u002Fdev-review-checklist.md)\n\n## Guardrails\n\n- Review ONLY files that were changed — don't audit the entire codebase\n- Report issues with file path and line number\n- Don't fix issues unless `--fix` is passed — document them clearly\n- Run `pnpm run type-check` at the end to confirm no regressions\n- If you find >10 issues, stop after Pass 3 and ask the user if they want to continue\n",{"name":5,"description":7,"argument-hint":36},"[--fix]","main","b033b1a8919dbb7c98e97cf24547a2416f65b53e",".catalyst\u002Fskills\u002Fdev-review",0,"https:\u002F\u002Fgithub.com\u002Flaunchpathventures\u002Fditto-os","https:\u002F\u002Fgithub.com\u002Flaunchpathventures","2026-06-08 19:31:48",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add launchpathventures\u002Fditto-os --skill dev-review",{"tool":50,"command":51},"bunx","bunx skills add launchpathventures\u002Fditto-os --skill dev-review",{"tool":53,"command":54},"pnpm","pnpm dlx skills add launchpathventures\u002Fditto-os --skill dev-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flaunchpathventures\u002Fditto-os\u002Fblob\u002Fmain\u002F.catalyst\u002Fskills\u002Fdev-review\u002FSKILL.md",true,[58],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fdev-review-checklist.md","REFERENCE","参考文档",9888,"https:\u002F\u002Fgithub.com\u002Flaunchpathventures\u002Fditto-os\u002Fblob\u002Fmain\u002F.catalyst\u002Fskills\u002Fdev-review\u002Freferences\u002Fdev-review-checklist.md",[65,86,91,112,117,122],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":31},"01M6ENJ12VWSMRZ4MW8550AG69","drain-queue","Cross-brief autopilot — claim the oldest ready brief whose Brief NNN deps are satisfied via atomic push, run \u002Fautobuild on each, stop when the queue is empty, blocked, or hits a failure.","https:\u002F\u002Fgithub.com\u002Flaunchpathventures\u002Fditto-os\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdrain-queue\u002FSKILL.md",[],[72,73,74,75,76,77,78,79,80,81,82,83,84,85],"drain queue","queue","push","autobuild","via","autopilot","empty","claim","max","stop","ready","deps","brief","run",{"skillNo":87,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":31},"01M6ENHXG16WJ4PN8CJHZYNT5T","https:\u002F\u002Fgithub.com\u002Flaunchpathventures\u002Fditto-os\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdev-review\u002FSKILL.md",[],[19,18,20,21,22,30,29,28,27,26,25,24,23],{"skillNo":92,"name":75,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":31},"01M6ENHSZBZFSB69TSV2TWGRJ1","End-to-end autopilot for a single brief — pre-flight, \u002Fdev-builder, fresh-subagent reviewers, push, open PR, mark **PR:** line on feature branch. Stops at the human merge gate.","https:\u002F\u002Fgithub.com\u002Flaunchpathventures\u002Fditto-os\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fautobuild\u002FSKILL.md",[],[75,97,98,74,99,100,101,102,103,77,104,105,106,107,108,109,19,110,111,84],"branch","open","merge gate","line","subagent","name","fresh","end","feature","human","builder","gate","open pr","pr","merge",{"skillNo":113,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":31},"01M6ENHPWYMN66EYQBV56HP9CW","https:\u002F\u002Fgithub.com\u002Flaunchpathventures\u002Fditto-os\u002Fblob\u002Fmain\u002F.catalyst\u002Fskills\u002Fdrain-queue\u002FSKILL.md",[],[73,72,80,75,76,77,78,79,81,82,83,84,74,85],{"skillNo":118,"name":75,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":31},"01M6ENHF62C7G6BC4YG44RWFB0","https:\u002F\u002Fgithub.com\u002Flaunchpathventures\u002Fditto-os\u002Fblob\u002Fmain\u002F.catalyst\u002Fskills\u002Fautobuild\u002FSKILL.md",[],[75,109,104,105,106,108,107,97,101,99,98,84,77,74,19,110,111,100,102,103],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":31},"01M6ENHBWGWPCR07Y9W1CTTMNE","typeset","Improves typography by fixing font choices, hierarchy, sizing, weight, and readability so text feels intentional. Use when the user mentions fonts, type, readability, text hierarchy, sizing looks off, or wants more polished, intentional typography.","https:\u002F\u002Fgithub.com\u002Flaunchpathventures\u002Fditto-os\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftypeset\u002FSKILL.md",[],[124,129,130,131,132,133,134],"type","readability","typography","use","user","text"]