[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EAM2DDFMH9NCHDPRMK2BKH":3,"skill-same:01M7EAM2DDFMH9NCHDPRMK2BKH":52},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7EAM2DDFMH9NCHDPRMK2BKH","retro",null,"Retrospective that improves the agent's environment (checks, standards, navigation), not the code. Use when a build finishes, a session went sideways, or the user asks for a retro.","navaniharsh31\u002Fkeel","navaniharsh31","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9514867?v=4","01M7EAKEK1XG862WJ5KK5DW1VW","Harsh Navani","01M7EAKEKP39B1RZWSE3GN9X3K",0,"MIT","https:\u002F\u002Fgithub.com\u002Fnavaniharsh31\u002Fkeel\u002Fblob\u002Fmain\u002Fskills\u002Fretro\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: retro\ndescription: Retrospective that improves the agent's environment (checks, standards, navigation), not the code. Use when a build finishes, a session went sideways, or the user asks for a retro.\n---\n\nA **retrospective** improves the coding agent's **environment** (the checks, standards and pointers around the code) so future runs go better. The code itself is out of its reach.\n\n## Steps\n\n### 1. Read the primary sources\n\nThe current session's conversation, diff since the spec's `Base:`, review report, every `BLOCKED:` and red suite; or, if the user names another session, its logs on this machine.\n\nDone when you can list every mistake, detour, and slow lookup in the session.\n\n### 2. Find candidates\n\n- **Navigation**: a file or fact took long to find, or files hide dependencies: a **navigation pointer**?\n- **Automated checks**: a check (lint, types, tests, filesystem linters) could have caught a mistake. Read the repo's own check command first (`package.json` or build-tool scripts, the CI workflow): a check that exists but is unwired or silently broken is the finding, its fix is the wiring, and the code it would flag is a follow-up. A repo with no **guardrail** (no pre-commit hook and no CI job running its lint\u002Ftypecheck\u002Ftest command) is itself a finding.\n- **Coding standards**: the **reviewer agent** missed a mistake: add, remove or clarify a rule.\n- **AGENTS.md \u002F CLAUDE.md** (repo or global) grown large: steering that belongs in standards or checks, and **no-ops** (instructions that change nothing).\n- **Tool economy**: an expensive call, or token-hungry custom tooling (CLIs, MCPs), to streamline.\n- **Information access**: a crucial fact out of reach (teed dev-server logs, read-only third-party access).\n\nClassify each by where its fix lives:\n\n- **Mechanical → a check**: a fixed syntactic pattern, banned API, import shape or file-location rule. Prefer the check to a written rule.\n- **Judgement → `CODING_STANDARDS.md`**: cross-file consistency, \"matches the surrounding style\", anything no guardrail could check.\n- **Navigation → a `CLAUDE.md` pointer**: one line naming a file and when to reach for it.\n- **Out of reach → a follow-up** for a new Bug or Change: product code, tests, dependency pins and edits to existing rules.\n\nDone when every item from step 1 is a classified candidate or judged not worth fixing.\n\n### 3. List, then pick\n\nList the candidates most severe first, each with its evidence, class and exact fix; or say nothing is worth fixing and skip to Done.\n\nAsk through `AskUserQuestion` on its own, `multiSelect`, at most 4 candidates per question, the rest in further questions of the same call. Without `AskUserQuestion`, list and stop: a candidate is applied only when a reply that arrives after the listing names it, and one that names nothing (\"take your recommendations\") applies nothing.\n\nDone when the candidates are listed and the user has answered every question, or, without `AskUserQuestion`, the list is printed.\n\n### 4. Apply\n\nRead [WRITING.md](WRITING.md), then apply every chosen candidate. Run a new check once: it passes on the current tree and, where reproducible, catches the original mistake. Commit as `chore(retro): \u003Cwhat changed>`, on the starting branch when the fix branch is already merged.\n\nDone when every chosen candidate is applied and committed.\n\n## Done\n\n- [ ] Every candidate a pick (or, without `AskUserQuestion`, a later reply) named is applied and committed; nothing else was applied.\n","A **retrospective** improves the coding agent's **environment** (the checks, standards and pointers around the code) so future runs go better. The code itself is out of its reach.\n\n## Steps\n\n### 1. Read the primary sources\n\nThe current session's conversation, diff since the spec's `Base:`, review report, every `BLOCKED:` and red suite; or, if the user names another session, its logs on this machine.\n\nDone when you can list every mistake, detour, and slow lookup in the session.\n\n### 2. Find candidates\n\n- **Navigation**: a file or fact took long to find, or files hide dependencies: a **navigation pointer**?\n- **Automated checks**: a check (lint, types, tests, filesystem linters) could have caught a mistake. Read the repo's own check command first (`package.json` or build-tool scripts, the CI workflow): a check that exists but is unwired or silently broken is the finding, its fix is the wiring, and the code it would flag is a follow-up. A repo with no **guardrail** (no pre-commit hook and no CI job running its lint\u002Ftypecheck\u002Ftest command) is itself a finding.\n- **Coding standards**: the **reviewer agent** missed a mistake: add, remove or clarify a rule.\n- **AGENTS.md \u002F CLAUDE.md** (repo or global) grown large: steering that belongs in standards or checks, and **no-ops** (instructions that change nothing).\n- **Tool economy**: an expensive call, or token-hungry custom tooling (CLIs, MCPs), to streamline.\n- **Information access**: a crucial fact out of reach (teed dev-server logs, read-only third-party access).\n\nClassify each by where its fix lives:\n\n- **Mechanical → a check**: a fixed syntactic pattern, banned API, import shape or file-location rule. Prefer the check to a written rule.\n- **Judgement → `CODING_STANDARDS.md`**: cross-file consistency, \"matches the surrounding style\", anything no guardrail could check.\n- **Navigation → a `CLAUDE.md` pointer**: one line naming a file and when to reach for it.\n- **Out of reach → a follow-up** for a new Bug or Change: product code, tests, dependency pins and edits to existing rules.\n\nDone when every item from step 1 is a classified candidate or judged not worth fixing.\n\n### 3. List, then pick\n\nList the candidates most severe first, each with its evidence, class and exact fix; or say nothing is worth fixing and skip to Done.\n\nAsk through `AskUserQuestion` on its own, `multiSelect`, at most 4 candidates per question, the rest in further questions of the same call. Without `AskUserQuestion`, list and stop: a candidate is applied only when a reply that arrives after the listing names it, and one that names nothing (\"take your recommendations\") applies nothing.\n\nDone when the candidates are listed and the user has answered every question, or, without `AskUserQuestion`, the list is printed.\n\n### 4. Apply\n\nRead [WRITING.md](WRITING.md), then apply every chosen candidate. Run a new check once: it passes on the current tree and, where reproducible, catches the original mistake. Commit as `chore(retro): \u003Cwhat changed>`, on the starting branch when the fix branch is already merged.\n\nDone when every chosen candidate is applied and committed.\n\n## Done\n\n- [ ] Every candidate a pick (or, without `AskUserQuestion`, a later reply) named is applied and committed; nothing else was applied.\n",{"name":5,"description":7},"main","e698afd7063631a7738541bcbcc479442ca96d93","skills\u002Fretro","https:\u002F\u002Fgithub.com\u002Fnavaniharsh31\u002Fkeel","https:\u002F\u002Fgithub.com\u002Fnavaniharsh31","https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fharshnavani\u002F","learning and growing...","2026-10-21 13:57:22",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add navaniharsh31\u002Fkeel --skill retro",{"tool":38,"command":39},"bunx","bunx skills add navaniharsh31\u002Fkeel --skill retro",{"tool":41,"command":42},"pnpm","pnpm dlx skills add navaniharsh31\u002Fkeel --skill retro","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnavaniharsh31\u002Fkeel\u002Fblob\u002Fmain\u002Fskills\u002Fretro\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"WRITING.md","REFERENCE","参考文档",2003,"https:\u002F\u002Fgithub.com\u002Fnavaniharsh31\u002Fkeel\u002Fblob\u002Fmain\u002Fskills\u002Fretro\u002FWRITING.md",[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7EAMEAMM8G3V5PB2K6CYER7","tickets","Split an approved spec into tracer-bullet vertical-slice tickets with blocking edges. Use right after a spec is approved, or when the user asks to break work into tickets.","https:\u002F\u002Fgithub.com\u002Fnavaniharsh31\u002Fkeel\u002Fblob\u002Fmain\u002Fskills\u002Ftickets\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7EAMB2SY3QG2K6NQYE089MH","tdd","Test-driven development, one red-green slice at a time at pre-agreed seams. Use when building a feature or fixing a bug test-first, or when writing tests.","https:\u002F\u002Fgithub.com\u002Fnavaniharsh31\u002Fkeel\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7EAM8VKHKC9H5RZT7KHR4VN","spec","Turn the aligned conversation into a spec file under docs\u002Fspecs\u002F. Use after grilling reaches alignment (G1) on a multi-slice feature, or when the user asks for a spec\u002FPRD.","https:\u002F\u002Fgithub.com\u002Fnavaniharsh31\u002Fkeel\u002Fblob\u002Fmain\u002Fskills\u002Fspec\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7EAM678V591FBX97XH6JRZ1","review","Two-axis review (Standards and Spec) of a diff against a fixed point, run as parallel sub-agents. Use after building, or when the user asks to review a branch, PR, or changes since X.","https:\u002F\u002Fgithub.com\u002Fnavaniharsh31\u002Fkeel\u002Fblob\u002Fmain\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7EAM03EGC84KPJ3AHVXP5HD","prototype","Throwaway prototype that answers one design question: does this logic or state model hold up, or what should this UI look like. Use when a grilling question can't be settled on paper.","https:\u002F\u002Fgithub.com\u002Fnavaniharsh31\u002Fkeel\u002Fblob\u002Fmain\u002Fskills\u002Fprototype\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7EAKWNH7A591R5R1D1SS4QV","pr","The shape of a PR body: smallest visual, before\u002Fafter evidence, merge danger. Use whenever writing or editing a pull request description.","https:\u002F\u002Fgithub.com\u002Fnavaniharsh31\u002Fkeel\u002Fblob\u002Fmain\u002Fskills\u002Fpr\u002FSKILL.md",[],[]]