[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6R63YBN7VRDA75PNN11QPF8":3,"skill-same:01M6R63YBN7VRDA75PNN11QPF8":54},{"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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":13,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":39,"install":40,"resources":53},"01M6R63YBN7VRDA75PNN11QPF8","retro",null,"Conduct a retrospective on a coding agent session: propose environment improvements ranked by severity. Invoked by the user after a session or post-merge.","r3dlex\u002Fskills","r3dlex","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F291373160?v=4","01M6PEFNGGBVB7SHAPWXFFX933","01M6R5SDWFHT94734KJFMYE1SX",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Fskills\u002Fblob\u002Fmain\u002F04-validate-handoff\u002Fretro\u002FSKILL.md",[],[5,18,19,20,21,22,23,24,25,26,27,28],"coding agent","merge","retrospective","severity","coding","user","environment","session","post","conduct","agent session","2026-11-10 10:12:30",false,"---\nname: retro\ndescription: 'Conduct a retrospective on a coding agent session: propose environment improvements ranked by severity. Invoked by the user after a session or post-merge.'\n---\n\nThe user has asked for a **retrospective**. You are suggesting improvements to the coding agent's **environment** to improve future runs. This is the post-merge closure step of a shipped goal: once a PR merges, ask whether a retro is wanted before moving on.\n\n## Steps\n\n1. Load the `write-a-skill` skill for the writing style guide, and follow `write-agent-docs` when a finding turns into an edit of an agent-facing document.\n\n2. Read the primary sources for the session, or the merged PR and its review thread. Sources may include session logs on this machine; default to the current session when the user does not specify one.\n\n3. Look for candidates for improvement in these categories.\n\n- **Navigation**: how easy was it for the agent to find the right files? Are there hidden dependencies between files? Would a **navigation pointer** make it easier? _Use when_ the session took a long time to find a piece of information.\n- **Automated checks**: are there automated checks that could catch errors the agent made? Linting, typing, tests, filesystem linters? Read the repo's own check command first (its `package.json`\u002Fbuild-tool `lint`\u002F`check` scripts, its CI workflow), so a check that already exists but sits unwired or silently broken is the finding, not a reinvention. A repo with no **guardrail** (no pre-commit hook and no CI job running its lint\u002Ftypecheck\u002Ftest command) is itself a finding: an un-linted repo is a standing missed opportunity, not a neutral default. _Use when_ the agent made a mistake an automated check could have caught, or the repo has no guardrail at all.\n- **Coding standards**: should the **reviewer agent** be given a new rule to enforce? Should an existing rule be removed or clarified? Classify the violation first: a **mechanical** one (a fixed syntactic pattern, a banned API, an import shape, a file-location rule) gets a deterministic check, full stop: a custom rule in the repo's own linter, a new pre-commit hook, or a new CI job, whichever the repo's language and existing guardrail make cheapest. Default to building the check over writing the rule. Reserve `CODING_STANDARDS.md` for genuine **judgement calls** (cross-file consistency, \"matches the surrounding style,\" anything no guardrail could ever substitute for). _Use when_ the reviewer agent failed to catch a mistake.\n- **Global AGENTS.md**: are there any steering instructions that should be moved to coding standards (or automated checks) instead? _Use when_ the AGENTS.md file is particularly large - in the repo OR the user's global scope.\n- **Tool economy**: did the agent make expensive tool calls that could be streamlined? Is there any custom tooling (CLIs, MCPs) that is particularly token-inefficient? _Use when_ the agent made an expensive tool call.\n- **No-ops**: look for instructions in steering files that don't modify the agent's behavior. _Use when_ the steering files are large and unwieldy.\n- **Information access**: look for opportunities to increase the agent's access to information. Teeing dev server logs, readonly access to third-party services. _Use when_ a crucial piece of information was not available to the agent.\n\n4. Present these candidates to the user, in order of severity, and record accepted ones in the retro summary.\n\n## Reference\n\n### Implementation vs Review\n\nAll work goes through two stages: implementation and review. The implementation agent has the most **context pressure** — it explores, writes code, and debugs failures. The review agent has the least: it receives a diff and usually needs no exploration.\n\nThis means the review agent should be responsible for imposing coding standards, not the implementation agent.\n\n### Files\n\n- `CLAUDE.md`\u002F`AGENTS.md`: pushed into the context window of any agent working in this repo. Use incredibly sparingly — usually only **navigation pointers** to other files.\n- `CODING_STANDARDS.md` (if present): read during review, not implementation. Add **navigation pointers** to docs folders if the standards file grows past ~1,000 lines.\n- Docs: reference files pointed to by other files. Look for existing docs before writing new ones.\n- Skills: the right home for reusable workflows, since the frontmatter description enters the agent's context. Follow `write-a-skill`.\n- Glossary: use the repo's `CONTEXT.md` (or `GLOSSARY.md` when the upstream rename has landed) vocabulary exactly.\n\nEnd by declaring knowledge kind `learning`, then reading\n[ai-catapult-init\u002Fmodules\u002Fknowledge-publish.md](..\u002Fai-catapult-init\u002Fmodules\u002Fknowledge-publish.md) and running its host-neutral producer step — publish when a registry exists, otherwise record `unpublished: \u003Creason>`; never fail the skill because of the registry.\n","The user has asked for a **retrospective**. You are suggesting improvements to the coding agent's **environment** to improve future runs. This is the post-merge closure step of a shipped goal: once a PR merges, ask whether a retro is wanted before moving on.\n\n## Steps\n\n1. Load the `write-a-skill` skill for the writing style guide, and follow `write-agent-docs` when a finding turns into an edit of an agent-facing document.\n\n2. Read the primary sources for the session, or the merged PR and its review thread. Sources may include session logs on this machine; default to the current session when the user does not specify one.\n\n3. Look for candidates for improvement in these categories.\n\n- **Navigation**: how easy was it for the agent to find the right files? Are there hidden dependencies between files? Would a **navigation pointer** make it easier? _Use when_ the session took a long time to find a piece of information.\n- **Automated checks**: are there automated checks that could catch errors the agent made? Linting, typing, tests, filesystem linters? Read the repo's own check command first (its `package.json`\u002Fbuild-tool `lint`\u002F`check` scripts, its CI workflow), so a check that already exists but sits unwired or silently broken is the finding, not a reinvention. A repo with no **guardrail** (no pre-commit hook and no CI job running its lint\u002Ftypecheck\u002Ftest command) is itself a finding: an un-linted repo is a standing missed opportunity, not a neutral default. _Use when_ the agent made a mistake an automated check could have caught, or the repo has no guardrail at all.\n- **Coding standards**: should the **reviewer agent** be given a new rule to enforce? Should an existing rule be removed or clarified? Classify the violation first: a **mechanical** one (a fixed syntactic pattern, a banned API, an import shape, a file-location rule) gets a deterministic check, full stop: a custom rule in the repo's own linter, a new pre-commit hook, or a new CI job, whichever the repo's language and existing guardrail make cheapest. Default to building the check over writing the rule. Reserve `CODING_STANDARDS.md` for genuine **judgement calls** (cross-file consistency, \"matches the surrounding style,\" anything no guardrail could ever substitute for). _Use when_ the reviewer agent failed to catch a mistake.\n- **Global AGENTS.md**: are there any steering instructions that should be moved to coding standards (or automated checks) instead? _Use when_ the AGENTS.md file is particularly large - in the repo OR the user's global scope.\n- **Tool economy**: did the agent make expensive tool calls that could be streamlined? Is there any custom tooling (CLIs, MCPs) that is particularly token-inefficient? _Use when_ the agent made an expensive tool call.\n- **No-ops**: look for instructions in steering files that don't modify the agent's behavior. _Use when_ the steering files are large and unwieldy.\n- **Information access**: look for opportunities to increase the agent's access to information. Teeing dev server logs, readonly access to third-party services. _Use when_ a crucial piece of information was not available to the agent.\n\n4. Present these candidates to the user, in order of severity, and record accepted ones in the retro summary.\n\n## Reference\n\n### Implementation vs Review\n\nAll work goes through two stages: implementation and review. The implementation agent has the most **context pressure** — it explores, writes code, and debugs failures. The review agent has the least: it receives a diff and usually needs no exploration.\n\nThis means the review agent should be responsible for imposing coding standards, not the implementation agent.\n\n### Files\n\n- `CLAUDE.md`\u002F`AGENTS.md`: pushed into the context window of any agent working in this repo. Use incredibly sparingly — usually only **navigation pointers** to other files.\n- `CODING_STANDARDS.md` (if present): read during review, not implementation. Add **navigation pointers** to docs folders if the standards file grows past ~1,000 lines.\n- Docs: reference files pointed to by other files. Look for existing docs before writing new ones.\n- Skills: the right home for reusable workflows, since the frontmatter description enters the agent's context. Follow `write-a-skill`.\n- Glossary: use the repo's `CONTEXT.md` (or `GLOSSARY.md` when the upstream rename has landed) vocabulary exactly.\n\nEnd by declaring knowledge kind `learning`, then reading\n[ai-catapult-init\u002Fmodules\u002Fknowledge-publish.md](..\u002Fai-catapult-init\u002Fmodules\u002Fknowledge-publish.md) and running its host-neutral producer step — publish when a registry exists, otherwise record `unpublished: \u003Creason>`; never fail the skill because of the registry.\n",{"name":5,"description":7},"main","037fe34299eb9c4a30b51f1a6bd101eae1c469b1","04-validate-handoff\u002Fretro","https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Fskills","https:\u002F\u002Fgithub.com\u002Fr3dlex","2026-10-29 16:22:54",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add r3dlex\u002Fskills --skill retro",{"tool":46,"command":47},"bunx","bunx skills add r3dlex\u002Fskills --skill retro",{"tool":49,"command":50},"pnpm","pnpm dlx skills add r3dlex\u002Fskills --skill retro","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Fskills\u002Fblob\u002Fmain\u002F04-validate-handoff\u002Fretro\u002FSKILL.md",true,[],[55,63,76,85,95,119],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":29},"01M6R652E42RZT7M2V3RWW991Z","skill","Fixture.","https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Fskills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcatalog-malformed\u002Fskill\u002FSKILL.md",[],[62],"fixture",{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":74,"publishedAt":29},"01M6R64MTPF0FGWHFS4DWP40GR","stable-skill","Fixture stable-skill.","https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Fskills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcatalog-lifecycle\u002Fstable-skill\u002FSKILL.md",[69],{"categoryNo":70,"categoryName":71,"taxonomyType":72,"taxonomyTypeDesc":73},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[75,62],"stable skill",{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":83,"publishedAt":29},"01M6R64HD4QVAYM2R0JSYNVDJW","experimental-skill","Fixture experimental-skill.","https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Fskills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcatalog-lifecycle\u002Fexperimental-skill\u002FSKILL.md",[82],{"categoryNo":70,"categoryName":71,"taxonomyType":72,"taxonomyTypeDesc":73},[84,62],"experimental skill",{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":92,"publishedAt":29},"01M6R64FZH05TEJQW75QX1E5XD","deprecated-skill","Fixture deprecated-skill.","https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Fskills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcatalog-lifecycle\u002Fdeprecated-skill\u002FSKILL.md",[91],{"categoryNo":70,"categoryName":71,"taxonomyType":72,"taxonomyTypeDesc":73},[93,94,62],"deprecated skill","deprecated",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":29},"01M6R64D13X5DC980GREWFSSFQ","karpathy-guidelines","Apply think-before-coding, simplicity, surgical-change, and goal-driven engineering rules. Use when planning, implementing, or reviewing code.","https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Fskills\u002Fblob\u002Fmain\u002Freference\u002Fgolden-skills\u002F.agents\u002Fskills\u002Fkarpathy-guidelines\u002FSKILL.md",[],[102,103,104,105,106,107,108,109,110,111,112,113,114,22,115,116,117,118],"karpathy guidelines","karpathy","guidelines","Rules","use","simplicity","goal","think","driven","reviewing code","implementing","apply","when","change","code","planning","engineering",{"skillNo":120,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":29},"01M6R640ZS60BRV9P49FT46ZJX","https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Fskills\u002Fblob\u002Fmain\u002Freference\u002Fgolden-root\u002F.agents\u002Fskills\u002Fkarpathy-guidelines\u002FSKILL.md",[],[104,102,103,115,110,116,117,118,22,105,106,107,108,109,111,112,113,114]]