[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75VJDHHPGB09FKS7HY8THVB":3,"skill-same:01M75VJDHHPGB09FKS7HY8THVB":59},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":44},"01M75VJDHHPGB09FKS7HY8THVB","setup-skills",null,"Configure this repo for the engineering skills — set up its durable document layout, temp-artifact policy, and domain doc layout. Run once before first use of the other engineering skills.","clementcaron\u002Fskills","clementcaron","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F95753473?v=4","01M75VHS1G94CEC0ZH5K9Y1JR5","Clément Caron","01M75VHS26PD49PX3ZX2XASXCK",0,"MIT","https:\u002F\u002Fgithub.com\u002Fclementcaron\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Feng\u002Fplanning\u002Fsetup-skills\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: setup-skills\ndescription: Configure this repo for the engineering skills — set up its durable document layout, temp-artifact policy, and domain doc layout. Run once before first use of the other engineering skills.\ndisable-model-invocation: true\n---\n\n# Setup Skills\n\nScaffold the per-repo configuration that the engineering skills assume:\n\n- **Durable docs** — which artifacts are allowed to persist in the repo\n- **Temp artifacts** — which artifacts should live in the OS temp directory by default\n- **Domain docs** — where `CONTEXT.md` and ADRs live, and the consumer rules for reading them\n\nThis is a prompt-driven skill, not a deterministic script. Explore, present what you found, confirm with the user, then write.\n\n## Process\n\n### 1. Explore\n\nLook at the current repo to understand its starting state. Read whatever exists; don't assume:\n\n- `AGENTS.md` and `CLAUDE.md` at the repo root — does either exist? Is there already an `## Agent skills` section in either?\n- `CONTEXT.md` and `CONTEXT-MAP.md` at the repo root\n- `docs\u002Fadr\u002F` and any `src\u002F*\u002Fdocs\u002Fadr\u002F` directories\n- `docs\u002Fslices\u002F` — sign that durable slice documents are already in use\n- `docs\u002Fagents\u002F` — does this skill's prior output already exist?\n\n### 2. Present findings and ask\n\nSummarise what's present and what's missing. Then walk the user through the three decisions **one at a time** — present a section, get the user's answer, then move to the next. Don't dump all three at once.\n\nAssume the user does not know what these terms mean. Each section starts with a short explainer (what it is, why these skills need it, what changes if they pick differently). Then show the choices and the default.\n\n**Section A — Durable docs.**\n\n> Explainer: Durable docs are the few markdown artifacts that are worth keeping in the repo because they remain useful after the current session is over. These skills work best when the durable set stays small and intentional.\n\nDefault posture:\n\n- `CONTEXT.md`\n- `docs\u002Fadr\u002F`\n- `docs\u002Fslices\u002F` only when the user explicitly wants slice docs kept or needs a persistent multi-session handoff\n\n**Section B — Temp artifacts.**\n\n> Explainer: Temporary artifacts are planning and coordination outputs that help during the current session but would create clutter if they stayed in the repo. These should live in the OS temp directory by default.\n\nDefault posture:\n\n- PRDs\n- draft slice breakdowns\n- handoff documents\n- triage notes\n- prototype verdict notes\n\nIf the user wants one of these to persist, ask for the exact path before writing it.\n\n**Section C — Domain docs.**\n\n> Explainer: Some skills (`improve-codebase-architecture`, `diagnosing-bugs`, `tdd`) read a `CONTEXT.md` file to learn the project's domain language, and `docs\u002Fadr\u002F` for past architectural decisions. They need to know whether the repo has one global context or multiple (e.g. a monorepo with separate frontend\u002Fbackend contexts) so they look in the right place.\n\nConfirm the layout:\n\n- **Single-context** — one `CONTEXT.md` + `docs\u002Fadr\u002F` at the repo root. Most repos are this.\n- **Multi-context** — `CONTEXT-MAP.md` at the root pointing to per-context `CONTEXT.md` files (typically a monorepo).\n\n### 3. Confirm and edit\n\nShow the user a draft of:\n\n- The `## Agent skills` block to add to whichever of `CLAUDE.md` \u002F `AGENTS.md` is being edited (see step 4 for selection rules)\n- The contents of `docs\u002Fagents\u002Fartifact-policy.md` and `docs\u002Fagents\u002Fdomain.md`\n\nLet them edit before writing.\n\n### 4. Write\n\n**Pick the file to edit:**\n\n- If `CLAUDE.md` exists, edit it.\n- Else if `AGENTS.md` exists, edit it.\n- If neither exists, ask the user which one to create — don't pick for them.\n\nNever create `AGENTS.md` when `CLAUDE.md` already exists (or vice versa) — always edit the one that's already there.\n\nIf an `## Agent skills` block already exists in the chosen file, update its contents in-place rather than appending a duplicate. Don't overwrite user edits to the surrounding sections.\n\nThe block:\n\n```markdown\n## Agent skills\n\n### Durable docs\n\nDurable artifacts for this repo live in `CONTEXT.md`, `docs\u002Fadr\u002F`, and optionally `docs\u002Fslices\u002F`. See `docs\u002Fagents\u002Fartifact-policy.md`.\n\n### Temp artifacts\n\nTransient artifacts live in the OS temp directory unless the user explicitly asks to keep them. See `docs\u002Fagents\u002Fartifact-policy.md`.\n\n### Domain docs\n\n[one-line summary of layout — \"single-context\" or \"multi-context\"]. See `docs\u002Fagents\u002Fdomain.md`.\n```\n\nThen write the two docs files using the seed templates in this skill folder as a starting point:\n\n- [artifact-policy.md](.\u002Fartifact-policy.md) — durable-docs and temp-artifacts policy\n- [domain.md](.\u002Fdomain.md) — domain doc consumer rules + layout\n\n### 5. Done\n\nTell the user the setup is complete and which engineering skills will now read from these files. Mention they can edit `docs\u002Fagents\u002F*.md` directly later — re-running this skill is only necessary if they want to change the policy or restart from scratch.\n","# Setup Skills\n\nScaffold the per-repo configuration that the engineering skills assume:\n\n- **Durable docs** — which artifacts are allowed to persist in the repo\n- **Temp artifacts** — which artifacts should live in the OS temp directory by default\n- **Domain docs** — where `CONTEXT.md` and ADRs live, and the consumer rules for reading them\n\nThis is a prompt-driven skill, not a deterministic script. Explore, present what you found, confirm with the user, then write.\n\n## Process\n\n### 1. Explore\n\nLook at the current repo to understand its starting state. Read whatever exists; don't assume:\n\n- `AGENTS.md` and `CLAUDE.md` at the repo root — does either exist? Is there already an `## Agent skills` section in either?\n- `CONTEXT.md` and `CONTEXT-MAP.md` at the repo root\n- `docs\u002Fadr\u002F` and any `src\u002F*\u002Fdocs\u002Fadr\u002F` directories\n- `docs\u002Fslices\u002F` — sign that durable slice documents are already in use\n- `docs\u002Fagents\u002F` — does this skill's prior output already exist?\n\n### 2. Present findings and ask\n\nSummarise what's present and what's missing. Then walk the user through the three decisions **one at a time** — present a section, get the user's answer, then move to the next. Don't dump all three at once.\n\nAssume the user does not know what these terms mean. Each section starts with a short explainer (what it is, why these skills need it, what changes if they pick differently). Then show the choices and the default.\n\n**Section A — Durable docs.**\n\n> Explainer: Durable docs are the few markdown artifacts that are worth keeping in the repo because they remain useful after the current session is over. These skills work best when the durable set stays small and intentional.\n\nDefault posture:\n\n- `CONTEXT.md`\n- `docs\u002Fadr\u002F`\n- `docs\u002Fslices\u002F` only when the user explicitly wants slice docs kept or needs a persistent multi-session handoff\n\n**Section B — Temp artifacts.**\n\n> Explainer: Temporary artifacts are planning and coordination outputs that help during the current session but would create clutter if they stayed in the repo. These should live in the OS temp directory by default.\n\nDefault posture:\n\n- PRDs\n- draft slice breakdowns\n- handoff documents\n- triage notes\n- prototype verdict notes\n\nIf the user wants one of these to persist, ask for the exact path before writing it.\n\n**Section C — Domain docs.**\n\n> Explainer: Some skills (`improve-codebase-architecture`, `diagnosing-bugs`, `tdd`) read a `CONTEXT.md` file to learn the project's domain language, and `docs\u002Fadr\u002F` for past architectural decisions. They need to know whether the repo has one global context or multiple (e.g. a monorepo with separate frontend\u002Fbackend contexts) so they look in the right place.\n\nConfirm the layout:\n\n- **Single-context** — one `CONTEXT.md` + `docs\u002Fadr\u002F` at the repo root. Most repos are this.\n- **Multi-context** — `CONTEXT-MAP.md` at the root pointing to per-context `CONTEXT.md` files (typically a monorepo).\n\n### 3. Confirm and edit\n\nShow the user a draft of:\n\n- The `## Agent skills` block to add to whichever of `CLAUDE.md` \u002F `AGENTS.md` is being edited (see step 4 for selection rules)\n- The contents of `docs\u002Fagents\u002Fartifact-policy.md` and `docs\u002Fagents\u002Fdomain.md`\n\nLet them edit before writing.\n\n### 4. Write\n\n**Pick the file to edit:**\n\n- If `CLAUDE.md` exists, edit it.\n- Else if `AGENTS.md` exists, edit it.\n- If neither exists, ask the user which one to create — don't pick for them.\n\nNever create `AGENTS.md` when `CLAUDE.md` already exists (or vice versa) — always edit the one that's already there.\n\nIf an `## Agent skills` block already exists in the chosen file, update its contents in-place rather than appending a duplicate. Don't overwrite user edits to the surrounding sections.\n\nThe block:\n\n```markdown\n## Agent skills\n\n### Durable docs\n\nDurable artifacts for this repo live in `CONTEXT.md`, `docs\u002Fadr\u002F`, and optionally `docs\u002Fslices\u002F`. See `docs\u002Fagents\u002Fartifact-policy.md`.\n\n### Temp artifacts\n\nTransient artifacts live in the OS temp directory unless the user explicitly asks to keep them. See `docs\u002Fagents\u002Fartifact-policy.md`.\n\n### Domain docs\n\n[one-line summary of layout — \"single-context\" or \"multi-context\"]. See `docs\u002Fagents\u002Fdomain.md`.\n```\n\nThen write the two docs files using the seed templates in this skill folder as a starting point:\n\n- [artifact-policy.md](.\u002Fartifact-policy.md) — durable-docs and temp-artifacts policy\n- [domain.md](.\u002Fdomain.md) — domain doc consumer rules + layout\n\n### 5. Done\n\nTell the user the setup is complete and which engineering skills will now read from these files. Mention they can edit `docs\u002Fagents\u002F*.md` directly later — re-running this skill is only necessary if they want to change the policy or restart from scratch.\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","e64768ea15f6494579e2224e79ae364c8f2c5810","skills\u002Feng\u002Fplanning\u002Fsetup-skills","https:\u002F\u002Fgithub.com\u002Fclementcaron\u002Fskills","https:\u002F\u002Fgithub.com\u002Fclementcaron","L'IA sans la data c'est comme un burger sans frites","2026-06-23 02:39:04",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":24},[34,37,40],{"tool":35,"command":36},"npx","npx skills add clementcaron\u002Fskills --skill setup-skills",{"tool":38,"command":39},"bunx","bunx skills add clementcaron\u002Fskills --skill setup-skills",{"tool":41,"command":42},"pnpm","pnpm dlx skills add clementcaron\u002Fskills --skill setup-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fclementcaron\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Feng\u002Fplanning\u002Fsetup-skills\u002FSKILL.md",[45,51,55],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"artifact-policy.md","REFERENCE","参考文档",566,"https:\u002F\u002Fgithub.com\u002Fclementcaron\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Feng\u002Fplanning\u002Fsetup-skills\u002Fartifact-policy.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"domain.md",2047,"https:\u002F\u002Fgithub.com\u002Fclementcaron\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Feng\u002Fplanning\u002Fsetup-skills\u002Fdomain.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"SKILLS.md",4985,"https:\u002F\u002Fgithub.com\u002Fclementcaron\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Feng\u002Fplanning\u002Fsetup-skills\u002FSKILLS.md",[60,67,74,81,88,95],{"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},"01M75VJVKJ9M93Z3GEEGG5643R","to-prd","Turn the current conversation into a PRD — no interview, just synthesis of what you've already discussed.","https:\u002F\u002Fgithub.com\u002Fclementcaron\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Feng\u002Ftasks\u002Fto-prd\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},"01M75VJSA8S1QB54F1KK9EMV12","to-issues","Break a plan, spec, or PRD into independently-grabbable vertical slices using tracer-bullet slices.","https:\u002F\u002Fgithub.com\u002Fclementcaron\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Feng\u002Ftasks\u002Fto-issues\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},"01M75VJPY5FAP7HEDNEKH2RTJK","tdd","Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions \"red-green-refactor\", or wants integration tests.","https:\u002F\u002Fgithub.com\u002Fclementcaron\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Feng\u002Ftasks\u002Ftdd\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},"01M75VJN4MT9F6Y9FARWYADBA3","implement","Implement a piece of work based on a PRD, a slice document, or a single approved slice.","https:\u002F\u002Fgithub.com\u002Fclementcaron\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Feng\u002Ftasks\u002Fimplement\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},"01M75VJJTQDMB4HYND8N43Z9PY","handoff","Compact the current conversation into a handoff document for another agent to pick up.","https:\u002F\u002Fgithub.com\u002Fclementcaron\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Feng\u002Ftasks\u002Fhandoff\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M75VJGAS8X647TNARF914K1H","diagnosing-bugs","Diagnosis loop for hard bugs and performance regressions. Use when the user says \"diagnose\"\u002F\"debug this\", or reports something broken\u002Fthrowing\u002Ffailing\u002Fslow.","https:\u002F\u002Fgithub.com\u002Fclementcaron\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Feng\u002Ftasks\u002Fdiagnosing-bugs\u002FSKILL.md",[],[]]