[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EG6H2J4FHDB2749WWH7YFD":3,"skill-same:01M7EG6H2J4FHDB2749WWH7YFD":65},{"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":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":46},"01M7EG6H2J4FHDB2749WWH7YFD","craft-mode",null,"Scope and route an engineering task through explicit behavior, test-first evidence, and verification, then report what was proven. Explicit invocation only. Routes to five bundled stage skills and reports the unshipped specification and final QA stages as blocked instead of improvising them.","giuseppecrj\u002Fpi-herdr-clean-craft","giuseppecrj","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5714678?v=4","01M7E7A7DZHS53J4N29EW0XYZX","Giuseppe Rodriguez","01M7EG6CZ3TEX6A0572FTR7CZ7",1,"MIT","https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-clean-craft\u002Fblob\u002Fmain\u002Fskills\u002Fcraft-mode\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: craft-mode\ndescription: Scope and route an engineering task through explicit behavior, test-first evidence, and verification, then report what was proven. Explicit invocation only. Routes to five bundled stage skills and reports the unshipped specification and final QA stages as blocked instead of improvising them.\ndisable-model-invocation: true\n---\n\n# Craft mode\n\nCoordinate one engineering task so that every claim in the final report rests on evidence you observed: a failing test before a fix, a passing suite after it, a real dependency edge, or a qualified measurement. Pick the smallest workflow that can produce that evidence.\n\nThis is a one-shot load. Reading this skill does not switch on a persistent mode, and it grants no permission beyond what the user has already given. Where the package's optional `\u002Fcraft-mode` command is loaded, only the user switches it on or off. While it is on, Pi repeats these instructions and a short reminder on later requests. That keeps the same instructions in force and grants nothing more.\n\n## What this release contains\n\nThis hub ships with five stage skills in sibling directories:\n\n- [craft-tdd](..\u002Fcraft-tdd\u002FSKILL.md): change behavior test-first, starting from a meaningful failing test.\n- [craft-refactor](..\u002Fcraft-refactor\u002FSKILL.md): improve structure without changing behavior.\n- [craft-architecture](..\u002Fcraft-architecture\u002FSKILL.md): review dependency and policy boundaries. Read-only by default.\n- [craft-quality](..\u002Fcraft-quality\u002FSKILL.md): assess risk from qualified measurements. Report-only by default.\n- [craft-mutation](..\u002Fcraft-mutation\u002FSKILL.md): check whether tests notice seeded changes.\n\nTwo planned stages are not part of this release: craft-spec, for specifying new behavior and acceptance criteria, and craft-qa, for independent verification through the public surface. Any route that needs them is blocked at that stage.\n\nA stage skill counts as available only if you can actually read its `SKILL.md`. A partial install or a package filter can hide a bundled stage, so check before relying on one. When a stage you need is missing:\n\n- Mark that stage **blocked: stage skill not installed** in your checklist.\n- Tell the user which stage is missing and what it would have covered.\n- Offer to continue with the project's own conventions under their direction, or to stop. Do not write a replacement procedure and present it as the craft stage.\n\n## Decide who coordinates\n\nIf another workflow already owns this task, for example a parent session that delegated it to you or a different methodology hub that is running, you are a contributor. Do the bounded part you were given, return its evidence to that owner, and stop. Do not start a competing workflow, re-plan the whole task, or launch children of your own.\n\nOtherwise you coordinate, and children you launch are leaves. Stage skills are procedures for one stage. When you read one, follow it for that stage and keep the route, the checklist, and the final report here.\n\n## Procedure\n\n1. **Classify the request.** Does it change behavior, preserve behavior while changing structure, diagnose quality, or verify an existing artifact? Ask when the request mixes these in a way that changes the route.\n2. **Establish scope.** Record the goal, the files or modules in scope, the starting revision or working-tree state, the project's own test and check commands, the tools that are actually installed, and the limits in [authorization](references\u002Fauthorization.md).\n3. **Take a baseline.** Run or inspect the relevant checks before changing anything. A failing baseline is a finding to report, not something to fix silently.\n4. **Choose a route** from [workflows](references\u002Fworkflows.md). Prefer the lightweight route and say why when a heavier one is warranted.\n5. **Check stage availability** for each stage on the route, as described above.\n6. **Decide whether to delegate** using [delegation](references\u002Fdelegation.md). Working locally is the default.\n7. **Keep a visible checklist.** One line per stage with its state and evidence: pass, fail, blocked\u002Fnot measured, or skipped with a reason.\n8. **Report** using [reporting](references\u002Freporting.md).\n\n## Ground rules\n\n- Follow the project's language, test runner, architecture policy, and verification commands. Do not import preferences from other ecosystems.\n- Treat metrics as signals that need interpretation, never as proof of correctness or as targets to optimize.\n- Detect optional tools before using them. Installing or configuring anything is a separate, authorized action.\n- When code changes after a verification step, that step's verdict no longer covers the new revision.\n","# Craft mode\n\nCoordinate one engineering task so that every claim in the final report rests on evidence you observed: a failing test before a fix, a passing suite after it, a real dependency edge, or a qualified measurement. Pick the smallest workflow that can produce that evidence.\n\nThis is a one-shot load. Reading this skill does not switch on a persistent mode, and it grants no permission beyond what the user has already given. Where the package's optional `\u002Fcraft-mode` command is loaded, only the user switches it on or off. While it is on, Pi repeats these instructions and a short reminder on later requests. That keeps the same instructions in force and grants nothing more.\n\n## What this release contains\n\nThis hub ships with five stage skills in sibling directories:\n\n- [craft-tdd](..\u002Fcraft-tdd\u002FSKILL.md): change behavior test-first, starting from a meaningful failing test.\n- [craft-refactor](..\u002Fcraft-refactor\u002FSKILL.md): improve structure without changing behavior.\n- [craft-architecture](..\u002Fcraft-architecture\u002FSKILL.md): review dependency and policy boundaries. Read-only by default.\n- [craft-quality](..\u002Fcraft-quality\u002FSKILL.md): assess risk from qualified measurements. Report-only by default.\n- [craft-mutation](..\u002Fcraft-mutation\u002FSKILL.md): check whether tests notice seeded changes.\n\nTwo planned stages are not part of this release: craft-spec, for specifying new behavior and acceptance criteria, and craft-qa, for independent verification through the public surface. Any route that needs them is blocked at that stage.\n\nA stage skill counts as available only if you can actually read its `SKILL.md`. A partial install or a package filter can hide a bundled stage, so check before relying on one. When a stage you need is missing:\n\n- Mark that stage **blocked: stage skill not installed** in your checklist.\n- Tell the user which stage is missing and what it would have covered.\n- Offer to continue with the project's own conventions under their direction, or to stop. Do not write a replacement procedure and present it as the craft stage.\n\n## Decide who coordinates\n\nIf another workflow already owns this task, for example a parent session that delegated it to you or a different methodology hub that is running, you are a contributor. Do the bounded part you were given, return its evidence to that owner, and stop. Do not start a competing workflow, re-plan the whole task, or launch children of your own.\n\nOtherwise you coordinate, and children you launch are leaves. Stage skills are procedures for one stage. When you read one, follow it for that stage and keep the route, the checklist, and the final report here.\n\n## Procedure\n\n1. **Classify the request.** Does it change behavior, preserve behavior while changing structure, diagnose quality, or verify an existing artifact? Ask when the request mixes these in a way that changes the route.\n2. **Establish scope.** Record the goal, the files or modules in scope, the starting revision or working-tree state, the project's own test and check commands, the tools that are actually installed, and the limits in [authorization](references\u002Fauthorization.md).\n3. **Take a baseline.** Run or inspect the relevant checks before changing anything. A failing baseline is a finding to report, not something to fix silently.\n4. **Choose a route** from [workflows](references\u002Fworkflows.md). Prefer the lightweight route and say why when a heavier one is warranted.\n5. **Check stage availability** for each stage on the route, as described above.\n6. **Decide whether to delegate** using [delegation](references\u002Fdelegation.md). Working locally is the default.\n7. **Keep a visible checklist.** One line per stage with its state and evidence: pass, fail, blocked\u002Fnot measured, or skipped with a reason.\n8. **Report** using [reporting](references\u002Freporting.md).\n\n## Ground rules\n\n- Follow the project's language, test runner, architecture policy, and verification commands. Do not import preferences from other ecosystems.\n- Treat metrics as signals that need interpretation, never as proof of correctness or as targets to optimize.\n- Detect optional tools before using them. Installing or configuring anything is a separate, authorized action.\n- When code changes after a verification step, that step's verdict no longer covers the new revision.\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","6b397836833902f4cf87dd008d22e067b1fb5e5d","skills\u002Fcraft-mode",0,"https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-clean-craft","https:\u002F\u002Fgithub.com\u002Fgiuseppecrj","giuseppecrj.com","Building agent infrastructure, protocol systems, and real-time product software.","2026-10-22 08:08:25",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":24},[36,39,42],{"tool":37,"command":38},"npx","npx skills add giuseppecrj\u002Fpi-herdr-clean-craft --skill craft-mode",{"tool":40,"command":41},"bunx","bunx skills add giuseppecrj\u002Fpi-herdr-clean-craft --skill craft-mode",{"tool":43,"command":44},"pnpm","pnpm dlx skills add giuseppecrj\u002Fpi-herdr-clean-craft --skill craft-mode","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-clean-craft\u002Fblob\u002Fmain\u002Fskills\u002Fcraft-mode\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fauthorization.md","REFERENCE","参考文档",1352,"https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-clean-craft\u002Fblob\u002Fmain\u002Fskills\u002Fcraft-mode\u002Freferences\u002Fauthorization.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fdelegation.md",3404,"https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-clean-craft\u002Fblob\u002Fmain\u002Fskills\u002Fcraft-mode\u002Freferences\u002Fdelegation.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Freporting.md",1689,"https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-clean-craft\u002Fblob\u002Fmain\u002Fskills\u002Fcraft-mode\u002Freferences\u002Freporting.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fworkflows.md",5322,"https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-clean-craft\u002Fblob\u002Fmain\u002Fskills\u002Fcraft-mode\u002Freferences\u002Fworkflows.md",[66,73,79,85,92,99],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7EG78GE5QAW7DS3RZ090NHJ","missing-reference","Fixture whose instructions link a bundled file that does not exist.","https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-clean-craft\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fmissing-reference\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7EG77BNMJ2DWZ3RZKPVNPE4","mismatched-name","https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-clean-craft\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fmismatched-name\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7EG74NFKN3NEZHDE2HTH89J","malformed-frontmatter","https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-clean-craft\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fmalformed-frontmatter\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7EG70MFPZ297S2A3F5P2ANG","craft-tdd","Change behavior test-first. Write one focused test, confirm it fails for the predicted reason, make the smallest passing change, then tidy under green. Explicit invocation only. Says so plainly when a meaningful failing test could not be shown.","https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-clean-craft\u002Fblob\u002Fmain\u002Fskills\u002Fcraft-tdd\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7EG6WRENPRZAVZT6HQV07MW","craft-refactor","Improve the structure of existing code without changing its behavior, in small verified steps from a green baseline, adding characterization tests where protection is thin. Explicit invocation only.","https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-clean-craft\u002Fblob\u002Fmain\u002Fskills\u002Fcraft-refactor\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M7EG6RH49ER1RK9P1QS572R0","craft-quality","Assess code risk from qualified measurements such as complexity, coverage, and duplication, and disclose missing or stale data instead of filling gaps. Report-only by default. Explicit invocation only. No upstream analyzer is supported in this release.","https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-clean-craft\u002Fblob\u002Fmain\u002Fskills\u002Fcraft-quality\u002FSKILL.md",[],[]]