[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79A0VQKM54R2XY6RT6M4VM5":3,"skill-same:01M79A0VQKM54R2XY6RT6M4VM5":47},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M79A0VQKM54R2XY6RT6M4VM5","arbeitsplan-preflight",null,"Read-only inventory of what a swarm run can and cannot do in this repository before any tokens are spent. Use before arbeitsplan-compile or arbeitsplan-run, when the user asks whether this repo is ready for a swarm, or when a run failed and the cause might be the environment rather than the work. Reports git\u002Fworktree support, test commands, other plugins' live guards, and any open run lock. Writes nothing.","Anselmoo\u002Fwerkstoff","Anselmoo","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F13209783?v=4","01M799YTB3D7RZ4P3B8CSR2X85","Anselm Hahn","01M799YTBRAM6719D9V0NRGB4R",1,"MIT","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Farbeitsplan\u002Fskills\u002Farbeitsplan-preflight\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: arbeitsplan-preflight\ndescription: Read-only inventory of what a swarm run can and cannot do in this repository before any tokens are spent. Use before arbeitsplan-compile or arbeitsplan-run, when the user asks whether this repo is ready for a swarm, or when a run failed and the cause might be the environment rather than the work. Reports git\u002Fworktree support, test commands, other plugins' live guards, and any open run lock. Writes nothing.\n---\n\n# Preflight\n\nKnow what is on the bench before measuring it. A run that discovers mid-swarm that the repo\ncannot make a worktree has already spent N dispatches on a result it cannot use.\n\n## Steps\n\n1. **Git and worktrees.** Is this a git repository? Can it create a worktree here — is the\n   candidate directory ignored? A repo that cannot make worktrees can still use the matrix\n   backend, so report the alternative rather than just failing.\n\n2. **Acceptance checks.** What test command does this repo actually use? A run whose criteria\n   carry no runnable check cannot be refereed, and that is better known now.\n\n3. **Other plugins' live guards.** Report every guard that would see this run's edits — takt,\n   cupertino, lehre, andon, zeugnis, befund, nacharbeit — and its marker. A fix pass runs\n   under them, and a denial from one is that plugin doing its job.\n\n   **Never suggest another plugin's escape hatch.** Naming it as an inventory fact is\n   reporting; recommending it is helping the user disable someone else's guard.\n\n4. **Existing state.** Is `analysis\u002Farbeitsplan\u002Frun_scope.json` open, and how old? Is\n   `.claude\u002Ftakt.local.md` present, and does it carry this plugin's provenance key?\n\n5. **The matrix backend.** Is `claude` on PATH? Is `timeout` or `gtimeout` available (cells\n   run untimed without one)? Is this session nested — because if so, the matrix runner will\n   refuse, correctly, and the user must run it from a terminal.\n\n6. **Toolchains (#107).** When a design exists, `compile_spec.py --design --spec \u003Cdesign>`\n   prints one `TOOLCHAIN \u003Cname> \u003Cprobe>` line per runtime its commands name — script nodes,\n   acceptance, setup, gates, smoke. Run each probe; **exit 0 means installed**, whatever it\n   prints (`go version` and `java -version` share no output convention). A missing toolchain\n   makes the design not ready. For a wave design, also report the helper runtime: a Python\n   >= 3.11 (`python3`, `python` or `py -3`) that `install_waves.py` will resolve, and whether\n   this checkout is the **primary** one (`git rev-parse --git-dir` equals `--git-common-dir`) —\n   a wave run launched from a linked worktree halts at its first node.\n\n7. **Say what the run can and cannot measure.** A missing checker means the phases that need\n   it are listed as skipped, never silently passed. Name them.\n\n## Rules\n\n- **Writes nothing.** Not even a state directory.\n- **Never infers a missing checker as present.** If there is no test command, say the\n  acceptance criteria will have to be structural, and say what that costs.\n- **Refuse to go further on an open lock.** Hand the user the release command. A stale lock\n  denies every edit, which is the safe direction, and only a person decides to release it.\n\n## Output format\n\n```\narbeitsplan preflight — \u002FUsers\u002Fx\u002Fproj\n  git                 yes (worktrees supported, .arbeitsplan\u002F is gitignored)\n  test command        go test .\u002F...        (from the Makefile's `test` target)\n  claude on PATH      yes\n  timeout             gtimeout (coreutils)\n  nested session      YES — the matrix runner will refuse; run it from a terminal\n  toolchains          go (go version) ok · shell (sh -c true) ok · julia (julia --version) MISSING\n  helper runtime      python3 3.12.3 (>= 3.11) · primary checkout: yes\n\nother guards live in this repository (a run executes under them; a denial from one is\nreported, never bypassed):\n  cupertino    marker .cupertino\n  takt         marker .claude\u002Ftakt.local.md  (no arbeitsplan provenance key — hand-written)\n\nrun lock: none open\nstate: workflow.json=absent, run_scope.json=absent, matrix results=absent\n\nCan measure: every phase. Cannot measure: nothing skipped.\nDesign not ready: julia is named by node conform-jl and is not installed here.\nCaution: takt.local.md is hand-written. arbeitsplan-compile will REFUSE to overwrite it.\nNext: arbeitsplan-compile to turn a problem into a spec.\n```\n\n## Resources\n\n- `references\u002Fmatrix-schema.md` — why a nested session cannot run the matrix.\n- `references\u002Fworkflow-spec-schema.md` — what compile will need from this repository.\n- `references\u002Fdesign-table-schema.md` — the toolchains a design names, and how each is probed.\n","# Preflight\n\nKnow what is on the bench before measuring it. A run that discovers mid-swarm that the repo\ncannot make a worktree has already spent N dispatches on a result it cannot use.\n\n## Steps\n\n1. **Git and worktrees.** Is this a git repository? Can it create a worktree here — is the\n   candidate directory ignored? A repo that cannot make worktrees can still use the matrix\n   backend, so report the alternative rather than just failing.\n\n2. **Acceptance checks.** What test command does this repo actually use? A run whose criteria\n   carry no runnable check cannot be refereed, and that is better known now.\n\n3. **Other plugins' live guards.** Report every guard that would see this run's edits — takt,\n   cupertino, lehre, andon, zeugnis, befund, nacharbeit — and its marker. A fix pass runs\n   under them, and a denial from one is that plugin doing its job.\n\n   **Never suggest another plugin's escape hatch.** Naming it as an inventory fact is\n   reporting; recommending it is helping the user disable someone else's guard.\n\n4. **Existing state.** Is `analysis\u002Farbeitsplan\u002Frun_scope.json` open, and how old? Is\n   `.claude\u002Ftakt.local.md` present, and does it carry this plugin's provenance key?\n\n5. **The matrix backend.** Is `claude` on PATH? Is `timeout` or `gtimeout` available (cells\n   run untimed without one)? Is this session nested — because if so, the matrix runner will\n   refuse, correctly, and the user must run it from a terminal.\n\n6. **Toolchains (#107).** When a design exists, `compile_spec.py --design --spec \u003Cdesign>`\n   prints one `TOOLCHAIN \u003Cname> \u003Cprobe>` line per runtime its commands name — script nodes,\n   acceptance, setup, gates, smoke. Run each probe; **exit 0 means installed**, whatever it\n   prints (`go version` and `java -version` share no output convention). A missing toolchain\n   makes the design not ready. For a wave design, also report the helper runtime: a Python\n   >= 3.11 (`python3`, `python` or `py -3`) that `install_waves.py` will resolve, and whether\n   this checkout is the **primary** one (`git rev-parse --git-dir` equals `--git-common-dir`) —\n   a wave run launched from a linked worktree halts at its first node.\n\n7. **Say what the run can and cannot measure.** A missing checker means the phases that need\n   it are listed as skipped, never silently passed. Name them.\n\n## Rules\n\n- **Writes nothing.** Not even a state directory.\n- **Never infers a missing checker as present.** If there is no test command, say the\n  acceptance criteria will have to be structural, and say what that costs.\n- **Refuse to go further on an open lock.** Hand the user the release command. A stale lock\n  denies every edit, which is the safe direction, and only a person decides to release it.\n\n## Output format\n\n```\narbeitsplan preflight — \u002FUsers\u002Fx\u002Fproj\n  git                 yes (worktrees supported, .arbeitsplan\u002F is gitignored)\n  test command        go test .\u002F...        (from the Makefile's `test` target)\n  claude on PATH      yes\n  timeout             gtimeout (coreutils)\n  nested session      YES — the matrix runner will refuse; run it from a terminal\n  toolchains          go (go version) ok · shell (sh -c true) ok · julia (julia --version) MISSING\n  helper runtime      python3 3.12.3 (>= 3.11) · primary checkout: yes\n\nother guards live in this repository (a run executes under them; a denial from one is\nreported, never bypassed):\n  cupertino    marker .cupertino\n  takt         marker .claude\u002Ftakt.local.md  (no arbeitsplan provenance key — hand-written)\n\nrun lock: none open\nstate: workflow.json=absent, run_scope.json=absent, matrix results=absent\n\nCan measure: every phase. Cannot measure: nothing skipped.\nDesign not ready: julia is named by node conform-jl and is not installed here.\nCaution: takt.local.md is hand-written. arbeitsplan-compile will REFUSE to overwrite it.\nNext: arbeitsplan-compile to turn a problem into a spec.\n```\n\n## Resources\n\n- `references\u002Fmatrix-schema.md` — why a nested session cannot run the matrix.\n- `references\u002Fworkflow-spec-schema.md` — what compile will need from this repository.\n- `references\u002Fdesign-table-schema.md` — the toolchains a design names, and how each is probed.\n",{"name":5,"description":7},"main","6158c1e4e112c06af2c7ac01b13b2ed7214c0fcf","plugins\u002Farbeitsplan\u002Fskills\u002Farbeitsplan-preflight",0,"https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff","https:\u002F\u002Fanselmoo.github.io\u002Fwerkstoff\u002F","https:\u002F\u002Fgithub.com\u002FAnselmoo","Likes to Develop","2026-11-02 04:20:59",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Anselmoo\u002Fwerkstoff --skill arbeitsplan-preflight",{"tool":39,"command":40},"bunx","bunx skills add Anselmoo\u002Fwerkstoff --skill arbeitsplan-preflight",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Anselmoo\u002Fwerkstoff --skill arbeitsplan-preflight","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Farbeitsplan\u002Fskills\u002Farbeitsplan-preflight\u002FSKILL.md",true,[],[48,55,62,67,72,77],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M79AJTRBNBX03WWKYJ8ENM45","toy-check","A skill that checks things in the repository and reports what it finds.","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fworkflows\u002Ffixtures\u002Ftoy-plugin\u002Fskills\u002Ftoy-check\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M79AJS292F3HTDRXWZVRSN5B","demo-check","Reports which generated files changed since the last generation run. Use when the user asks what drifted. Read-only; never edits a file.","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fplugins\u002Ffixtures\u002Fnacharbeit-uncompleted-run\u002Fplugins\u002Fdemo\u002Fskills\u002Fdemo-check\u002FSKILL.md",[],[],{"skillNo":63,"name":57,"nameZh":6,"description":58,"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},"01M79AJP4TFQXKT1AAK1WC1JYK","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fplugins\u002Ffixtures\u002Fnacharbeit-stale-lock\u002Fplugins\u002Fdemo\u002Fskills\u002Fdemo-check\u002FSKILL.md",[],[],{"skillNo":68,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M79AJM6Y50WP3G2BR4H0M60Z","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fplugins\u002Ffixtures\u002Fnacharbeit-preflight-mixed\u002Fplugins\u002Fdemo\u002Fskills\u002Fdemo-check\u002FSKILL.md",[],[],{"skillNo":73,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M79AJGR6DMT8KCCK071V78XM","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fplugins\u002Ffixtures\u002Fnacharbeit-hooks-shape\u002Fplugins\u002Fdemo\u002Fskills\u002Fdemo-check\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M79AJBJ4CHC4PZVWKERWF3HF","zirkel-verify-assumptions","Checks exactly ONE named assumption against real evidence in at most 3 steps and reports one outcome: confidence raised (>=90), reading changed, or still unresolved. Use to resolve a single load-bearing uncertainty — typically a blocking entry surfaced by zirkel-clarify-scope: \"verify this one assumption\", \"is it actually true that X\", \"check this before we rely on it\". For multiple uncertainties, invoke once per uncertainty — the step budget is never shared.","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Fzirkel\u002Fskills\u002Fzirkel-verify-assumptions\u002FSKILL.md",[],[]]