[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79A0ABTVNAFQ92B7PDSAYT0":3,"skill-same:01M79A0ABTVNAFQ92B7PDSAYT0":48},{"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":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M79A0ABTVNAFQ92B7PDSAYT0","arbeitsplan-design",null,"Designs a workflow node by node before anything runs — for each step, what it does, where it runs (primary checkout, agent worktree, scratch directory), when (dependencies, human gates between runs) and how (kind, model, write scope, output schema, and for script nodes the exact command and its toolchain, in any language). Use when the user wants to plan a workflow step by step, a restructuring spans several waves, a deterministic step (a gate, a conformance runner, a state helper) would otherwise be disguised as an agent, or a hand-written workflow keeps making where\u002Fwhen\u002Fhow decisions in prose. Read-only; produces a validated design.json and a handoff, never runs it.","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-design\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: arbeitsplan-design\ndescription: Designs a workflow node by node before anything runs — for each step, what it does, where it runs (primary checkout, agent worktree, scratch directory), when (dependencies, human gates between runs) and how (kind, model, write scope, output schema, and for script nodes the exact command and its toolchain, in any language). Use when the user wants to plan a workflow step by step, a restructuring spans several waves, a deterministic step (a gate, a conformance runner, a state helper) would otherwise be disguised as an agent, or a hand-written workflow keeps making where\u002Fwhen\u002Fhow decisions in prose. Read-only; produces a validated design.json and a handoff, never runs it.\nargument-hint: \"\u003Cthe approved problem statement, or its path>\"\n---\n\n# Design a workflow, node by node\n\n`arbeitsplan-compile` picks a pattern per phase. This skill answers the questions compile\nleaves in prose, **before** anything runs. For every node it asks:\n\n- **what** the node does;\n- **where** it runs;\n- **when** it runs;\n- **how** it runs.\n\nA hand-written multi-wave prototype answered them ad hoc. Three of its bugs came from that: a\nwrong worktree base, state passed as a JSON string, and a gate run where untracked files live.\n\nRun this skill in **plan mode**. It writes nothing but the design under `analysis\u002Farbeitsplan\u002F`,\nand only after the user approves.\n\n## Steps\n\n1. **Read the contract first.** `references\u002Fdesign-table-schema.md` defines every key and\n   every rejection. `references\u002Fpatterns.md` has `script-step` and `gated-disjoint-waves`, and\n   explains why a merge of *unproven* partitions is still rejected.\n\n2. **Take an approved problem statement, not a vague one.** If it is not scoped, stop and scope\n   it (`zirkel:zirkel-clarify-scope` when zirkel is installed; ask directly when it is not, and\n   say so). Record its path as `problemRef`.\n\n3. **Snapshot the agent types that exist now**, before designing anything:\n\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fhandoff.py\" snapshot --root . \\\n     --out analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fagents-before.json\n   ```\n\n   The handoff compares against this snapshot. An agent type added in the middle of a session\n   does not resolve in `agent()`.\n\n4. **Find the repository's own toolchain before writing a single command.** Read its build\n   files: `Makefile`, `go.mod`, `Cargo.toml`, `*.csproj`, `package.json`, `*.cabal`,\n   `pyproject.toml`, `Project.toml`, `build.gradle`, `CMakeLists.txt`, or whatever is there.\n   Write the gates, acceptance and smoke steps in **that** toolchain. Never write `pytest`\n   into a project that does not use it. If a runtime is not among the built-ins, declare it\n   under `toolchains`.\n\n5. **Walk the nodes one at a time.** For each, settle with the user:\n\n   | question | the node's keys |\n   |---|---|\n   | what | `goal`, `output_schema` (strict, no JSON-in-a-string) |\n   | where | `where`: `primary`, `worktree` or `scratch` |\n   | when | `depends_on`; a `human-gate` only *between* runs |\n   | how | `kind`, `model` (recommended per node; omit it to inherit the session's), `agentType`, `writeScope`, `inputs` (ids and paths only), `script` or steps |\n\n   A deterministic step — a gate, a conformance runner, a state helper — is a `script` node.\n   It is **not** an agent told to run a command. When the repository has no such command yet,\n   the node **authors** it: `script.author = {model, purpose, sample}` in a wave design, in\n   bash, pwsh, ruby, node or python, following the repository's own language where it can (see\n   the schema's \"Authored steps\"). The plan writes the script and verifies it before anything\n   runs it.\n\n6. **Prove the write scopes.** Dispatch `arbeitsplan:scope-prover` for the rows that run\n   concurrently. Where two rows need one shared file (a module manifest, a lockfile), give it\n   to one owner: an integrator row that depends on both, or a scaffold row in an earlier wave.\n\n7. **Validate, without writing:**\n\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcompile_spec.py\" --design \\\n     --spec analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fdesign.draft.json\n   ```\n\n   Every `REJECTED` line names its key. Fix the design, never the validator.\n\n8. **Preflight the toolchains.** The compile prints one `TOOLCHAIN \u003Cname> \u003Cprobe>` line per\n   runtime the design names. Invoke `arbeitsplan-preflight`, which runs each probe; exit 0\n   means installed. A missing toolchain makes the design **not ready**, however clean it\n   compiled.\n\n9. **Render the design as a graph** for the user to approve from. Record the probes' results\n   as `{toolchain: true|false}` in `analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fpreflight.json`, then:\n\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fbuild_design_html.py\" \\\n     --design analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fdesign.draft.json \\\n     --preflight analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fpreflight.json \\\n     --out analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fdesign-report.html\n   ```\n\n   It prints the page's verdict. The page shows which rows run side by side, any two that may\n   write the same file, and where a human gate ends a run. Every rejection on it comes from the\n   same validator as step 7.\n\n10. **Present the design table and the preflight results**, in the output format below, and\n   ask for approval. Approval binds to the printed sha256. When an ExitPlanMode hook is\n   available, it can check that hash, but that binding is unprobed, so say so rather than\n   claim it.\n\n11. **On approval**, write the design:\n\n    ```bash\n    python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcompile_spec.py\" --design --write \\\n      --spec analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fdesign.draft.json\n    ```\n\n    Then hand off:\n\n    ```bash\n    python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fhandoff.py\" plan \\\n      --design analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fdesign.json \\\n      --snapshot analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fagents-before.json\n    ```\n\n## Execute, then hand off\n\n- **Execute** in auto mode, from the **primary checkout**:\n  - a design with waves goes to `arbeitsplan-waves`;\n  - a single change goes to `arbeitsplan-compile` and then `arbeitsplan-run`, with each script\n    node becoming a `script` phase.\n\n  The run stops at the first checkpoint or red gate and leaves a state file to resume from.\n- **Same session:** `EnterWorktree` into the branch the run produced. The cwd, settings and\n  CLAUDE.md move with it; agents and hooks are read from the main checkout.\n- **A later turn:** when the design created agent types, `handoff.py` says\n  `LAUNCH IN A LATER TURN`. A type written mid-session is not found in the turn that wrote it,\n  and resolves from the next turn on. A fresh session with the exact start prompt\n  `handoff.py plan` prints also works.\n\nWhat `scripts\u002Fprobe_runtime.py` measured on CLI 2.1.283 (ADR 0004), beyond the docs:\n\n- **Plan mode holds inside a worktree the same way it holds in the primary checkout.** Asked\n  to write a file in plan mode, the model declined in both, 3 of 3 each. That is the model\n  honouring the mode; a headless run never reached the harness's own refusal, so do not treat\n  a worktree as a way around plan mode, nor as a second lock.\n- **Resume returns to the worktree.** A session that ran `EnterWorktree`, resumed from the\n  primary checkout, starts in that worktree and remembers the conversation, 3 of 3.\n- **Agent types: a later turn, not a new session** (above), 3 of 3 for both the Agent tool and\n  a Workflow `agent()`.\n\n## Rules\n\n- **Never infer a gating value.** A wave design without `integration.target` is refused.\n  A model is not a gating value: tiering is a recommendation, so a node that omits `model`\n  inherits the session's by design (#118) and is dispatched without a `model` key. The skill\n  *proposes* a tier (opus for builders and referees, sonnet for merger, smoke, reviewer and\n  fixer, haiku for script runners) and the design states it; a stated model that is not an\n  alias or a `claude-...` id is refused (`AP-NODE-BAD-MODEL`), and `inherit` is not one --\n  omit the key instead.\n- **Commands come from the repository, not from habit.** Every example here is one language\n  among many. Match the project.\n- **A human gate is between runs.** A Workflow run cannot pause for input, and the validator\n  refuses a gate that does not cut the graph in two.\n- **Writes nothing before approval**, and never runs the design.\n\n## Output format\n\n```\ndesign rebuild-cli (run ap-2026-09-27-wv01)  sha256 3f9c1e…  — compiles clean\nproblem: analysis\u002Farbeitsplan\u002Fap-2026-09-27-wv01\u002Fproblem.md\n\n node        kind        where     when (after)        model   writes             command \u002F check\n preflight   script      primary   —                   haiku   —                  python3 …_state.py preflight\n w1-parse    agent       worktree  preflight           opus    internal\u002Fparse\u002F**  go test .\u002Finternal\u002Fparse\u002F...\n w1-render   agent       worktree  preflight           opus    internal\u002Frender\u002F** go test .\u002Finternal\u002Frender\u002F...\n gate-1      merge-gate  primary   w1-parse, w1-render haiku   —                  gates: go vet, go test\n w2-cli      agent       worktree  gate-1              opus    cmd\u002Ftool\u002F**        go test .\u002Fcmd\u002Ftool\u002F...\n gate-2      merge-gate  primary   w2-cli              haiku   —                  gates: go vet, go test\n smoke       agent       scratch   gate-2              sonnet  —                  go build …; go run … --help\n review      agent       primary   smoke               sonnet  —                  —\n fix         agent       worktree  review (if blocking) sonnet internal\u002F**, cmd\u002F** —\n\ntoolchains: go (go version) — installed · python (python3 --version) — installed, helper >= 3.11\nintegration: waves merge into integration\u002Frebuild-cli; main moves only on a green gate\nnew agent types: rebuild-cli-builder, -smoke, -reviewer, -fixer, -runner → LAUNCH IN A LATER TURN than the install\nApprove this design (sha256 3f9c1e…)?  Next: arbeitsplan-waves install, then launch on the next turn.\n```\n\n## Resources\n\n- `references\u002Fdesign-table-schema.md` — every key, every rejection, and the two worked\n  fixtures (Go, and Rust with an integrator row).\n- `references\u002Fpatterns.md` — `script-step`, `gated-disjoint-waves`, and the rejected\n  `partition-then-merge-worktrees` this narrows.\n- `scripts\u002Fhandoff.py` — the snapshot, and the new-session prompt when one is required.\n- `scripts\u002Fbuild_design_html.py` — the design (and later its run) as a graph with a verdict;\n  `assets\u002Fdesign-viewer.html` is its template.\n","# Design a workflow, node by node\n\n`arbeitsplan-compile` picks a pattern per phase. This skill answers the questions compile\nleaves in prose, **before** anything runs. For every node it asks:\n\n- **what** the node does;\n- **where** it runs;\n- **when** it runs;\n- **how** it runs.\n\nA hand-written multi-wave prototype answered them ad hoc. Three of its bugs came from that: a\nwrong worktree base, state passed as a JSON string, and a gate run where untracked files live.\n\nRun this skill in **plan mode**. It writes nothing but the design under `analysis\u002Farbeitsplan\u002F`,\nand only after the user approves.\n\n## Steps\n\n1. **Read the contract first.** `references\u002Fdesign-table-schema.md` defines every key and\n   every rejection. `references\u002Fpatterns.md` has `script-step` and `gated-disjoint-waves`, and\n   explains why a merge of *unproven* partitions is still rejected.\n\n2. **Take an approved problem statement, not a vague one.** If it is not scoped, stop and scope\n   it (`zirkel:zirkel-clarify-scope` when zirkel is installed; ask directly when it is not, and\n   say so). Record its path as `problemRef`.\n\n3. **Snapshot the agent types that exist now**, before designing anything:\n\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fhandoff.py\" snapshot --root . \\\n     --out analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fagents-before.json\n   ```\n\n   The handoff compares against this snapshot. An agent type added in the middle of a session\n   does not resolve in `agent()`.\n\n4. **Find the repository's own toolchain before writing a single command.** Read its build\n   files: `Makefile`, `go.mod`, `Cargo.toml`, `*.csproj`, `package.json`, `*.cabal`,\n   `pyproject.toml`, `Project.toml`, `build.gradle`, `CMakeLists.txt`, or whatever is there.\n   Write the gates, acceptance and smoke steps in **that** toolchain. Never write `pytest`\n   into a project that does not use it. If a runtime is not among the built-ins, declare it\n   under `toolchains`.\n\n5. **Walk the nodes one at a time.** For each, settle with the user:\n\n   | question | the node's keys |\n   |---|---|\n   | what | `goal`, `output_schema` (strict, no JSON-in-a-string) |\n   | where | `where`: `primary`, `worktree` or `scratch` |\n   | when | `depends_on`; a `human-gate` only *between* runs |\n   | how | `kind`, `model` (recommended per node; omit it to inherit the session's), `agentType`, `writeScope`, `inputs` (ids and paths only), `script` or steps |\n\n   A deterministic step — a gate, a conformance runner, a state helper — is a `script` node.\n   It is **not** an agent told to run a command. When the repository has no such command yet,\n   the node **authors** it: `script.author = {model, purpose, sample}` in a wave design, in\n   bash, pwsh, ruby, node or python, following the repository's own language where it can (see\n   the schema's \"Authored steps\"). The plan writes the script and verifies it before anything\n   runs it.\n\n6. **Prove the write scopes.** Dispatch `arbeitsplan:scope-prover` for the rows that run\n   concurrently. Where two rows need one shared file (a module manifest, a lockfile), give it\n   to one owner: an integrator row that depends on both, or a scaffold row in an earlier wave.\n\n7. **Validate, without writing:**\n\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcompile_spec.py\" --design \\\n     --spec analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fdesign.draft.json\n   ```\n\n   Every `REJECTED` line names its key. Fix the design, never the validator.\n\n8. **Preflight the toolchains.** The compile prints one `TOOLCHAIN \u003Cname> \u003Cprobe>` line per\n   runtime the design names. Invoke `arbeitsplan-preflight`, which runs each probe; exit 0\n   means installed. A missing toolchain makes the design **not ready**, however clean it\n   compiled.\n\n9. **Render the design as a graph** for the user to approve from. Record the probes' results\n   as `{toolchain: true|false}` in `analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fpreflight.json`, then:\n\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fbuild_design_html.py\" \\\n     --design analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fdesign.draft.json \\\n     --preflight analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fpreflight.json \\\n     --out analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fdesign-report.html\n   ```\n\n   It prints the page's verdict. The page shows which rows run side by side, any two that may\n   write the same file, and where a human gate ends a run. Every rejection on it comes from the\n   same validator as step 7.\n\n10. **Present the design table and the preflight results**, in the output format below, and\n   ask for approval. Approval binds to the printed sha256. When an ExitPlanMode hook is\n   available, it can check that hash, but that binding is unprobed, so say so rather than\n   claim it.\n\n11. **On approval**, write the design:\n\n    ```bash\n    python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcompile_spec.py\" --design --write \\\n      --spec analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fdesign.draft.json\n    ```\n\n    Then hand off:\n\n    ```bash\n    python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fhandoff.py\" plan \\\n      --design analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fdesign.json \\\n      --snapshot analysis\u002Farbeitsplan\u002F\u003CrunId>\u002Fagents-before.json\n    ```\n\n## Execute, then hand off\n\n- **Execute** in auto mode, from the **primary checkout**:\n  - a design with waves goes to `arbeitsplan-waves`;\n  - a single change goes to `arbeitsplan-compile` and then `arbeitsplan-run`, with each script\n    node becoming a `script` phase.\n\n  The run stops at the first checkpoint or red gate and leaves a state file to resume from.\n- **Same session:** `EnterWorktree` into the branch the run produced. The cwd, settings and\n  CLAUDE.md move with it; agents and hooks are read from the main checkout.\n- **A later turn:** when the design created agent types, `handoff.py` says\n  `LAUNCH IN A LATER TURN`. A type written mid-session is not found in the turn that wrote it,\n  and resolves from the next turn on. A fresh session with the exact start prompt\n  `handoff.py plan` prints also works.\n\nWhat `scripts\u002Fprobe_runtime.py` measured on CLI 2.1.283 (ADR 0004), beyond the docs:\n\n- **Plan mode holds inside a worktree the same way it holds in the primary checkout.** Asked\n  to write a file in plan mode, the model declined in both, 3 of 3 each. That is the model\n  honouring the mode; a headless run never reached the harness's own refusal, so do not treat\n  a worktree as a way around plan mode, nor as a second lock.\n- **Resume returns to the worktree.** A session that ran `EnterWorktree`, resumed from the\n  primary checkout, starts in that worktree and remembers the conversation, 3 of 3.\n- **Agent types: a later turn, not a new session** (above), 3 of 3 for both the Agent tool and\n  a Workflow `agent()`.\n\n## Rules\n\n- **Never infer a gating value.** A wave design without `integration.target` is refused.\n  A model is not a gating value: tiering is a recommendation, so a node that omits `model`\n  inherits the session's by design (#118) and is dispatched without a `model` key. The skill\n  *proposes* a tier (opus for builders and referees, sonnet for merger, smoke, reviewer and\n  fixer, haiku for script runners) and the design states it; a stated model that is not an\n  alias or a `claude-...` id is refused (`AP-NODE-BAD-MODEL`), and `inherit` is not one --\n  omit the key instead.\n- **Commands come from the repository, not from habit.** Every example here is one language\n  among many. Match the project.\n- **A human gate is between runs.** A Workflow run cannot pause for input, and the validator\n  refuses a gate that does not cut the graph in two.\n- **Writes nothing before approval**, and never runs the design.\n\n## Output format\n\n```\ndesign rebuild-cli (run ap-2026-09-27-wv01)  sha256 3f9c1e…  — compiles clean\nproblem: analysis\u002Farbeitsplan\u002Fap-2026-09-27-wv01\u002Fproblem.md\n\n node        kind        where     when (after)        model   writes             command \u002F check\n preflight   script      primary   —                   haiku   —                  python3 …_state.py preflight\n w1-parse    agent       worktree  preflight           opus    internal\u002Fparse\u002F**  go test .\u002Finternal\u002Fparse\u002F...\n w1-render   agent       worktree  preflight           opus    internal\u002Frender\u002F** go test .\u002Finternal\u002Frender\u002F...\n gate-1      merge-gate  primary   w1-parse, w1-render haiku   —                  gates: go vet, go test\n w2-cli      agent       worktree  gate-1              opus    cmd\u002Ftool\u002F**        go test .\u002Fcmd\u002Ftool\u002F...\n gate-2      merge-gate  primary   w2-cli              haiku   —                  gates: go vet, go test\n smoke       agent       scratch   gate-2              sonnet  —                  go build …; go run … --help\n review      agent       primary   smoke               sonnet  —                  —\n fix         agent       worktree  review (if blocking) sonnet internal\u002F**, cmd\u002F** —\n\ntoolchains: go (go version) — installed · python (python3 --version) — installed, helper >= 3.11\nintegration: waves merge into integration\u002Frebuild-cli; main moves only on a green gate\nnew agent types: rebuild-cli-builder, -smoke, -reviewer, -fixer, -runner → LAUNCH IN A LATER TURN than the install\nApprove this design (sha256 3f9c1e…)?  Next: arbeitsplan-waves install, then launch on the next turn.\n```\n\n## Resources\n\n- `references\u002Fdesign-table-schema.md` — every key, every rejection, and the two worked\n  fixtures (Go, and Rust with an integrator row).\n- `references\u002Fpatterns.md` — `script-step`, `gated-disjoint-waves`, and the rejected\n  `partition-then-merge-worktrees` this narrows.\n- `scripts\u002Fhandoff.py` — the snapshot, and the new-session prompt when one is required.\n- `scripts\u002Fbuild_design_html.py` — the design (and later its run) as a graph with a verdict;\n  `assets\u002Fdesign-viewer.html` is its template.\n",{"name":5,"description":7,"argument-hint":24},"\u003Cthe approved problem statement, or its path>","main","6158c1e4e112c06af2c7ac01b13b2ed7214c0fcf","plugins\u002Farbeitsplan\u002Fskills\u002Farbeitsplan-design",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":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Anselmoo\u002Fwerkstoff --skill arbeitsplan-design",{"tool":40,"command":41},"bunx","bunx skills add Anselmoo\u002Fwerkstoff --skill arbeitsplan-design",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Anselmoo\u002Fwerkstoff --skill arbeitsplan-design","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Farbeitsplan\u002Fskills\u002Farbeitsplan-design\u002FSKILL.md",true,[],[49,56,63,68,73,78],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"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":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"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":64,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"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":69,"name":58,"nameZh":6,"description":59,"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},"01M79AJM6Y50WP3G2BR4H0M60Z","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fplugins\u002Ffixtures\u002Fnacharbeit-preflight-mixed\u002Fplugins\u002Fdemo\u002Fskills\u002Fdemo-check\u002FSKILL.md",[],[],{"skillNo":74,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"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},"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",[],[]]