[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79AFAFTADDTJCMETHRCDF43":3,"skill-same:01M79AFAFTADDTJCMETHRCDF43":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},"01M79AFAFTADDTJCMETHRCDF43","zeugnis-contract-drift",null,"Use when the user asks to audit type signatures, docstrings, or API\u002FOpenAPI\u002FGraphQL schemas against actual call-site or handler usage, wants to check for contract drift after a refactor, or wants zeugnis's contract-drift audit run. Scope is structural, machine-checkable declarations only. Not for prose documentation drift — claims in CLAUDE.md, README.md, ARCHITECTURE.md, DECISIONS.md or ADR files no longer matching the code: use befund-docs-drift for that. Verification runs by default and only skips if the user explicitly says skip_verification.","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\u002Fzeugnis\u002Fskills\u002Fzeugnis-contract-drift\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: zeugnis-contract-drift\ndescription: \"Use when the user asks to audit type signatures, docstrings, or API\u002FOpenAPI\u002FGraphQL schemas against actual call-site or handler usage, wants to check for contract drift after a refactor, or wants zeugnis's contract-drift audit run. Scope is structural, machine-checkable declarations only. Not for prose documentation drift — claims in CLAUDE.md, README.md, ARCHITECTURE.md, DECISIONS.md or ADR files no longer matching the code: use befund-docs-drift for that. Verification runs by default and only skips if the user explicitly says skip_verification.\"\n---\n\nFind drift between machine-checkable contracts (type hints, function\nsignatures, docstring parameter\u002Freturn descriptions, API\u002FOpenAPI\u002FGraphQL\nschemas) and how code actually uses them. Never extract or verify prose\ndocumentation — only structural, machine-checkable declarations.\n\n## Steps\n\n1. Determine `repo_root`, the contract source files (typed source, schema\n   files) to scan, and any house rules the user mentioned. Determine\n   `skip_verification`: **default `false`**. Only treat it as `true` if\n   the user explicitly said so in this request — silence, \"just run it\n   quickly,\" or similar is NOT an explicit `true`.\n2. Optionally build\u002Freuse a symbol index (see \"Shared symbol index\" in\n   `zeugnis-assertion-audit`'s SKILL.md — the same single-flight rule\n   applies here).\n3. Dispatch the `contract-auditor` agent in **Find mode**: give it the\n   contract source files and symbol index (if built) — if step 2 was\n   skipped, tell the agent no symbol index exists and it should read the\n   contract source files directly instead. Ask for `{\"findings\": [...]}`\n   where each finding includes `declaredLocation` and\n   `actualUsageLocation` (both `file:line`) in addition to the shared\n   schema fields. Write its output to a scratch JSON file.\n4. Unless `skip_verification` is `true`: dispatch the `contract-auditor`\n   agent again in **Verify mode**, independently re-checking each\n   Find-phase finding. Write `{\"findings\": [{\"evidence\": \"...\",\n   \"confirmed\": true|false}, ...]}` to a second scratch file, with a literal\n   boolean for every Find-phase finding: any other answer is kept as\n   `verification: \"unverified\"` and counted in `unverifiedCount`.\n5. Run:\n   ```\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcontract_drift.py\" \u003Crepo_root> \\\n       --find-json \u003Cpath-from-step-3> \\\n       [--verify-json \u003Cpath-from-step-4>] \\\n       [--skip-verification]\n   ```\n   Pass `--skip-verification` ONLY if step 1 determined it should be\n   `true` — in that case, omit `--verify-json` entirely (there is nothing\n   to verify). Otherwise `--verify-json` is required; the script refuses\n   to run without it when `--skip-verification` is absent.\n   The script maps `confidence: \"High\"` findings to `severity: \"High\"`\n   and writes `analysis\u002Fzeugnis\u002Freports\u002FCONTRACT_DRIFT.md` and\n   `analysis\u002Fzeugnis\u002Fcontract_drift_summary.json`.\n6. Report the finding count to the user, and if `skip_verification` was\n   `true`, say so explicitly in your summary — an unverified contract-\n   drift report is weaker evidence and the user should know which one\n   they got.\n\n## What NOT to do\n\n- Do not default to skipping verification for speed — it must be an\n  explicit user request, every time, not an assumption you make on their\n  behalf.\n- Do not report a docstring-only observation as a contract mismatch if it\n  isn't tied to an actual type hint, signature, or schema — that's prose\n  documentation drift, out of this skill's scope.\n","Find drift between machine-checkable contracts (type hints, function\nsignatures, docstring parameter\u002Freturn descriptions, API\u002FOpenAPI\u002FGraphQL\nschemas) and how code actually uses them. Never extract or verify prose\ndocumentation — only structural, machine-checkable declarations.\n\n## Steps\n\n1. Determine `repo_root`, the contract source files (typed source, schema\n   files) to scan, and any house rules the user mentioned. Determine\n   `skip_verification`: **default `false`**. Only treat it as `true` if\n   the user explicitly said so in this request — silence, \"just run it\n   quickly,\" or similar is NOT an explicit `true`.\n2. Optionally build\u002Freuse a symbol index (see \"Shared symbol index\" in\n   `zeugnis-assertion-audit`'s SKILL.md — the same single-flight rule\n   applies here).\n3. Dispatch the `contract-auditor` agent in **Find mode**: give it the\n   contract source files and symbol index (if built) — if step 2 was\n   skipped, tell the agent no symbol index exists and it should read the\n   contract source files directly instead. Ask for `{\"findings\": [...]}`\n   where each finding includes `declaredLocation` and\n   `actualUsageLocation` (both `file:line`) in addition to the shared\n   schema fields. Write its output to a scratch JSON file.\n4. Unless `skip_verification` is `true`: dispatch the `contract-auditor`\n   agent again in **Verify mode**, independently re-checking each\n   Find-phase finding. Write `{\"findings\": [{\"evidence\": \"...\",\n   \"confirmed\": true|false}, ...]}` to a second scratch file, with a literal\n   boolean for every Find-phase finding: any other answer is kept as\n   `verification: \"unverified\"` and counted in `unverifiedCount`.\n5. Run:\n   ```\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcontract_drift.py\" \u003Crepo_root> \\\n       --find-json \u003Cpath-from-step-3> \\\n       [--verify-json \u003Cpath-from-step-4>] \\\n       [--skip-verification]\n   ```\n   Pass `--skip-verification` ONLY if step 1 determined it should be\n   `true` — in that case, omit `--verify-json` entirely (there is nothing\n   to verify). Otherwise `--verify-json` is required; the script refuses\n   to run without it when `--skip-verification` is absent.\n   The script maps `confidence: \"High\"` findings to `severity: \"High\"`\n   and writes `analysis\u002Fzeugnis\u002Freports\u002FCONTRACT_DRIFT.md` and\n   `analysis\u002Fzeugnis\u002Fcontract_drift_summary.json`.\n6. Report the finding count to the user, and if `skip_verification` was\n   `true`, say so explicitly in your summary — an unverified contract-\n   drift report is weaker evidence and the user should know which one\n   they got.\n\n## What NOT to do\n\n- Do not default to skipping verification for speed — it must be an\n  explicit user request, every time, not an assumption you make on their\n  behalf.\n- Do not report a docstring-only observation as a contract mismatch if it\n  isn't tied to an actual type hint, signature, or schema — that's prose\n  documentation drift, out of this skill's scope.\n",{"name":5,"description":7},"main","6158c1e4e112c06af2c7ac01b13b2ed7214c0fcf","plugins\u002Fzeugnis\u002Fskills\u002Fzeugnis-contract-drift",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 zeugnis-contract-drift",{"tool":39,"command":40},"bunx","bunx skills add Anselmoo\u002Fwerkstoff --skill zeugnis-contract-drift",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Anselmoo\u002Fwerkstoff --skill zeugnis-contract-drift","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Fzeugnis\u002Fskills\u002Fzeugnis-contract-drift\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",[],[]]