[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79AF6QV5XPSG22T8H7352PD":3,"skill-same:01M79AF6QV5XPSG22T8H7352PD":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},"01M79AF6QV5XPSG22T8H7352PD","zeugnis-code-change",null,"Use when the user asks for a pre-commit quality check on staged or uncommitted changes, wants a quick zeugnis pass over 'what I just changed' before committing, or asks 'is this diff okay to commit'. Only runs the domains whose file patterns match the changed files, and always produces an advisory verdict that never blocks the commit.","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-code-change\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: zeugnis-code-change\ndescription: \"Use when the user asks for a pre-commit quality check on staged or uncommitted changes, wants a quick zeugnis pass over 'what I just changed' before committing, or asks 'is this diff okay to commit'. Only runs the domains whose file patterns match the changed files, and always produces an advisory verdict that never blocks the commit.\"\n---\n\nRun a fast, changed-files-scoped zeugnis pass across whichever domains are\nactually relevant to what changed. This is a lighter-weight sibling of the\nfour full domain-audit skills — each Find-phase pass here is a single,\nun-verified check (the code-change verdict is advisory by construction,\nso it does not carry the same mandatory-verification guarantees the full\naudits do). If the user wants a fully verified audit, tell them to run\nthe specific `zeugnis-*-audit` skill instead.\n\n## Steps\n\n1. Determine `repo_root`. Get the changed-file list:\n   ```\n   git -C \u003Crepo_root> diff --staged --name-only\n   ```\n   (or `git diff HEAD --name-only` if the user means uncommitted rather\n   than staged changes — ask if ambiguous). Write the list to a scratch\n   JSON file as a plain array of repo-relative paths.\n2. Run:\n   ```\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcode_change_review.py\" \u003Crepo_root> \\\n       --changed-files-json \u003Cpath-from-step-1>\n   ```\n   with NO `--domain-findings` yet, just to see which domains matched. If\n   it exits 1, it printed \"zero domains matched\" to stderr — relay that\n   to the user verbatim and stop; there is nothing to review.\n3. For each matched domain printed in step 2's `matchedDomains`, produce a\n   lightweight findings JSON scoped to only the matched files:\n   - `dependency_audit`: only if a manifest file changed. Run\n     `scripts\u002Fdependency_audit.py \u003Crepo_root> --skip-verification` — it\n     performs the real bounded-timeout registry lookup and typosquat\n     heuristic without the mandatory independent re-check, matching this\n     pass's single-check, advisory rigor. Optionally supplement it with the\n     `dependency-auditor` agent in Find mode for ambiguous names — a\n     supplement to the script's findings, never a replacement for it.\n   - `assertion_audit`: dispatch `assertion-auditor` in Find mode only,\n     scoped to the changed source\u002Ftest files.\n   - `contract_drift`: dispatch `contract-auditor` in Find mode only,\n     scoped to the changed files.\n   - `agentic_reliability`: dispatch `agentic-reliability-auditor` in Find\n     mode only, scoped to the changed skill\u002Fagent\u002Fworkflow files.\n   Write each domain's findings to its own scratch JSON file.\n4. Re-run the script, now passing every matched domain's findings:\n   ```\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcode_change_review.py\" \u003Crepo_root> \\\n       --changed-files-json \u003Cpath-from-step-1> \\\n       --domain-findings dependency_audit=\u003Cpath> \\\n       --domain-findings assertion_audit=\u003Cpath> \\\n       ...\n   ```\n   (only pass `--domain-findings` for domains that actually matched).\n   This writes `analysis\u002Fzeugnis\u002Freports\u002FCODE_CHANGE_REVIEW.md` with one section\n   per matched domain (unmatched domains are omitted entirely — never\n   zero-filled) and a verdict line that always reads `ADVISORY: ...` and\n   never suggests blocking anything.\n5. Report the verdict line and per-domain finding counts to the user.\n   Always phrase the summary as advisory — e.g. \"N findings worth a look\n   before you commit, but nothing here blocks you.\"\n\n## What NOT to do\n\n- Do not tell the user their commit is \"blocked\" or \"failing\" — this\n  skill has no gate, only advice. If the user wants a hard gate, that's a\n  git hook they'd configure themselves, not something this skill does.\n- Do not run a domain that didn't match — e.g. don't dispatch\n  `assertion-auditor` if no source or test file changed.\n- Do not invent a zero-finding section for a domain that didn't match,\n  either in the report or in your summary to the user.\n","Run a fast, changed-files-scoped zeugnis pass across whichever domains are\nactually relevant to what changed. This is a lighter-weight sibling of the\nfour full domain-audit skills — each Find-phase pass here is a single,\nun-verified check (the code-change verdict is advisory by construction,\nso it does not carry the same mandatory-verification guarantees the full\naudits do). If the user wants a fully verified audit, tell them to run\nthe specific `zeugnis-*-audit` skill instead.\n\n## Steps\n\n1. Determine `repo_root`. Get the changed-file list:\n   ```\n   git -C \u003Crepo_root> diff --staged --name-only\n   ```\n   (or `git diff HEAD --name-only` if the user means uncommitted rather\n   than staged changes — ask if ambiguous). Write the list to a scratch\n   JSON file as a plain array of repo-relative paths.\n2. Run:\n   ```\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcode_change_review.py\" \u003Crepo_root> \\\n       --changed-files-json \u003Cpath-from-step-1>\n   ```\n   with NO `--domain-findings` yet, just to see which domains matched. If\n   it exits 1, it printed \"zero domains matched\" to stderr — relay that\n   to the user verbatim and stop; there is nothing to review.\n3. For each matched domain printed in step 2's `matchedDomains`, produce a\n   lightweight findings JSON scoped to only the matched files:\n   - `dependency_audit`: only if a manifest file changed. Run\n     `scripts\u002Fdependency_audit.py \u003Crepo_root> --skip-verification` — it\n     performs the real bounded-timeout registry lookup and typosquat\n     heuristic without the mandatory independent re-check, matching this\n     pass's single-check, advisory rigor. Optionally supplement it with the\n     `dependency-auditor` agent in Find mode for ambiguous names — a\n     supplement to the script's findings, never a replacement for it.\n   - `assertion_audit`: dispatch `assertion-auditor` in Find mode only,\n     scoped to the changed source\u002Ftest files.\n   - `contract_drift`: dispatch `contract-auditor` in Find mode only,\n     scoped to the changed files.\n   - `agentic_reliability`: dispatch `agentic-reliability-auditor` in Find\n     mode only, scoped to the changed skill\u002Fagent\u002Fworkflow files.\n   Write each domain's findings to its own scratch JSON file.\n4. Re-run the script, now passing every matched domain's findings:\n   ```\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcode_change_review.py\" \u003Crepo_root> \\\n       --changed-files-json \u003Cpath-from-step-1> \\\n       --domain-findings dependency_audit=\u003Cpath> \\\n       --domain-findings assertion_audit=\u003Cpath> \\\n       ...\n   ```\n   (only pass `--domain-findings` for domains that actually matched).\n   This writes `analysis\u002Fzeugnis\u002Freports\u002FCODE_CHANGE_REVIEW.md` with one section\n   per matched domain (unmatched domains are omitted entirely — never\n   zero-filled) and a verdict line that always reads `ADVISORY: ...` and\n   never suggests blocking anything.\n5. Report the verdict line and per-domain finding counts to the user.\n   Always phrase the summary as advisory — e.g. \"N findings worth a look\n   before you commit, but nothing here blocks you.\"\n\n## What NOT to do\n\n- Do not tell the user their commit is \"blocked\" or \"failing\" — this\n  skill has no gate, only advice. If the user wants a hard gate, that's a\n  git hook they'd configure themselves, not something this skill does.\n- Do not run a domain that didn't match — e.g. don't dispatch\n  `assertion-auditor` if no source or test file changed.\n- Do not invent a zero-finding section for a domain that didn't match,\n  either in the report or in your summary to the user.\n",{"name":5,"description":7},"main","6158c1e4e112c06af2c7ac01b13b2ed7214c0fcf","plugins\u002Fzeugnis\u002Fskills\u002Fzeugnis-code-change",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-code-change",{"tool":39,"command":40},"bunx","bunx skills add Anselmoo\u002Fwerkstoff --skill zeugnis-code-change",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Anselmoo\u002Fwerkstoff --skill zeugnis-code-change","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Fzeugnis\u002Fskills\u002Fzeugnis-code-change\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",[],[]]