[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79A8V4KFAJCSHZRC01HF41D":3,"skill-same:01M79A8V4KFAJCSHZRC01HF41D":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},"01M79A8V4KFAJCSHZRC01HF41D","lehre-pin",null,"Use once a unit or phase is validated, to make its rules survive without the plugin: emit a CI check that runs the doctrine with no agent in the loop, and write behaviour tests around the code that was changed to conform. Covers CI pinning of the ruleset, durable enforcement once the plugin is uninstalled, and regression tests for conformance edits. Two phases — the durable rule check, then the regression net.","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\u002Flehre\u002Fskills\u002Flehre-pin\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: lehre-pin\ndescription: \"Use once a unit or phase is validated, to make its rules survive without the plugin: emit a CI check that runs the doctrine with no agent in the loop, and write behaviour tests around the code that was changed to conform. Covers CI pinning of the ruleset, durable enforcement once the plugin is uninstalled, and regression tests for conformance edits. Two phases — the durable rule check, then the regression net.\"\n---\n\nMake the doctrine outlive the session. Every enforcement layer above this one\ndepends on an agent being in the loop; this one does not.\n\nTwo phases, both run:\n\n## Phase 1 — pin the rules\n\n0. **Run the gate before pinning anything.** Name the unit(s) being pinned; if\n   the user named none, gate on every declared unit:\n\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Flehre_cli.py\" status --require-validated --unit \u003Cunit-id>\n   ```\n\n   (repeat `--unit` per unit; omit it to require them all). Act on the **exit\n   code**, not on how the printed rows read — plain `status` exits `0` whatever\n   the states are, so only this flag can stop you:\n\n   - `0` — every required unit holds its done-marker; continue.\n   - `1` — **stop. Nothing is pinned.** Report the units it names and send the\n     user to `lehre-validate`. Emit the `BLOCKED` block below, not a CI check.\n   - `2` — **stop.** The ruleset is unusable or the unit does not exist; fix that\n     first. It does not mean the unit is validated.\n\n   In a brownfield ruleset there are no units, so the gate says it has no\n   done-marker to check and exits `0`. That `0` is not a validation: confirm\n   `lehre-validate` passed from its own report before continuing, and say that\n   the confirmation is yours, not the gate's.\n\n1. **Emit a CI invocation of the real gauge**, not a reimplementation:\n\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Flehre_cli.py\" gauge --severity blocking\n   ```\n\n   Exit `1` fails the job. A hand-written CI script that re-encodes the rules is\n   a second implementation that will drift from the ruleset — the exact defect\n   the shared evaluator exists to prevent.\n\n2. **Prefer the project's own linter where the rule is expressible there.** A\n   rule already covered by ruff\u002Feslint\u002Fclippy belongs in that tool's config,\n   where it runs on every developer's machine with no Python path and no plugin\n   installed. Convert it and change the ruleset rule to `linter` kind pointing\n   at the same tool. Reach for the gauge only for what a linter cannot say —\n   layering, forbidden paths, unit ordering.\n\n3. **Cover the write-time gap explicitly.** The PreToolUse hook does not see\n   files written through `Bash`, and `linter`-kind rules are never write-time\n   denials at all. CI is what closes both. Say so in the emitted config's\n   comment, so the next reader knows why the job exists when a hook already does\n   \"the same thing\".\n\n## Phase 2 — pin the behaviour\n\n4. **Write tests around what conformance changed**, not around the rule. The\n   rule is already pinned by phase 1. What is unpinned is whether the\n   conformance edit preserved behaviour — a layering fix that moved a database\n   call behind a service is exactly the kind of change that compiles, passes\n   every rule, and silently changes semantics.\n\n5. **Target the seams the decomposition declared**, as read from\n   `.lehre\u002Fruleset.json` (the same source `lehre-validate` names). A test at a\n   seam catches a later unit violating the contract long before a rule could; a\n   test buried inside one unit's internals catches only that unit's refactors.\n\n6. **Prove the test can fail.** State, per test, the mutation it would catch.\n   A test written after the fact that passes against both the old and the new\n   behaviour pins nothing, and this repo's `zeugnis-assertion-audit` exists\n   because that failure is common enough to need its own auditor.\n\n## Output format\n\n```\nphase 1 — rules pinned\n\n  .github\u002Fworkflows\u002Flehre.yml     runs lehre_cli.py gauge --severity blocking\n                                  covers: Bash-written files, linter-tier rules,\n                                  and any session with the plugin uninstalled\n  pyproject.toml [tool.ruff]      + \"TRY\", \"BLE\"  \u003C- absorbs no-bare-except and\n                                  prefer-logging; ruleset rules converted to\n                                  linter kind so there is one implementation, not two\n\n  still gauge-only (no linter can express these)\n    no-api-to-db             layering across packages\n    tests-live-in-tests      file location\n    unit build order         .lehre\u002Funits\u002F*.done\n\nphase 2 — behaviour pinned\n\n  tests\u002Fadapters\u002Ftest_vendor_a.py::test_code_map_passed_in_not_looked_up\n      seam: contracts -> adapters\n      would catch: reverting the fix, i.e. re-importing src.db.session to look\n                   up the vendor code. Fails on the pre-conformance code.\n  tests\u002Fcontracts\u002Ftest_schema_stability.py::test_row_schema_field_order\n      seam: contracts -> everything\n      would catch: a field reordered or renamed in RowSchema, which every\n                   adapter and the writer silently depend on.\n\nverified: both tests fail against the pre-conformance revision.\n```\n\nWhen the gate halts, this is the whole output — no phase 1, no phase 2:\n\n```\nBLOCKED — nothing pinned\n\n  gate: FAILED -- not validated: domain, cli. Run lehre-validate first; do not pin.\n\n  Pinning now would make CI defend behaviour nobody has confirmed is right.\n  next: lehre-validate domain, then lehre-validate cli, then re-run lehre-pin.\n```\n\n## Rules\n\n- **Never reimplement a rule in CI.** Call the gauge. Two implementations of one\n  rule is the drift the shared evaluator was built to eliminate.\n- **Never claim a test pins behaviour without naming the mutation it catches.**\n  If no mutation can be named, the test asserts nothing and should not be\n  written.\n- **Never pin an unvalidated unit.** Pinning cements the current behaviour; if\n  `lehre-validate` has not passed, that behaviour is not known to be right.\n  Step 0's gate is the check: write no CI config, linter change or test until it\n  has exited `0`, and never reason around an exit `1` because the unit \"looks done\".\n","Make the doctrine outlive the session. Every enforcement layer above this one\ndepends on an agent being in the loop; this one does not.\n\nTwo phases, both run:\n\n## Phase 1 — pin the rules\n\n0. **Run the gate before pinning anything.** Name the unit(s) being pinned; if\n   the user named none, gate on every declared unit:\n\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Flehre_cli.py\" status --require-validated --unit \u003Cunit-id>\n   ```\n\n   (repeat `--unit` per unit; omit it to require them all). Act on the **exit\n   code**, not on how the printed rows read — plain `status` exits `0` whatever\n   the states are, so only this flag can stop you:\n\n   - `0` — every required unit holds its done-marker; continue.\n   - `1` — **stop. Nothing is pinned.** Report the units it names and send the\n     user to `lehre-validate`. Emit the `BLOCKED` block below, not a CI check.\n   - `2` — **stop.** The ruleset is unusable or the unit does not exist; fix that\n     first. It does not mean the unit is validated.\n\n   In a brownfield ruleset there are no units, so the gate says it has no\n   done-marker to check and exits `0`. That `0` is not a validation: confirm\n   `lehre-validate` passed from its own report before continuing, and say that\n   the confirmation is yours, not the gate's.\n\n1. **Emit a CI invocation of the real gauge**, not a reimplementation:\n\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Flehre_cli.py\" gauge --severity blocking\n   ```\n\n   Exit `1` fails the job. A hand-written CI script that re-encodes the rules is\n   a second implementation that will drift from the ruleset — the exact defect\n   the shared evaluator exists to prevent.\n\n2. **Prefer the project's own linter where the rule is expressible there.** A\n   rule already covered by ruff\u002Feslint\u002Fclippy belongs in that tool's config,\n   where it runs on every developer's machine with no Python path and no plugin\n   installed. Convert it and change the ruleset rule to `linter` kind pointing\n   at the same tool. Reach for the gauge only for what a linter cannot say —\n   layering, forbidden paths, unit ordering.\n\n3. **Cover the write-time gap explicitly.** The PreToolUse hook does not see\n   files written through `Bash`, and `linter`-kind rules are never write-time\n   denials at all. CI is what closes both. Say so in the emitted config's\n   comment, so the next reader knows why the job exists when a hook already does\n   \"the same thing\".\n\n## Phase 2 — pin the behaviour\n\n4. **Write tests around what conformance changed**, not around the rule. The\n   rule is already pinned by phase 1. What is unpinned is whether the\n   conformance edit preserved behaviour — a layering fix that moved a database\n   call behind a service is exactly the kind of change that compiles, passes\n   every rule, and silently changes semantics.\n\n5. **Target the seams the decomposition declared**, as read from\n   `.lehre\u002Fruleset.json` (the same source `lehre-validate` names). A test at a\n   seam catches a later unit violating the contract long before a rule could; a\n   test buried inside one unit's internals catches only that unit's refactors.\n\n6. **Prove the test can fail.** State, per test, the mutation it would catch.\n   A test written after the fact that passes against both the old and the new\n   behaviour pins nothing, and this repo's `zeugnis-assertion-audit` exists\n   because that failure is common enough to need its own auditor.\n\n## Output format\n\n```\nphase 1 — rules pinned\n\n  .github\u002Fworkflows\u002Flehre.yml     runs lehre_cli.py gauge --severity blocking\n                                  covers: Bash-written files, linter-tier rules,\n                                  and any session with the plugin uninstalled\n  pyproject.toml [tool.ruff]      + \"TRY\", \"BLE\"  \u003C- absorbs no-bare-except and\n                                  prefer-logging; ruleset rules converted to\n                                  linter kind so there is one implementation, not two\n\n  still gauge-only (no linter can express these)\n    no-api-to-db             layering across packages\n    tests-live-in-tests      file location\n    unit build order         .lehre\u002Funits\u002F*.done\n\nphase 2 — behaviour pinned\n\n  tests\u002Fadapters\u002Ftest_vendor_a.py::test_code_map_passed_in_not_looked_up\n      seam: contracts -> adapters\n      would catch: reverting the fix, i.e. re-importing src.db.session to look\n                   up the vendor code. Fails on the pre-conformance code.\n  tests\u002Fcontracts\u002Ftest_schema_stability.py::test_row_schema_field_order\n      seam: contracts -> everything\n      would catch: a field reordered or renamed in RowSchema, which every\n                   adapter and the writer silently depend on.\n\nverified: both tests fail against the pre-conformance revision.\n```\n\nWhen the gate halts, this is the whole output — no phase 1, no phase 2:\n\n```\nBLOCKED — nothing pinned\n\n  gate: FAILED -- not validated: domain, cli. Run lehre-validate first; do not pin.\n\n  Pinning now would make CI defend behaviour nobody has confirmed is right.\n  next: lehre-validate domain, then lehre-validate cli, then re-run lehre-pin.\n```\n\n## Rules\n\n- **Never reimplement a rule in CI.** Call the gauge. Two implementations of one\n  rule is the drift the shared evaluator was built to eliminate.\n- **Never claim a test pins behaviour without naming the mutation it catches.**\n  If no mutation can be named, the test asserts nothing and should not be\n  written.\n- **Never pin an unvalidated unit.** Pinning cements the current behaviour; if\n  `lehre-validate` has not passed, that behaviour is not known to be right.\n  Step 0's gate is the check: write no CI config, linter change or test until it\n  has exited `0`, and never reason around an exit `1` because the unit \"looks done\".\n",{"name":5,"description":7},"main","6158c1e4e112c06af2c7ac01b13b2ed7214c0fcf","plugins\u002Flehre\u002Fskills\u002Flehre-pin",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 lehre-pin",{"tool":39,"command":40},"bunx","bunx skills add Anselmoo\u002Fwerkstoff --skill lehre-pin",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Anselmoo\u002Fwerkstoff --skill lehre-pin","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Flehre\u002Fskills\u002Flehre-pin\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",[],[]]