[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M756YGQCCHYVVCKQ12ED7BBC":3,"skill-same:01M756YGQCCHYVVCKQ12ED7BBC":46},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M756YGQCCHYVVCKQ12ED7BBC","docs-audit",null,"Audit the LaNorme docs for accuracy, currency, no-archeology, clarity, and coverage, then fix what it finds. Use before a release or after changing the CLI, the rules, or any Markdown doc, or when asked whether the docs are solid, current, or up to date. It runs the docs-audit workflow, which checks every documented flag, rule code, config key, and output example against the real tool, flags changelog-style narration outside CHANGELOG and any bluff, and lists undocumented surface.","lanorme\u002Flanorme","lanorme","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F289880483?v=4","01M756YE5P1Y6R0SE0SHBC7ZPF","01M756YE6QHCA3SRDKNSHVPSYF",3,"MIT","https:\u002F\u002Fgithub.com\u002Flanorme\u002Flanorme\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdocs-audit\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: docs-audit\ndescription: Audit the LaNorme docs for accuracy, currency, no-archeology, clarity, and coverage, then fix what it finds. Use before a release or after changing the CLI, the rules, or any Markdown doc, or when asked whether the docs are solid, current, or up to date. It runs the docs-audit workflow, which checks every documented flag, rule code, config key, and output example against the real tool, flags changelog-style narration outside CHANGELOG and any bluff, and lists undocumented surface.\nlicense: MIT\nmetadata:\n  project: lanorme\n---\n\n# Audit the docs\n\nLaNorme's own `prose` check (PROSE-001\u002F002\u002F003) already gates em-dashes, British\nspelling, and emoji on Markdown. It cannot tell whether a documented flag still\nexists or an example still reproduces. This skill fills that gap: it verifies the\ndocs against the real tool and flags prose that is stale, narrated as history, or\npuffed up.\n\n## Run the audit\n\nRun the `docs-audit` workflow from the repo root. Pass the absolute repo path so\nthe agents work in the right tree:\n\n```\nWorkflow({ name: \"docs-audit\", args: { repo: \"\u003Cabsolute path to the lanorme repo>\" } })\n```\n\nIf the name does not resolve (for example when the working directory is a\ndifferent repository), invoke it by path instead:\n\n```\nWorkflow({ scriptPath: \"\u003Crepo>\u002F.claude\u002Fworkflows\u002Fdocs-audit.js\", args: { repo: \"\u003Crepo>\" } })\n```\n\nOptional `args`:\n\n- `docs`: an explicit list of Markdown files to audit, instead of letting the\n  workflow discover them.\n- `cli`: how to invoke the tool if not the dev default (`PYTHONPATH=src python3 -m lanorme.cli`).\n\nThe workflow runs three phases: discover the user-facing docs and snapshot the\nreal CLI surface, audit each doc on two lenses (accuracy and prose) then\nadversarially verify each finding, and report any user-facing surface that is\nundocumented. It returns confirmed findings per doc plus a list of coverage gaps.\n\n## Act on the result\n\n1. Read the returned `audited` findings and `coverage_gaps`.\n2. Fix accuracy issues first: a documented flag, rule code, config key, default,\n   or output example that no longer matches the tool. These are the ones that\n   mislead a reader.\n3. Remove any changelog-style narration (\"previously\", \"now\", \"renamed\") from\n   docs other than CHANGELOG. State the current behaviour directly. The\n   CHANGELOG is the one place history belongs.\n4. Cut bluff and redundancy. Keep the prose direct and grounded.\n5. Close real coverage gaps by documenting the missing flag, format, or key in\n   the doc the workflow suggests.\n\n## Verify\n\nAfter applying fixes, confirm the docs still pass LaNorme's own style gate and\nthat the changes hold up:\n\n```\nlanorme check README.md CONTRIBUTING.md CLAUDE.md docs\u002FRULES.md\n```\n\nRe-run the workflow if you made large changes, and confirm every doc comes back\nwith verdict `solid` and no confirmed blocker or major remains.\n","# Audit the docs\n\nLaNorme's own `prose` check (PROSE-001\u002F002\u002F003) already gates em-dashes, British\nspelling, and emoji on Markdown. It cannot tell whether a documented flag still\nexists or an example still reproduces. This skill fills that gap: it verifies the\ndocs against the real tool and flags prose that is stale, narrated as history, or\npuffed up.\n\n## Run the audit\n\nRun the `docs-audit` workflow from the repo root. Pass the absolute repo path so\nthe agents work in the right tree:\n\n```\nWorkflow({ name: \"docs-audit\", args: { repo: \"\u003Cabsolute path to the lanorme repo>\" } })\n```\n\nIf the name does not resolve (for example when the working directory is a\ndifferent repository), invoke it by path instead:\n\n```\nWorkflow({ scriptPath: \"\u003Crepo>\u002F.claude\u002Fworkflows\u002Fdocs-audit.js\", args: { repo: \"\u003Crepo>\" } })\n```\n\nOptional `args`:\n\n- `docs`: an explicit list of Markdown files to audit, instead of letting the\n  workflow discover them.\n- `cli`: how to invoke the tool if not the dev default (`PYTHONPATH=src python3 -m lanorme.cli`).\n\nThe workflow runs three phases: discover the user-facing docs and snapshot the\nreal CLI surface, audit each doc on two lenses (accuracy and prose) then\nadversarially verify each finding, and report any user-facing surface that is\nundocumented. It returns confirmed findings per doc plus a list of coverage gaps.\n\n## Act on the result\n\n1. Read the returned `audited` findings and `coverage_gaps`.\n2. Fix accuracy issues first: a documented flag, rule code, config key, default,\n   or output example that no longer matches the tool. These are the ones that\n   mislead a reader.\n3. Remove any changelog-style narration (\"previously\", \"now\", \"renamed\") from\n   docs other than CHANGELOG. State the current behaviour directly. The\n   CHANGELOG is the one place history belongs.\n4. Cut bluff and redundancy. Keep the prose direct and grounded.\n5. Close real coverage gaps by documenting the missing flag, format, or key in\n   the doc the workflow suggests.\n\n## Verify\n\nAfter applying fixes, confirm the docs still pass LaNorme's own style gate and\nthat the changes hold up:\n\n```\nlanorme check README.md CONTRIBUTING.md CLAUDE.md docs\u002FRULES.md\n```\n\nRe-run the workflow if you made large changes, and confirm every doc comes back\nwith verdict `solid` and no confirmed blocker or major remains.\n",{"name":5,"license":14,"metadata":23,"description":7},{"project":9},"main","49cf2b150731b9b2f20c63a00f55911ec76efd07",".claude\u002Fskills\u002Fdocs-audit",6,"https:\u002F\u002Fgithub.com\u002Flanorme\u002Flanorme","https:\u002F\u002Flanorme.github.io\u002Flanorme\u002F","https:\u002F\u002Fgithub.com\u002Flanorme","2026-11-14 08:19:23",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lanorme\u002Flanorme --skill docs-audit",{"tool":38,"command":39},"bunx","bunx skills add lanorme\u002Flanorme --skill docs-audit",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lanorme\u002Flanorme --skill docs-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flanorme\u002Flanorme\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdocs-audit\u002FSKILL.md",true,[],[47,54,61,68,74,80],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":18},"01M756ZM21V76B0ZBFZAY82KF1","valid-minimal","A minimal valid skill used as a parser fixture.","https:\u002F\u002Fgithub.com\u002Flanorme\u002Flanorme\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fvalid-minimal\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":18},"01M756ZHMJ94FRJ1JG09KY46DN","valid-links","A valid skill that links to a bundled reference file.","https:\u002F\u002Fgithub.com\u002Flanorme\u002Flanorme\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fvalid-links\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M756ZE4AK413FAJFMNGFA9CZ","valid-folded","A valid skill whose description is a folded block scalar spanning multiple lines, to make sure the parser does not call it empty.","https:\u002F\u002Fgithub.com\u002Flanorme\u002Flanorme\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fvalid-folded\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M756ZCXB36P5G924X31E7Y0T","unterminated","https:\u002F\u002Fgithub.com\u002Flanorme\u002Flanorme\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Funterminated\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M756ZBMET5CDBKZB1XQRNA0J","missing-desc","https:\u002F\u002Fgithub.com\u002Flanorme\u002Flanorme\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fmissing-desc\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M756ZA64EC9QA4KCY33GQB7E","invalid-no-frontmatter","https:\u002F\u002Fgithub.com\u002Flanorme\u002Flanorme\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Finvalid-no-frontmatter\u002FSKILL.md",[],[]]