[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79ABCTXFPR7EAMS0Q6KCXTT":3,"skill-same:01M79ABCTXFPR7EAMS0Q6KCXTT":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},"01M79ABCTXFPR7EAMS0Q6KCXTT","matrize-survey",null,"Use to scan the current state of the art in design-system delivery — token formats and tooling, build and bundler conventions per target, component distribution, the accessibility baseline, and how systems are actually documented today — because a design handbook does not go stale on style, it goes stale on the delivery chain. Trigger on 'what's the current state of the art for design tokens', 'is our delivery chain out of date', 'resurvey the tooling', 'matrize survey'. Every named package, tool, spec or API is verified to exist before the file is written; an unverifiable name is removed and logged, never softened into a hedge.","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\u002Fmatrize\u002Fskills\u002Fmatrize-survey\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: matrize-survey\ndescription: \"Use to scan the current state of the art in design-system delivery — token formats and tooling, build and bundler conventions per target, component distribution, the accessibility baseline, and how systems are actually documented today — because a design handbook does not go stale on style, it goes stale on the delivery chain. Trigger on 'what's the current state of the art for design tokens', 'is our delivery chain out of date', 'resurvey the tooling', 'matrize survey'. Every named package, tool, spec or API is verified to exist before the file is written; an unverifiable name is removed and logged, never softened into a hedge.\"\nargument-hint: \"[domain]\"\n---\n\nAnswer the question a reference cannot: not *what should this look like*, but *how are\nsystems actually delivered right now*. Re-runnable, because the answer decays.\n\n## What it covers\n\n- **token format and tooling conventions** — which spec revision is current, which tools\n  claim support, and where that support is uneven rather than absent\n- **build and bundler conventions** per target in play\n- **component distribution** conventions\n- **the current accessibility baseline**, and what changed in it\n- **how systems are documented today** — which is *not* a 13-page landscape PDF, and the\n  survey should say when that still wins anyway: it wins for approval by a\n  non-technical decision-maker, and loses for developer consumption. Both halves are\n  findings; recording only one is advocacy\n\n## The confabulation gate\n\n> Every named package, tool, specification or API is verified to exist **before** the\n> file is written.\n\nVerify by resolving the thing itself — a registry entry, the spec's own URL, the\nrepository. Not by recalling it, and not by finding it mentioned somewhere.\n\nA name that cannot be verified is **removed and logged** in a \"could not verify\" list.\nIt is never softened into a hedge: \"possibly `some-tool`\" reads as a real option to the\nnext reader, and a hedge is how a confabulated dependency survives review. Dispatch\n`fact-checker` for the existence checks — they are mechanical and verifiable by\nconstruction.\n\n## Per-claim volatility, and an expiry derived from it\n\nEach claim carries: **source URL**, **retrieval date**, and a **volatility flag** —\n`stable` (a convention that moves on a multi-year cadence) or `moving` (tooling support,\nversion coverage, anything mid-adoption).\n\nThe file's expiry is the **earliest** of its claims' horizons: roughly 365 days for a\nstable claim, roughly 90 for a moving one. A survey made entirely of stable conventions\nshould not expire on a calendar that assumes churn; one resting on a single fast-moving\ntooling fact should not look fresh for a year.\n\n`matrize-status` names **which claim** forces the expiry, so a re-survey can be targeted\nrather than total.\n\n## The delta section\n\nIf a previous `STATE-OF-THE-ART.md` exists, end with what changed since it: claims that\nheld, claims that moved, and claims that turned out to be wrong. A survey with no delta\nagainst its predecessor has not been compared to it.\n\n## Worked example of why this phase exists\n\nUneven support for a *stable* specification is the characteristic shape of this domain:\na spec can reach a stable revision while the major implementations are still catching up\nto it, so \"tool X supports the spec\" and \"tool X supports the revision you are targeting\"\nare different claims. That distinction was not true a year earlier and will not stay\ntrue — which is the whole argument for re-running this rather than writing it once.\n\nRecord the revision you actually target, per tool, with its retrieval date.\n","Answer the question a reference cannot: not *what should this look like*, but *how are\nsystems actually delivered right now*. Re-runnable, because the answer decays.\n\n## What it covers\n\n- **token format and tooling conventions** — which spec revision is current, which tools\n  claim support, and where that support is uneven rather than absent\n- **build and bundler conventions** per target in play\n- **component distribution** conventions\n- **the current accessibility baseline**, and what changed in it\n- **how systems are documented today** — which is *not* a 13-page landscape PDF, and the\n  survey should say when that still wins anyway: it wins for approval by a\n  non-technical decision-maker, and loses for developer consumption. Both halves are\n  findings; recording only one is advocacy\n\n## The confabulation gate\n\n> Every named package, tool, specification or API is verified to exist **before** the\n> file is written.\n\nVerify by resolving the thing itself — a registry entry, the spec's own URL, the\nrepository. Not by recalling it, and not by finding it mentioned somewhere.\n\nA name that cannot be verified is **removed and logged** in a \"could not verify\" list.\nIt is never softened into a hedge: \"possibly `some-tool`\" reads as a real option to the\nnext reader, and a hedge is how a confabulated dependency survives review. Dispatch\n`fact-checker` for the existence checks — they are mechanical and verifiable by\nconstruction.\n\n## Per-claim volatility, and an expiry derived from it\n\nEach claim carries: **source URL**, **retrieval date**, and a **volatility flag** —\n`stable` (a convention that moves on a multi-year cadence) or `moving` (tooling support,\nversion coverage, anything mid-adoption).\n\nThe file's expiry is the **earliest** of its claims' horizons: roughly 365 days for a\nstable claim, roughly 90 for a moving one. A survey made entirely of stable conventions\nshould not expire on a calendar that assumes churn; one resting on a single fast-moving\ntooling fact should not look fresh for a year.\n\n`matrize-status` names **which claim** forces the expiry, so a re-survey can be targeted\nrather than total.\n\n## The delta section\n\nIf a previous `STATE-OF-THE-ART.md` exists, end with what changed since it: claims that\nheld, claims that moved, and claims that turned out to be wrong. A survey with no delta\nagainst its predecessor has not been compared to it.\n\n## Worked example of why this phase exists\n\nUneven support for a *stable* specification is the characteristic shape of this domain:\na spec can reach a stable revision while the major implementations are still catching up\nto it, so \"tool X supports the spec\" and \"tool X supports the revision you are targeting\"\nare different claims. That distinction was not true a year earlier and will not stay\ntrue — which is the whole argument for re-running this rather than writing it once.\n\nRecord the revision you actually target, per tool, with its retrieval date.\n",{"name":5,"description":7,"argument-hint":24},"[domain]","main","6158c1e4e112c06af2c7ac01b13b2ed7214c0fcf","plugins\u002Fmatrize\u002Fskills\u002Fmatrize-survey",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 matrize-survey",{"tool":40,"command":41},"bunx","bunx skills add Anselmoo\u002Fwerkstoff --skill matrize-survey",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Anselmoo\u002Fwerkstoff --skill matrize-survey","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Fmatrize\u002Fskills\u002Fmatrize-survey\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",[],[]]