[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79AAACKS4DBFHC37NNE03V6":3,"skill-same:01M79AAACKS4DBFHC37NNE03V6":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},"01M79AAACKS4DBFHC37NNE03V6","matrize-emit",null,"Use to render a derived design system to a concrete target by running the plugin's committed formatter scripts against its DTCG token file — html and pdf produce the landscape sketchbook that carries the approval block, css and vitepress produce platform output, and provenance produces the graph viewer. Trigger on 'emit the design system as CSS', 'produce the sketchbook PDF', 'regenerate the docs theme from tokens', 'matrize emit'. One neutral source, N formatters: nothing here is authored per run, so the same tokens regenerate byte-stable, and prose from an R2 or R3 reference is refused rather than reproduced.","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-emit\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: matrize-emit\ndescription: \"Use to render a derived design system to a concrete target by running the plugin's committed formatter scripts against its DTCG token file — html and pdf produce the landscape sketchbook that carries the approval block, css and vitepress produce platform output, and provenance produces the graph viewer. Trigger on 'emit the design system as CSS', 'produce the sketchbook PDF', 'regenerate the docs theme from tokens', 'matrize emit'. One neutral source, N formatters: nothing here is authored per run, so the same tokens regenerate byte-stable, and prose from an R2 or R3 reference is refused rather than reproduced.\"\nargument-hint: \"--target \u003Chtml|pdf|css|vitepress|provenance>\"\n---\n\nRun a formatter. Do not author one at run time.\n\n`emit` is a tool-wrapper: the formatters are committed scripts under\n`${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002F`, so emitting is deterministic and free. Authoring a new\nformatter is a change to this plugin, reviewed like any other — not something that\nhappens invisibly inside a run and produces slightly different output each time.\n\nThat determinism is what makes `matrize-retrofit`'s zero-visual-diff proof possible at\nall. A formatter that re-decides its output per run cannot prove equivalence with\nanything.\n\n## Input gate\n\nRequires `\u003Croot>\u002Fsystem\u002Ftokens.json`. If it is absent, say which phase produces it\n(`decode` + `name`, or `retrofit`) and stop.\n\nIf a `spread` choice record exists and is unanswered, the `PreToolUse` guard denies the\nwrite — so record the choice first. That is a refusal, not a warning, and reaching for\n`MATRIZE_DISABLE_GUARD=1` to get past it defeats the phase.\n\n## The rights refusal\n\n> Reference prose from an R2 or R3 source is never written into an emitted artefact.\n\nValues, measured facts, and rules restated in this system's own words are fine. The\nsource's sentences, illustrations and assets are not. When a formatter would need to\nreproduce reference text to be useful, the design is wrong — cite and link instead.\n\n## Targets\n\n**`html`** is the reference formatter and simultaneously the portfolio: the landscape\nsketchbook, one building block per page, marginal callouts carrying purpose, rule and\nanti-rule, and the approval block naming the decision-maker and the gate criteria.\n\n**`pdf`** renders that HTML through headless Chrome `--print-to-pdf`, honouring\n`@page { size: … landscape }`.\n\nNever wkhtmltopdf. Its Qt WebKit engine renders `@font-face` spans **blank** — text\ndisappears entirely while spaces are preserved — does not interleave multi-page CSS Grid\ncolumns, silently ignores header\u002Ffooter flags on unpatched builds, and has no useful\n`--zoom` when the CSS uses physical units. Those are documented failures, not\nspeculation, and re-acquiring them would be a choice.\n\n**Verify the render, do not trust it.** After producing a PDF: extract its text\n(`pdftotext -layout`) and grep for strings that must be present. A silently blanked span\nlooks fine in a page count and is invisible in a thumbnail. Also confirm the page count\nand reading order.\n\n## The targets that exist, and the ones that do not\n\nA target is real when a committed script emits it. Anything else is a plan, and naming it\nhere as though it worked would be the same defect as a rule with no card behind it.\n\n| target | script | status |\n|---|---|---|\n| `css` | `scripts\u002Femit_css.py` | ships |\n| `vitepress` | `scripts\u002Femit_vitepress.py` | ships |\n| `html` | `scripts\u002Fbuild_sketchbook_html.py` | ships |\n| `pdf` | the `html` output through headless Chromium | ships |\n| `provenance` | `scripts\u002Fbuild_provenance_html.py` | ships |\n| `tailwind`, `scss`, `json`, `toml` | — | **not built.** Do not offer them |\n\nIf a user asks for one of the last row, say it is not implemented and name what is. A\nformatter is a small, well-specified piece of work; pretending one exists is not.\n\n**`css` and `vitepress`** are platform output. Neither is ever an input: if a change needs\nmaking, it is made in `tokens.json` and re-emitted. A hand edit to emitted output is lost\non the next run, and worse, it makes the source untrue.\n\n## Report\n\nName the target, the formatter script that ran, the output path, and — for `pdf` — the\nverification that actually executed, with its result. If a verification step did not\nrun, say so rather than implying it passed.\n","Run a formatter. Do not author one at run time.\n\n`emit` is a tool-wrapper: the formatters are committed scripts under\n`${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002F`, so emitting is deterministic and free. Authoring a new\nformatter is a change to this plugin, reviewed like any other — not something that\nhappens invisibly inside a run and produces slightly different output each time.\n\nThat determinism is what makes `matrize-retrofit`'s zero-visual-diff proof possible at\nall. A formatter that re-decides its output per run cannot prove equivalence with\nanything.\n\n## Input gate\n\nRequires `\u003Croot>\u002Fsystem\u002Ftokens.json`. If it is absent, say which phase produces it\n(`decode` + `name`, or `retrofit`) and stop.\n\nIf a `spread` choice record exists and is unanswered, the `PreToolUse` guard denies the\nwrite — so record the choice first. That is a refusal, not a warning, and reaching for\n`MATRIZE_DISABLE_GUARD=1` to get past it defeats the phase.\n\n## The rights refusal\n\n> Reference prose from an R2 or R3 source is never written into an emitted artefact.\n\nValues, measured facts, and rules restated in this system's own words are fine. The\nsource's sentences, illustrations and assets are not. When a formatter would need to\nreproduce reference text to be useful, the design is wrong — cite and link instead.\n\n## Targets\n\n**`html`** is the reference formatter and simultaneously the portfolio: the landscape\nsketchbook, one building block per page, marginal callouts carrying purpose, rule and\nanti-rule, and the approval block naming the decision-maker and the gate criteria.\n\n**`pdf`** renders that HTML through headless Chrome `--print-to-pdf`, honouring\n`@page { size: … landscape }`.\n\nNever wkhtmltopdf. Its Qt WebKit engine renders `@font-face` spans **blank** — text\ndisappears entirely while spaces are preserved — does not interleave multi-page CSS Grid\ncolumns, silently ignores header\u002Ffooter flags on unpatched builds, and has no useful\n`--zoom` when the CSS uses physical units. Those are documented failures, not\nspeculation, and re-acquiring them would be a choice.\n\n**Verify the render, do not trust it.** After producing a PDF: extract its text\n(`pdftotext -layout`) and grep for strings that must be present. A silently blanked span\nlooks fine in a page count and is invisible in a thumbnail. Also confirm the page count\nand reading order.\n\n## The targets that exist, and the ones that do not\n\nA target is real when a committed script emits it. Anything else is a plan, and naming it\nhere as though it worked would be the same defect as a rule with no card behind it.\n\n| target | script | status |\n|---|---|---|\n| `css` | `scripts\u002Femit_css.py` | ships |\n| `vitepress` | `scripts\u002Femit_vitepress.py` | ships |\n| `html` | `scripts\u002Fbuild_sketchbook_html.py` | ships |\n| `pdf` | the `html` output through headless Chromium | ships |\n| `provenance` | `scripts\u002Fbuild_provenance_html.py` | ships |\n| `tailwind`, `scss`, `json`, `toml` | — | **not built.** Do not offer them |\n\nIf a user asks for one of the last row, say it is not implemented and name what is. A\nformatter is a small, well-specified piece of work; pretending one exists is not.\n\n**`css` and `vitepress`** are platform output. Neither is ever an input: if a change needs\nmaking, it is made in `tokens.json` and re-emitted. A hand edit to emitted output is lost\non the next run, and worse, it makes the source untrue.\n\n## Report\n\nName the target, the formatter script that ran, the output path, and — for `pdf` — the\nverification that actually executed, with its result. If a verification step did not\nrun, say so rather than implying it passed.\n",{"name":5,"description":7,"argument-hint":24},"--target \u003Chtml|pdf|css|vitepress|provenance>","main","6158c1e4e112c06af2c7ac01b13b2ed7214c0fcf","plugins\u002Fmatrize\u002Fskills\u002Fmatrize-emit",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-emit",{"tool":40,"command":41},"bunx","bunx skills add Anselmoo\u002Fwerkstoff --skill matrize-emit",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Anselmoo\u002Fwerkstoff --skill matrize-emit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Fmatrize\u002Fskills\u002Fmatrize-emit\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",[],[]]