[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DBAB9KG3YMWVXWA41TWQ79":3,"skill-same:01M6DBAB9KG3YMWVXWA41TWQ79":118},{"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":31,"publishedAt":50,"linkOnly":51,"markdownContent":52,"markdownBody":53,"frontMatter":54,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":14,"repositoryHtmlUrl":59,"repositoryHomepageUrl":6,"ownerHtmlUrl":60,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":61,"install":62,"resources":75},"01M6DBAB9KG3YMWVXWA41TWQ79","design-system",null,"Use this skill to generate or audit design systems, check visual consistency, and review PRs that touch styling. Emits\u002Fconsumes the single `.design\u002F` artifact contract and scores on the canonical DESIGN-EVAL v1 rubric (9 dims, 0-4) — the legacy 10-dim 0-10 visual-audit scale is RETIRED.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdesign-system\u002FSKILL.md",[18,23,28],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",{"categoryNo":29,"categoryName":30,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000037","律师与法务",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"design system","system","design","rubric","dim","systems","contract","visual","artifact","Legacy","styling","use","check","eval","audit","design systems","generate","review","2026-11-10 10:12:30",false,"---\nname: design-system\ndescription: Use this skill to generate or audit design systems, check visual consistency, and review PRs that touch styling. Emits\u002Fconsumes the single `.design\u002F` artifact contract and scores on the canonical DESIGN-EVAL v1 rubric (9 dims, 0-4) — the legacy 10-dim 0-10 visual-audit scale is RETIRED.\norigin: ECC\n---\n\n# Design System — Generate & Audit Visual Systems\n\n> **Canon note (2026-07-12 consolidation).** This skill now rides ONE rubric, ONE canon,\n> and ONE artifact contract:\n> - **One rubric:** the design-quality verdict is **DESIGN-EVAL v1** (9 dimensions, 0-4,\n>   critical-error override, weighted composite), whose single source of truth is\n>   `~\u002F.claude\u002Fskills\u002Fui-audit\u002Fcritique_rubric.md` + `critique.schema.json`. The former\n>   Mode-2 bespoke **10-dimension \u002F 0-10** scale is **RETIRED** (crosswalk below).\n> - **One canon:** design decisions live in **`\u003Crepo>\u002F.design\u002FDESIGN.md`** (per-page\n>   override sections) + a **W3C-DTCG** `\u003Crepo>\u002F.design\u002Fdesign-tokens.json`. There is no\n>   longer a competing `design-system\u002FMASTER.md` canon.\n> - **One artifact contract:** every stage reads\u002Fwrites a leaf under **`\u003Crepo>\u002F.design\u002F`**\n>   (see [The `.design\u002F` artifact contract](#the-design-artifact-contract)). Downstream\n>   gates parse those leaf artifacts — never an honor-system \"audit passed\" flag.\n>\n> This skill is being consolidated under the **`design-studio`** meta-skill (the mode\n> router). Until that rename lands, invoke it as `design-system` and treat `ui-audit` as\n> the audit\u002Fdrive engine it delegates to. Nothing here BLOCKS: the artifact-contract\n> gates run in shadow\u002Fadvisory mode when first wired (council C5).\n\n## When to Use\n\n- Starting a new project that needs a design system\n- Auditing an existing codebase for visual consistency\n- Before a redesign — understand what you have\n- When the UI looks \"off\" but you can't pinpoint why\n- Reviewing PRs that touch styling\n\n## How It Works\n\n### Mode 1: Generate Design System\n\nAnalyzes your codebase and generates a cohesive design system into the single canon:\n\n```\n1. Scan CSS\u002FTailwind\u002Fstyled-components for existing patterns\n2. Extract: colors, typography, spacing, border-radius, shadows, breakpoints\n3. Research 3 competitor sites for inspiration (via browser MCP)\n4. Propose a design token set as W3C-DTCG tokens ($value\u002F$type)\n5. Generate .design\u002FDESIGN.md with rationale for each decision\n6. (Optional) Create an interactive HTML preview page (self-contained, no deps)\n```\n\n**Output (canon):**\n- `\u003Crepo>\u002F.design\u002FDESIGN.md` — the human canon, with per-page override sections.\n- `\u003Crepo>\u002F.design\u002Fdesign-tokens.json` — **W3C-DTCG** source-of-truth tokens\n  (see [`design-tokens-pipeline`](#token-spine) for the Style-Dictionary\u002FFigma emit).\n- `\u003Crepo>\u002F.design\u002Fdesign-preview.html` — optional, self-contained preview (NOT canon).\n\n> The tokens are authored in the **W3C Design Tokens Community Group** format\n> (`$value` \u002F `$type` \u002F `$description`, group nesting, `{alias.reference}` refs). This is\n> the lossless half of the code↔Figma round-trip and the input to the token pipeline.\n\n### Mode 2: Visual Audit — DESIGN-EVAL v1 (canonical)\n\nThe visual audit no longer defines its own scale. It **delegates to the canonical\nDESIGN-EVAL v1 rubric** driven by `ui-audit`:\n\n```\n1. Capture the running app  → ui-audit Track-A  → .design\u002Faudit.json   (deterministic numbers)\n2. Reason over numbers + screenshot on DESIGN-EVAL v1 (9 dims, one dim per pass)\n3. Compute the weighted composite → .design\u002Fcritique-output.json (Track-B verdict)\n```\n\nDESIGN-EVAL v1 scores **nine dimensions, each 0-4** (not 0-10), with a **critical-error\noverride** (forces that dimension to 0 and caps the verdict) and a **weighted composite**\n(color-contrast weighted highest at 2.0). The nine dimensions:\n\n| # | Dimension | Weight |\n|---|-----------|--------|\n| 1 | `visual-hierarchy` | 1.5 |\n| 2 | `spacing-rhythm` | 1.0 |\n| 3 | `alignment` | 0.75 |\n| 4 | `type-scale` | 1.0 |\n| 5 | `color-contrast` | **2.0** |\n| 6 | `consistency` | 1.0 |\n| 7 | `empty-error-states` | 1.5 |\n| 8 | `affordance` | 1.5 |\n| 9 | `motion` | 0.75 |\n\n**Ship gate** (WCAG-3.0-style Bronze): mean ≥ 3.0 AND no dimension \u003C 2 AND zero critical\nerrors. The rubric text, per-dimension anchors, critical triggers, and the composite\nformula are canonical in `ui-audit\u002Fcritique_rubric.md` — **do not re-state or fork them\nhere.**\n\n#### Retired 10-dim → DESIGN-EVAL v1 crosswalk\n\nThe legacy Mode-2 10-dimension \u002F 0-10 scale is **retired**. Every legacy dimension maps\nonto a DESIGN-EVAL v1 dimension (or an advisory sub-signal) so no coverage is lost:\n\n| Legacy Mode-2 dim (0-10) | → DESIGN-EVAL v1 (0-4) | Note |\n|--------------------------|------------------------|------|\n| 1. Color consistency | `color-contrast` | palette\u002Ftoken consolidation + WCAG |\n| 2. Typography hierarchy | `type-scale` + `visual-hierarchy` | ramp discipline vs. focal order |\n| 3. Spacing rhythm | `spacing-rhythm` | 1:1 |\n| 4. Component consistency | `consistency` | 1:1 |\n| 5. Responsive behavior | `consistency` (advisory sub-signal) | breakpoint\u002Freflow capture, advisory |\n| 6. Dark mode | `consistency` (advisory sub-signal) | dual-theme capture, advisory |\n| 7. Animation | `motion` | 200-500ms band + reduced-motion |\n| 8. Accessibility | `color-contrast` (WCAG) + `affordance` (focus\u002Ftarget) | split by concern |\n| 9. Information density | `visual-hierarchy` (anchor) | density reads as hierarchy pressure |\n| 10. Polish | `affordance` + `empty-error-states` + `motion` | hover\u002Ffeedback, empty\u002Floading, transitions |\n| — (new in v1) | `alignment` | shared edges\u002Fbaselines — screenshot-judged |\n\nEach finding still gets a severity (Nielsen 0-4: critical\u002Fhigh\u002Fmedium\u002Flow\u002Finfo), the\nconcrete evidence (cited by its Track-A `ref`), and a fix with exact `file:line`.\n\n### Mode 3: AI Slop Detection (advisory critique pack)\n\nSlop detection is now an **advisory heuristics pack** that feeds the DESIGN-EVAL v1\ncritique as anchors — it is **not** a separate score. Surface these as `info`\u002F`low`\nfindings on the mapped dimension (shown in brackets):\n\n```\n- Gratuitous gradients on everything                              [visual-hierarchy]\n- Purple-to-blue defaults                                         [color-contrast]\n- \"Glass morphism\" cards with no purpose                          [consistency]\n- Rounded corners on things that shouldn't be rounded            [consistency]\n- Excessive animations on scroll                                  [motion]\n- Generic hero with centered text over stock gradient            [visual-hierarchy]\n- Sans-serif font stack with no personality                      [type-scale]\n```\n\nFold these into `critique.mjs assemble` as slop-pack anchors; they raise scrutiny, never\nforce a score on their own (only the rubric's critical-error triggers do that).\n\n## The `.design\u002F` artifact contract\n\nEvery stage of the design pipeline reads and writes a **leaf artifact** under the repo's\n`.design\u002F` directory. This mirrors metaswarm's proven `.beads\u002F` recovery pattern: a fresh\nClaude or Codex thread can pick up `.design\u002F` cold and know exactly where each stage's\ninput\u002Foutput lives. **Downstream gates parse these leaves — never an honor-system flag.**\n\n| Leaf | Written by | Read by | Purpose |\n|------|-----------|---------|---------|\n| `DESIGN.md` | Mode 1 (generate) \u002F DIRECT | every stage | the human canon (per-page override sections) |\n| `design-tokens.json` | Mode 1 \u002F token pipeline | tokens, mirror | **W3C-DTCG** source-of-truth tokens |\n| `audit.json` | `ui-audit` Track-A | critique, gates | deterministic numbers (contrast, spacing, tap-targets, a11y, regression) |\n| `critique-output.json` | `ui-audit` Track-B | gates, revert-gate | the DESIGN-EVAL v1 verdict (9 dims + composite) |\n| `transpose-record.json` | transpose (code→canvas) | mirror, gates | what was mirrored to Figma + drift class |\n| `tokens.json` | token pipeline (emit) | transpose, mirror | resolved\u002Femitted DTCG tokens (Style-Dictionary output) |\n| `mirror-manifest.json` | mirror (`use_figma`) | reverse-drift guard | `screen → figmaFileKey+nodeId, commit, content-hash` (skip when unchanged) |\n| `loop-state.json` | `loop.mjs advance` | recovery, gates | stage → artifact-path map; the state machine's memory |\n| `baselines\u002F` | `ui-audit visual_diff` | regression | per-screen baseline PNGs |\n\n**Evidence-bound gates (the point).** When the pipeline advances a stage, the gate\n**parses the leaf** (e.g. reads `critique-output.json.verdict.score` + the critical-error\ncount, or `audit.json` totals) rather than trusting a caller-supplied \"it passed\" boolean.\n`loop-state.json` records each stage's artifact path so the next stage auto-discovers its\ninput and a reviewer can reconstruct the whole run from disk. This applies the skill's own\n\"never self-certify\" rule to the skill itself.\n\nReference templates for every leaf ship alongside this skill under\n`references\u002F.design-templates\u002F` (copy them to seed a repo's `.design\u002F`).\n\n## \u003Ca name=\"token-spine\">\u003C\u002Fa>Token spine (DTCG)\n\nThe W3C-DTCG `design-tokens.json` is the lossless canon. The\n[`design-tokens-pipeline`](#) skill emits platform artifacts (CSS custom properties,\nTailwind, Style-Dictionary output → `tokens.json`) and Figma Variables (via a `use_figma`\nPlugin-API script — quota-exempt writes on the Education Full seat). **Code → Figma is\nrender-mediated and lossy:** tokens + Code-Connected components round-trip; React\nstate\u002Frouting\u002Flogic never survive. The mirror marks *staleness*, never pretends a live\ntwo-way sync.\n\n## Examples\n\n**Generate into the canon:**\n```\n\u002Fdesign-system generate --style minimal --palette earth-tones\n# → .design\u002FDESIGN.md + .design\u002Fdesign-tokens.json (DTCG)\n```\n\n**Audit an existing UI (DESIGN-EVAL v1):**\n```\n\u002Fdesign-system audit --url http:\u002F\u002Flocalhost:3000 --pages \u002F \u002Fpricing \u002Fdocs\n# → .design\u002Faudit.json (Track-A) + .design\u002Fcritique-output.json (Track-B, 9-dim verdict)\n```\n\n**Check for AI slop (advisory anchors):**\n```\n\u002Fdesign-system slop-check\n# → info\u002Flow findings folded into the DESIGN-EVAL v1 critique\n```\n","# Design System — Generate & Audit Visual Systems\n\n> **Canon note (2026-07-12 consolidation).** This skill now rides ONE rubric, ONE canon,\n> and ONE artifact contract:\n> - **One rubric:** the design-quality verdict is **DESIGN-EVAL v1** (9 dimensions, 0-4,\n>   critical-error override, weighted composite), whose single source of truth is\n>   `~\u002F.claude\u002Fskills\u002Fui-audit\u002Fcritique_rubric.md` + `critique.schema.json`. The former\n>   Mode-2 bespoke **10-dimension \u002F 0-10** scale is **RETIRED** (crosswalk below).\n> - **One canon:** design decisions live in **`\u003Crepo>\u002F.design\u002FDESIGN.md`** (per-page\n>   override sections) + a **W3C-DTCG** `\u003Crepo>\u002F.design\u002Fdesign-tokens.json`. There is no\n>   longer a competing `design-system\u002FMASTER.md` canon.\n> - **One artifact contract:** every stage reads\u002Fwrites a leaf under **`\u003Crepo>\u002F.design\u002F`**\n>   (see [The `.design\u002F` artifact contract](#the-design-artifact-contract)). Downstream\n>   gates parse those leaf artifacts — never an honor-system \"audit passed\" flag.\n>\n> This skill is being consolidated under the **`design-studio`** meta-skill (the mode\n> router). Until that rename lands, invoke it as `design-system` and treat `ui-audit` as\n> the audit\u002Fdrive engine it delegates to. Nothing here BLOCKS: the artifact-contract\n> gates run in shadow\u002Fadvisory mode when first wired (council C5).\n\n## When to Use\n\n- Starting a new project that needs a design system\n- Auditing an existing codebase for visual consistency\n- Before a redesign — understand what you have\n- When the UI looks \"off\" but you can't pinpoint why\n- Reviewing PRs that touch styling\n\n## How It Works\n\n### Mode 1: Generate Design System\n\nAnalyzes your codebase and generates a cohesive design system into the single canon:\n\n```\n1. Scan CSS\u002FTailwind\u002Fstyled-components for existing patterns\n2. Extract: colors, typography, spacing, border-radius, shadows, breakpoints\n3. Research 3 competitor sites for inspiration (via browser MCP)\n4. Propose a design token set as W3C-DTCG tokens ($value\u002F$type)\n5. Generate .design\u002FDESIGN.md with rationale for each decision\n6. (Optional) Create an interactive HTML preview page (self-contained, no deps)\n```\n\n**Output (canon):**\n- `\u003Crepo>\u002F.design\u002FDESIGN.md` — the human canon, with per-page override sections.\n- `\u003Crepo>\u002F.design\u002Fdesign-tokens.json` — **W3C-DTCG** source-of-truth tokens\n  (see [`design-tokens-pipeline`](#token-spine) for the Style-Dictionary\u002FFigma emit).\n- `\u003Crepo>\u002F.design\u002Fdesign-preview.html` — optional, self-contained preview (NOT canon).\n\n> The tokens are authored in the **W3C Design Tokens Community Group** format\n> (`$value` \u002F `$type` \u002F `$description`, group nesting, `{alias.reference}` refs). This is\n> the lossless half of the code↔Figma round-trip and the input to the token pipeline.\n\n### Mode 2: Visual Audit — DESIGN-EVAL v1 (canonical)\n\nThe visual audit no longer defines its own scale. It **delegates to the canonical\nDESIGN-EVAL v1 rubric** driven by `ui-audit`:\n\n```\n1. Capture the running app  → ui-audit Track-A  → .design\u002Faudit.json   (deterministic numbers)\n2. Reason over numbers + screenshot on DESIGN-EVAL v1 (9 dims, one dim per pass)\n3. Compute the weighted composite → .design\u002Fcritique-output.json (Track-B verdict)\n```\n\nDESIGN-EVAL v1 scores **nine dimensions, each 0-4** (not 0-10), with a **critical-error\noverride** (forces that dimension to 0 and caps the verdict) and a **weighted composite**\n(color-contrast weighted highest at 2.0). The nine dimensions:\n\n| # | Dimension | Weight |\n|---|-----------|--------|\n| 1 | `visual-hierarchy` | 1.5 |\n| 2 | `spacing-rhythm` | 1.0 |\n| 3 | `alignment` | 0.75 |\n| 4 | `type-scale` | 1.0 |\n| 5 | `color-contrast` | **2.0** |\n| 6 | `consistency` | 1.0 |\n| 7 | `empty-error-states` | 1.5 |\n| 8 | `affordance` | 1.5 |\n| 9 | `motion` | 0.75 |\n\n**Ship gate** (WCAG-3.0-style Bronze): mean ≥ 3.0 AND no dimension \u003C 2 AND zero critical\nerrors. The rubric text, per-dimension anchors, critical triggers, and the composite\nformula are canonical in `ui-audit\u002Fcritique_rubric.md` — **do not re-state or fork them\nhere.**\n\n#### Retired 10-dim → DESIGN-EVAL v1 crosswalk\n\nThe legacy Mode-2 10-dimension \u002F 0-10 scale is **retired**. Every legacy dimension maps\nonto a DESIGN-EVAL v1 dimension (or an advisory sub-signal) so no coverage is lost:\n\n| Legacy Mode-2 dim (0-10) | → DESIGN-EVAL v1 (0-4) | Note |\n|--------------------------|------------------------|------|\n| 1. Color consistency | `color-contrast` | palette\u002Ftoken consolidation + WCAG |\n| 2. Typography hierarchy | `type-scale` + `visual-hierarchy` | ramp discipline vs. focal order |\n| 3. Spacing rhythm | `spacing-rhythm` | 1:1 |\n| 4. Component consistency | `consistency` | 1:1 |\n| 5. Responsive behavior | `consistency` (advisory sub-signal) | breakpoint\u002Freflow capture, advisory |\n| 6. Dark mode | `consistency` (advisory sub-signal) | dual-theme capture, advisory |\n| 7. Animation | `motion` | 200-500ms band + reduced-motion |\n| 8. Accessibility | `color-contrast` (WCAG) + `affordance` (focus\u002Ftarget) | split by concern |\n| 9. Information density | `visual-hierarchy` (anchor) | density reads as hierarchy pressure |\n| 10. Polish | `affordance` + `empty-error-states` + `motion` | hover\u002Ffeedback, empty\u002Floading, transitions |\n| — (new in v1) | `alignment` | shared edges\u002Fbaselines — screenshot-judged |\n\nEach finding still gets a severity (Nielsen 0-4: critical\u002Fhigh\u002Fmedium\u002Flow\u002Finfo), the\nconcrete evidence (cited by its Track-A `ref`), and a fix with exact `file:line`.\n\n### Mode 3: AI Slop Detection (advisory critique pack)\n\nSlop detection is now an **advisory heuristics pack** that feeds the DESIGN-EVAL v1\ncritique as anchors — it is **not** a separate score. Surface these as `info`\u002F`low`\nfindings on the mapped dimension (shown in brackets):\n\n```\n- Gratuitous gradients on everything                              [visual-hierarchy]\n- Purple-to-blue defaults                                         [color-contrast]\n- \"Glass morphism\" cards with no purpose                          [consistency]\n- Rounded corners on things that shouldn't be rounded            [consistency]\n- Excessive animations on scroll                                  [motion]\n- Generic hero with centered text over stock gradient            [visual-hierarchy]\n- Sans-serif font stack with no personality                      [type-scale]\n```\n\nFold these into `critique.mjs assemble` as slop-pack anchors; they raise scrutiny, never\nforce a score on their own (only the rubric's critical-error triggers do that).\n\n## The `.design\u002F` artifact contract\n\nEvery stage of the design pipeline reads and writes a **leaf artifact** under the repo's\n`.design\u002F` directory. This mirrors metaswarm's proven `.beads\u002F` recovery pattern: a fresh\nClaude or Codex thread can pick up `.design\u002F` cold and know exactly where each stage's\ninput\u002Foutput lives. **Downstream gates parse these leaves — never an honor-system flag.**\n\n| Leaf | Written by | Read by | Purpose |\n|------|-----------|---------|---------|\n| `DESIGN.md` | Mode 1 (generate) \u002F DIRECT | every stage | the human canon (per-page override sections) |\n| `design-tokens.json` | Mode 1 \u002F token pipeline | tokens, mirror | **W3C-DTCG** source-of-truth tokens |\n| `audit.json` | `ui-audit` Track-A | critique, gates | deterministic numbers (contrast, spacing, tap-targets, a11y, regression) |\n| `critique-output.json` | `ui-audit` Track-B | gates, revert-gate | the DESIGN-EVAL v1 verdict (9 dims + composite) |\n| `transpose-record.json` | transpose (code→canvas) | mirror, gates | what was mirrored to Figma + drift class |\n| `tokens.json` | token pipeline (emit) | transpose, mirror | resolved\u002Femitted DTCG tokens (Style-Dictionary output) |\n| `mirror-manifest.json` | mirror (`use_figma`) | reverse-drift guard | `screen → figmaFileKey+nodeId, commit, content-hash` (skip when unchanged) |\n| `loop-state.json` | `loop.mjs advance` | recovery, gates | stage → artifact-path map; the state machine's memory |\n| `baselines\u002F` | `ui-audit visual_diff` | regression | per-screen baseline PNGs |\n\n**Evidence-bound gates (the point).** When the pipeline advances a stage, the gate\n**parses the leaf** (e.g. reads `critique-output.json.verdict.score` + the critical-error\ncount, or `audit.json` totals) rather than trusting a caller-supplied \"it passed\" boolean.\n`loop-state.json` records each stage's artifact path so the next stage auto-discovers its\ninput and a reviewer can reconstruct the whole run from disk. This applies the skill's own\n\"never self-certify\" rule to the skill itself.\n\nReference templates for every leaf ship alongside this skill under\n`references\u002F.design-templates\u002F` (copy them to seed a repo's `.design\u002F`).\n\n## \u003Ca name=\"token-spine\">\u003C\u002Fa>Token spine (DTCG)\n\nThe W3C-DTCG `design-tokens.json` is the lossless canon. The\n[`design-tokens-pipeline`](#) skill emits platform artifacts (CSS custom properties,\nTailwind, Style-Dictionary output → `tokens.json`) and Figma Variables (via a `use_figma`\nPlugin-API script — quota-exempt writes on the Education Full seat). **Code → Figma is\nrender-mediated and lossy:** tokens + Code-Connected components round-trip; React\nstate\u002Frouting\u002Flogic never survive. The mirror marks *staleness*, never pretends a live\ntwo-way sync.\n\n## Examples\n\n**Generate into the canon:**\n```\n\u002Fdesign-system generate --style minimal --palette earth-tones\n# → .design\u002FDESIGN.md + .design\u002Fdesign-tokens.json (DTCG)\n```\n\n**Audit an existing UI (DESIGN-EVAL v1):**\n```\n\u002Fdesign-system audit --url http:\u002F\u002Flocalhost:3000 --pages \u002F \u002Fpricing \u002Fdocs\n# → .design\u002Faudit.json (Track-A) + .design\u002Fcritique-output.json (Track-B, 9-dim verdict)\n```\n\n**Check for AI slop (advisory anchors):**\n```\n\u002Fdesign-system slop-check\n# → info\u002Flow findings folded into the DESIGN-EVAL v1 critique\n```\n",{"name":5,"origin":55,"description":7},"ECC","main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fdesign-system","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill design-system",{"tool":68,"command":69},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill design-system",{"tool":71,"command":72},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill design-system","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdesign-system\u002FSKILL.md",true,[76,82,86,90,94,98,102,106,110,114],{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002F.design-templates\u002Faudit.json","REFERENCE","参考文档",1512,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdesign-system\u002Freferences\u002F.design-templates\u002Faudit.json",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002F.design-templates\u002Fbaselines\u002F.gitkeep",58,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdesign-system\u002Freferences\u002F.design-templates\u002Fbaselines\u002F.gitkeep",{"path":87,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002F.design-templates\u002Fcritique-output.json",1918,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdesign-system\u002Freferences\u002F.design-templates\u002Fcritique-output.json",{"path":91,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002F.design-templates\u002Fdesign-tokens.json",2355,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdesign-system\u002Freferences\u002F.design-templates\u002Fdesign-tokens.json",{"path":95,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002F.design-templates\u002FDESIGN.md",1751,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdesign-system\u002Freferences\u002F.design-templates\u002FDESIGN.md",{"path":99,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002F.design-templates\u002Floop-state.json",1878,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdesign-system\u002Freferences\u002F.design-templates\u002Floop-state.json",{"path":103,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":104,"sourceHtmlUrl":105},"references\u002F.design-templates\u002Fmirror-manifest.json",703,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdesign-system\u002Freferences\u002F.design-templates\u002Fmirror-manifest.json",{"path":107,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":108,"sourceHtmlUrl":109},"references\u002F.design-templates\u002FREADME.md",2228,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdesign-system\u002Freferences\u002F.design-templates\u002FREADME.md",{"path":111,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":112,"sourceHtmlUrl":113},"references\u002F.design-templates\u002Ftokens.json",891,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdesign-system\u002Freferences\u002F.design-templates\u002Ftokens.json",{"path":115,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":116,"sourceHtmlUrl":117},"references\u002F.design-templates\u002Ftranspose-record.json",709,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdesign-system\u002Freferences\u002F.design-templates\u002Ftranspose-record.json",[119,140,169,193,207,223],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":50},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[126,127,128,129,130,131,132,133,134,43,135,136,137,138,139],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":149,"publishedAt":50},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[146],{"categoryNo":147,"categoryName":148,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[150,151,152,153,154,155,156,157,158,159,160,161,162,163,43,164,165,166,167,168],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":181,"publishedAt":50},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[175,178],{"categoryNo":176,"categoryName":177,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":179,"categoryName":180,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[49,39,182,183,184,185,186,187,44,188,151,189,190,191,192],"visual review","pages","web","false","iteration","take","slides","ui","screenshot","playwright","screenshots",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":199,"publishedAt":50},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[195,200,201,202,203,204,205,206],"setup","report","project","installation","project setup","issues","state",{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":211,"categories":212,"keywords":214,"publishedAt":50},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[213],{"categoryNo":147,"categoryName":148,"taxonomyType":21,"taxonomyTypeDesc":22},[209,215,131,216,217,218,43,219,220,221,222],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":224,"name":200,"nameZh":6,"description":225,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":226,"categories":227,"keywords":228,"publishedAt":50},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[200,202,166,229,204,230],"files","interactive"]