[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MFXWPE1BS0894EP4EDE4XR":3,"skill-same:01M6MFXWPE1BS0894EP4EDE4XR":96},{"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":33,"publishedAt":54,"linkOnly":55,"markdownContent":56,"markdownBody":57,"frontMatter":58,"refName":76,"commitSha":77,"skillDirectory":78,"forksCount":13,"repositoryHtmlUrl":79,"repositoryHomepageUrl":6,"ownerHtmlUrl":80,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":81,"install":82,"resources":95},"01M6MFXWPE1BS0894EP4EDE4XR","design-system",null,"Captures the user's brand identity once via a 10-question onboarding wizard (primary\u002Faccent HEX + heading + body Google Fonts + design style editorial\u002Ftechnical\u002Fminimal\u002Fplayful + default output directory + syntax theme + TOC behavior + optional logo\u002Fcompany), validates body-text and link contrast against WCAG 2.2 AA, derives 12 CSS custom properties in HSL space, and stores the result for every markdown-html converter to consume. Use before any markdown-html conversion. Triggers on first-run onboarding (\"set up the brand\", \"configure markdown-html\", \"run onboarding\"), on explicit reset (\"reset the design system\", \"re-onboard\"), and is checked by every converter via config_loader.py before rendering. Refuses to save if body-text contrast fails AA 4.5:1 or the output dir isn't writable. Precedence is project (.\u002F.markdown-html\u002F) > global (~\u002F.config\u002Fmarkdown-html\u002F) > built-in defaults; MARKDOWN_HTML_NO_CONFIG=1 bypasses.","JiayiV\u002Fquestion_mixing","JiayiV","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54466889?v=4","01M6JFJYYMRZ3QRGP9339JNQ2K","01M6JFJZ35KB0QVT50NAHPJA7G",0,"MIT","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-gemini-skills-design-system-skill-8e01c868\u002FSKILL.md",[17,22,25,30],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":26,"categoryName":27,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",{"categoryNo":31,"categoryName":32,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000038","人力资源",[34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53],"design system","system","design","up","company","design style","re","Variables","reset","project","hex","default","conversion","question","configure","logo","wizard","SET","code","css","2026-11-10 10:12:30",false,"---\nname: design-system\ndescription: Captures the user's brand identity once via a 10-question onboarding wizard (primary\u002Faccent HEX + heading + body Google Fonts + design style editorial\u002Ftechnical\u002Fminimal\u002Fplayful + default output directory + syntax theme + TOC behavior + optional logo\u002Fcompany), validates body-text and link contrast against WCAG 2.2 AA, derives 12 CSS custom properties in HSL space, and stores the result for every markdown-html converter to consume. Use before any markdown-html conversion. Triggers on first-run onboarding (\"set up the brand\", \"configure markdown-html\", \"run onboarding\"), on explicit reset (\"reset the design system\", \"re-onboard\"), and is checked by every converter via config_loader.py before rendering. Refuses to save if body-text contrast fails AA 4.5:1 or the output dir isn't writable. Precedence is project (.\u002F.markdown-html\u002F) > global (~\u002F.config\u002Fmarkdown-html\u002F) > built-in defaults; MARKDOWN_HTML_NO_CONFIG=1 bypasses.\nversion: 2.10.0\nauthor: Alireza Rezvani\nlicense: MIT\ntags: [design-system, brand-palette, wcag, onboarding, customization, markdown-html, css-variables, typography]\ncompatible_tools: [claude-code, codex-cli, cursor, antigravity, opencode, gemini-cli]\n---\n\n# Design System — Onboarding + Shared Brand Tokens\n\nThe design-system skill is the **shared brand owner** for the markdown-html plugin. Run its onboarding once. Every converter (`md-document`, `md-review`, `md-slides`) reads the resulting config via `config_loader.py` and applies the same 12 CSS custom properties to its output. Without this, conversions render with placeholder defaults — technically functional but unbranded.\n\nThis skill ships exactly three Python tools:\n\n1. **`onboard.py`** — interactive (or `--defaults` \u002F `--set` \u002F `--show` \u002F `--reset`) wizard.\n2. **`config_loader.py`** — importable customization loader with project > global > defaults precedence and `MARKDOWN_HTML_NO_CONFIG=1` bypass.\n3. **`brand_palette_validator.py`** — WCAG-AA contrast checker + HSL palette deriver.\n\nAll three are stdlib-only and contain no LLM calls (deterministic per Path-B discipline).\n\n## When to invoke\n\n| Symptom | Action |\n|---|---|\n| User says \"convert this markdown to HTML\" for the first time in this workspace | Run `python3 markdown-html\u002Fskills\u002Fdesign-system\u002Fscripts\u002Fonboard.py` |\n| `~\u002F.config\u002Fmarkdown-html\u002Fdesign-system.json` doesn't exist OR `setup_completed_at` is null | Refuse conversion, surface onboarding |\n| User wants per-repo brand override | `python3 ...\u002Fonboard.py --scope project` |\n| User wants to change a single field non-interactively | `python3 ...\u002Fonboard.py --set brand.primary=#FF6B35` |\n| User wants to reset and re-onboard | `python3 ...\u002Fonboard.py --reset` then re-run |\n| User wants zero-touch defaults (CI, ephemeral session) | `python3 ...\u002Fonboard.py --defaults` |\n| Headless \u002F containerized run that should ignore saved config | `MARKDOWN_HTML_NO_CONFIG=1 ...` |\n\n## Onboarding question set (10 questions)\n\n| # | Key | Choices \u002F Validator | Default |\n|---|---|---|---|\n| 1 | `default_output_dir` | path; `os.access(parent, os.W_OK)` | `.\u002Fmarkdown-html-out\u002F` |\n| 2 | `brand.primary` | HEX `^#?[0-9a-fA-F]{6}$` | `#0A1628` |\n| 3 | `brand.accent` | HEX or blank (auto-derive) | derive from primary |\n| 4 | `typography.heading_font` | Google Font name (12 safe defaults) | `Inter` |\n| 5 | `typography.body_font` | Google Font name | `Inter` |\n| 6 | `design_style` | `editorial \u002F technical \u002F minimal \u002F playful` | `technical` |\n| 7 | `code_theme` | `light \u002F dark \u002F auto` | `auto` |\n| 8 | `toc.behavior` | `sticky-sidebar \u002F collapsible-top \u002F inline \u002F none` | `sticky-sidebar` |\n| 9 | `company_name` | string (may be empty) | `\"\"` |\n| 10 | `logo_url` | URL or empty (base64-embedded at render) | `\"\"` |\n\n## Hard rules\n\n1. **WCAG AA body-text contrast must pass.** `brand_palette_validator.validate()` runs after every change. Body text on bg must reach 4.5:1; link on bg must reach 4.5:1. If either fails, `onboard.py` refuses to save (exit code 4) and tells the user to pick a darker primary, blank `brand.bg`\u002F`brand.text` to let derivation pick a safe pair, or override `brand.text` directly. Canon: WCAG 2.2 §1.4.3.\n2. **Output directory must be writable.** `onboard.py` walks up the path to find an existing ancestor and checks `os.W_OK`. Empty or unwritable path → exit code 3. The orchestrator's `output_path_resolver.py` honors the same rule per-conversion.\n3. **Customization must change behavior, not sit as decoration.** Every consumer (md-document, md-review, md-slides) must read the config and render differently when the user changes `design_style`, `brand.primary`, `code_theme`, or `toc.behavior`. Decorative-only fields fail the design discipline.\n4. **Precedence is fixed.** Project > global > defaults. The deep-merge preserves nested keys (e.g. you can override `brand.primary` in a project config without losing `typography.heading_font` from global).\n5. **Bypass env exists for a reason.** `MARKDOWN_HTML_NO_CONFIG=1` is for headless CI, ephemeral test containers, and the autoresearch-style evaluator loops. Never set it silently for an interactive user.\n\n## Derived 12-token palette\n\nOnce the user's brand is captured, `brand_palette_validator.derive_palette()` produces 12 CSS custom properties stored under `derived_palette` in the same config file. Every converter inlines these into its `\u003Cstyle>` block.\n\n| Token | Purpose | Derivation |\n|---|---|---|\n| `--md-bg` | Document background | Primary if dark, near-neutral if vibrant |\n| `--md-surface` | Card \u002F callout \u002F blockquote background | Bg ± 4-6% luminance |\n| `--md-border` | Hairline dividers, table borders | Bg ± 8-12% luminance |\n| `--md-text` | Body text | Off-white on dark bg, near-black on light bg |\n| `--md-text-muted` | Captions, metadata, footers | `rgba(text, 0.68)` |\n| `--md-accent` | Primary CTA, callout headers, link emphasis | Primary if vibrant, hue-shifted lighter if dark |\n| `--md-accent-soft` | Accent backgrounds, hover states | `rgba(accent, 0.14)` |\n| `--md-code-bg` | Inline code, fenced block bg | Bg ± 4-5% luminance |\n| `--md-link` | Hyperlinks | Iteratively walked to reach 4.5:1 contrast on bg |\n| `--md-link-hover` | Hover state | Link ± 6-8% luminance |\n| `--md-success` | OK \u002F approved \u002F passed | Green anchored, luminance-matched |\n| `--md-warn` | Caution \u002F nit \u002F TODO | Amber anchored, luminance-matched |\n\n## Forcing-question library (Matt Pocock grill-with-docs pattern)\n\nOne question per turn, recommended answer, canon citation.\n\n1. **What's your brand primary color?** Recommended: a HEX you already use in your product or docs — not a stock blue. Canon: Aarron Walter, *Designing for Emotion* (color carries brand affect).\n2. **Should accent be derived or set?** Recommended: derive on first run (hue-shift + lighten produces a coherent companion); set explicitly only if your brand kit specifies one. Canon: Adobe Spectrum, *Color Foundations*.\n3. **Editorial, technical, minimal, or playful?** Recommended: `technical` for engineering specs\u002Freports, `editorial` for long-read narratives, `minimal` for sparse reference docs, `playful` for marketing\u002Flanding content. Canon: Ellen Lupton, *Thinking with Type* (style serves the rhetorical purpose).\n4. **Sticky-sidebar TOC, or inline?** Recommended: `sticky-sidebar` for documents over 800 words, `inline` for short reads. Canon: Nielsen-Norman, *Table of Contents Best Practices* (2023).\n5. **Save to global or per-project?** Recommended: global by default (consistent across your work); use `--scope project` only when this repo has a different brand. Canon: research-ops onboarding pattern, `research-ops\u002FCLAUDE.md` §8.\n\n## Customization in use (worked example)\n\n```bash\n# First-run onboarding (interactive, walks all 10 questions)\npython3 markdown-html\u002Fskills\u002Fdesign-system\u002Fscripts\u002Fonboard.py\n\n# Zero-touch defaults for CI \u002F first-test\npython3 ...\u002Fonboard.py --defaults\n\n# Change just the primary color and design style\npython3 ...\u002Fonboard.py --set brand.primary=#FF6B35 --set design_style=editorial\n\n# Per-repo override\npython3 ...\u002Fonboard.py --scope project --set design_style=minimal\n\n# Reset and re-onboard\npython3 ...\u002Fonboard.py --reset\npython3 ...\u002Fonboard.py\n\n# Inspect the effective config (project > global > defaults)\npython3 ...\u002Fconfig_loader.py --show\npython3 ...\u002Fconfig_loader.py --status\n\n# Bypass saved config (returns DEFAULTS only)\nMARKDOWN_HTML_NO_CONFIG=1 python3 ...\u002Fconfig_loader.py --show\n\n# Spot-check WCAG contrast before committing to a brand\npython3 ...\u002Fbrand_palette_validator.py --primary \"#FF6B35\" --accent \"#00D4AA\"\n```\n\n## Assumptions\n\n1. User has at least one brand HEX they want consistent across their HTML conversions.\n2. User accepts a 1-2 minute one-time setup.\n3. User is OK with Google Fonts as the typography source (CDN, no local font hosting).\n4. WCAG 2.2 AA is the accessibility floor (4.5:1 body, 3:1 large\u002FUI). AAA (7:1) is out of scope.\n\n## Non-goals\n\n- Not a full design-token system (Style Dictionary, Theo). Twelve tokens, not a hundred.\n- Not a custom-font hosting solution. Google Fonts only.\n- Not a dark\u002Flight mode switcher in the converters. `code_theme: auto` handles the prefers-color-scheme case for syntax highlighting; layout palette is single-mode per onboarding.\n- Not an accessibility audit suite (use axe-core \u002F pa11y for that). We enforce contrast only.\n- Does not transform existing CSS — the derived palette is injected into freshly generated HTML.\n\n## Distinct from\n\n- **`marketing\u002Flanding\u002Fskills\u002Flanding\u002Fscripts\u002Fbrand_palette_validator.py`** — that script's `derive_palette()` produces 8 tokens shaped for hero-page rendering (`--navy`, `--teal`, `--card-bg`, `--card-border`). This script produces 12 tokens shaped for document rendering (sticky surface, hairline border, code bg, link, link-hover, success, warn). Same WCAG + HSL math, different token taxonomy.\n- **`research-ops\u002Fskills\u002Fclinical-research\u002Fscripts\u002Fonboard.py`** — same pattern (interactive + `--defaults`\u002F`--set`\u002F`--show`\u002F`--reset`\u002F`--scope`), different question set (clinical alpha\u002Fpower\u002Fdropout vs. brand palette\u002Ftypography\u002Flayout).\n\n## Output artifact\n\n`~\u002F.config\u002Fmarkdown-html\u002Fdesign-system.json` (global) or `.\u002F.markdown-html\u002Fdesign-system.json` (project). JSON schema lives at `assets\u002Fdesign_system_schema.json`.\n\n## Anti-patterns (do not)\n\n- ❌ Skip onboarding and run a converter with placeholder defaults — output looks unbranded.\n- ❌ Pick a vibrant brand primary as `brand.bg` directly (low text contrast). Use it as accent instead.\n- ❌ Set `MARKDOWN_HTML_NO_CONFIG=1` silently for an interactive user — they'll wonder why their tokens disappeared.\n- ❌ Encode brand semantics in `derived_palette` outside the 12-token taxonomy. Add a new token only with a deliberate name + purpose + derivation rule.\n\n## References\n\n- WCAG 2.2 — §1.4.3 (contrast), §1.4.4 (resize), §1.4.11 (non-text contrast)\n- Aarron Walter — *Designing for Emotion* (A Book Apart)\n- Ellen Lupton — *Thinking with Type*\n- Adobe Spectrum — *Color Foundations*\n- Nielsen-Norman — *Table of Contents Best Practices* (2023)\n- research-ops onboarding pattern: `research-ops\u002FCLAUDE.md` §8\n- Brand palette math source: `marketing\u002Flanding\u002Fskills\u002Flanding\u002Fscripts\u002Fbrand_palette_validator.py`\n","# Design System — Onboarding + Shared Brand Tokens\n\nThe design-system skill is the **shared brand owner** for the markdown-html plugin. Run its onboarding once. Every converter (`md-document`, `md-review`, `md-slides`) reads the resulting config via `config_loader.py` and applies the same 12 CSS custom properties to its output. Without this, conversions render with placeholder defaults — technically functional but unbranded.\n\nThis skill ships exactly three Python tools:\n\n1. **`onboard.py`** — interactive (or `--defaults` \u002F `--set` \u002F `--show` \u002F `--reset`) wizard.\n2. **`config_loader.py`** — importable customization loader with project > global > defaults precedence and `MARKDOWN_HTML_NO_CONFIG=1` bypass.\n3. **`brand_palette_validator.py`** — WCAG-AA contrast checker + HSL palette deriver.\n\nAll three are stdlib-only and contain no LLM calls (deterministic per Path-B discipline).\n\n## When to invoke\n\n| Symptom | Action |\n|---|---|\n| User says \"convert this markdown to HTML\" for the first time in this workspace | Run `python3 markdown-html\u002Fskills\u002Fdesign-system\u002Fscripts\u002Fonboard.py` |\n| `~\u002F.config\u002Fmarkdown-html\u002Fdesign-system.json` doesn't exist OR `setup_completed_at` is null | Refuse conversion, surface onboarding |\n| User wants per-repo brand override | `python3 ...\u002Fonboard.py --scope project` |\n| User wants to change a single field non-interactively | `python3 ...\u002Fonboard.py --set brand.primary=#FF6B35` |\n| User wants to reset and re-onboard | `python3 ...\u002Fonboard.py --reset` then re-run |\n| User wants zero-touch defaults (CI, ephemeral session) | `python3 ...\u002Fonboard.py --defaults` |\n| Headless \u002F containerized run that should ignore saved config | `MARKDOWN_HTML_NO_CONFIG=1 ...` |\n\n## Onboarding question set (10 questions)\n\n| # | Key | Choices \u002F Validator | Default |\n|---|---|---|---|\n| 1 | `default_output_dir` | path; `os.access(parent, os.W_OK)` | `.\u002Fmarkdown-html-out\u002F` |\n| 2 | `brand.primary` | HEX `^#?[0-9a-fA-F]{6}$` | `#0A1628` |\n| 3 | `brand.accent` | HEX or blank (auto-derive) | derive from primary |\n| 4 | `typography.heading_font` | Google Font name (12 safe defaults) | `Inter` |\n| 5 | `typography.body_font` | Google Font name | `Inter` |\n| 6 | `design_style` | `editorial \u002F technical \u002F minimal \u002F playful` | `technical` |\n| 7 | `code_theme` | `light \u002F dark \u002F auto` | `auto` |\n| 8 | `toc.behavior` | `sticky-sidebar \u002F collapsible-top \u002F inline \u002F none` | `sticky-sidebar` |\n| 9 | `company_name` | string (may be empty) | `\"\"` |\n| 10 | `logo_url` | URL or empty (base64-embedded at render) | `\"\"` |\n\n## Hard rules\n\n1. **WCAG AA body-text contrast must pass.** `brand_palette_validator.validate()` runs after every change. Body text on bg must reach 4.5:1; link on bg must reach 4.5:1. If either fails, `onboard.py` refuses to save (exit code 4) and tells the user to pick a darker primary, blank `brand.bg`\u002F`brand.text` to let derivation pick a safe pair, or override `brand.text` directly. Canon: WCAG 2.2 §1.4.3.\n2. **Output directory must be writable.** `onboard.py` walks up the path to find an existing ancestor and checks `os.W_OK`. Empty or unwritable path → exit code 3. The orchestrator's `output_path_resolver.py` honors the same rule per-conversion.\n3. **Customization must change behavior, not sit as decoration.** Every consumer (md-document, md-review, md-slides) must read the config and render differently when the user changes `design_style`, `brand.primary`, `code_theme`, or `toc.behavior`. Decorative-only fields fail the design discipline.\n4. **Precedence is fixed.** Project > global > defaults. The deep-merge preserves nested keys (e.g. you can override `brand.primary` in a project config without losing `typography.heading_font` from global).\n5. **Bypass env exists for a reason.** `MARKDOWN_HTML_NO_CONFIG=1` is for headless CI, ephemeral test containers, and the autoresearch-style evaluator loops. Never set it silently for an interactive user.\n\n## Derived 12-token palette\n\nOnce the user's brand is captured, `brand_palette_validator.derive_palette()` produces 12 CSS custom properties stored under `derived_palette` in the same config file. Every converter inlines these into its `\u003Cstyle>` block.\n\n| Token | Purpose | Derivation |\n|---|---|---|\n| `--md-bg` | Document background | Primary if dark, near-neutral if vibrant |\n| `--md-surface` | Card \u002F callout \u002F blockquote background | Bg ± 4-6% luminance |\n| `--md-border` | Hairline dividers, table borders | Bg ± 8-12% luminance |\n| `--md-text` | Body text | Off-white on dark bg, near-black on light bg |\n| `--md-text-muted` | Captions, metadata, footers | `rgba(text, 0.68)` |\n| `--md-accent` | Primary CTA, callout headers, link emphasis | Primary if vibrant, hue-shifted lighter if dark |\n| `--md-accent-soft` | Accent backgrounds, hover states | `rgba(accent, 0.14)` |\n| `--md-code-bg` | Inline code, fenced block bg | Bg ± 4-5% luminance |\n| `--md-link` | Hyperlinks | Iteratively walked to reach 4.5:1 contrast on bg |\n| `--md-link-hover` | Hover state | Link ± 6-8% luminance |\n| `--md-success` | OK \u002F approved \u002F passed | Green anchored, luminance-matched |\n| `--md-warn` | Caution \u002F nit \u002F TODO | Amber anchored, luminance-matched |\n\n## Forcing-question library (Matt Pocock grill-with-docs pattern)\n\nOne question per turn, recommended answer, canon citation.\n\n1. **What's your brand primary color?** Recommended: a HEX you already use in your product or docs — not a stock blue. Canon: Aarron Walter, *Designing for Emotion* (color carries brand affect).\n2. **Should accent be derived or set?** Recommended: derive on first run (hue-shift + lighten produces a coherent companion); set explicitly only if your brand kit specifies one. Canon: Adobe Spectrum, *Color Foundations*.\n3. **Editorial, technical, minimal, or playful?** Recommended: `technical` for engineering specs\u002Freports, `editorial` for long-read narratives, `minimal` for sparse reference docs, `playful` for marketing\u002Flanding content. Canon: Ellen Lupton, *Thinking with Type* (style serves the rhetorical purpose).\n4. **Sticky-sidebar TOC, or inline?** Recommended: `sticky-sidebar` for documents over 800 words, `inline` for short reads. Canon: Nielsen-Norman, *Table of Contents Best Practices* (2023).\n5. **Save to global or per-project?** Recommended: global by default (consistent across your work); use `--scope project` only when this repo has a different brand. Canon: research-ops onboarding pattern, `research-ops\u002FCLAUDE.md` §8.\n\n## Customization in use (worked example)\n\n```bash\n# First-run onboarding (interactive, walks all 10 questions)\npython3 markdown-html\u002Fskills\u002Fdesign-system\u002Fscripts\u002Fonboard.py\n\n# Zero-touch defaults for CI \u002F first-test\npython3 ...\u002Fonboard.py --defaults\n\n# Change just the primary color and design style\npython3 ...\u002Fonboard.py --set brand.primary=#FF6B35 --set design_style=editorial\n\n# Per-repo override\npython3 ...\u002Fonboard.py --scope project --set design_style=minimal\n\n# Reset and re-onboard\npython3 ...\u002Fonboard.py --reset\npython3 ...\u002Fonboard.py\n\n# Inspect the effective config (project > global > defaults)\npython3 ...\u002Fconfig_loader.py --show\npython3 ...\u002Fconfig_loader.py --status\n\n# Bypass saved config (returns DEFAULTS only)\nMARKDOWN_HTML_NO_CONFIG=1 python3 ...\u002Fconfig_loader.py --show\n\n# Spot-check WCAG contrast before committing to a brand\npython3 ...\u002Fbrand_palette_validator.py --primary \"#FF6B35\" --accent \"#00D4AA\"\n```\n\n## Assumptions\n\n1. User has at least one brand HEX they want consistent across their HTML conversions.\n2. User accepts a 1-2 minute one-time setup.\n3. User is OK with Google Fonts as the typography source (CDN, no local font hosting).\n4. WCAG 2.2 AA is the accessibility floor (4.5:1 body, 3:1 large\u002FUI). AAA (7:1) is out of scope.\n\n## Non-goals\n\n- Not a full design-token system (Style Dictionary, Theo). Twelve tokens, not a hundred.\n- Not a custom-font hosting solution. Google Fonts only.\n- Not a dark\u002Flight mode switcher in the converters. `code_theme: auto` handles the prefers-color-scheme case for syntax highlighting; layout palette is single-mode per onboarding.\n- Not an accessibility audit suite (use axe-core \u002F pa11y for that). We enforce contrast only.\n- Does not transform existing CSS — the derived palette is injected into freshly generated HTML.\n\n## Distinct from\n\n- **`marketing\u002Flanding\u002Fskills\u002Flanding\u002Fscripts\u002Fbrand_palette_validator.py`** — that script's `derive_palette()` produces 8 tokens shaped for hero-page rendering (`--navy`, `--teal`, `--card-bg`, `--card-border`). This script produces 12 tokens shaped for document rendering (sticky surface, hairline border, code bg, link, link-hover, success, warn). Same WCAG + HSL math, different token taxonomy.\n- **`research-ops\u002Fskills\u002Fclinical-research\u002Fscripts\u002Fonboard.py`** — same pattern (interactive + `--defaults`\u002F`--set`\u002F`--show`\u002F`--reset`\u002F`--scope`), different question set (clinical alpha\u002Fpower\u002Fdropout vs. brand palette\u002Ftypography\u002Flayout).\n\n## Output artifact\n\n`~\u002F.config\u002Fmarkdown-html\u002Fdesign-system.json` (global) or `.\u002F.markdown-html\u002Fdesign-system.json` (project). JSON schema lives at `assets\u002Fdesign_system_schema.json`.\n\n## Anti-patterns (do not)\n\n- ❌ Skip onboarding and run a converter with placeholder defaults — output looks unbranded.\n- ❌ Pick a vibrant brand primary as `brand.bg` directly (low text contrast). Use it as accent instead.\n- ❌ Set `MARKDOWN_HTML_NO_CONFIG=1` silently for an interactive user — they'll wonder why their tokens disappeared.\n- ❌ Encode brand semantics in `derived_palette` outside the 12-token taxonomy. Add a new token only with a deliberate name + purpose + derivation rule.\n\n## References\n\n- WCAG 2.2 — §1.4.3 (contrast), §1.4.4 (resize), §1.4.11 (non-text contrast)\n- Aarron Walter — *Designing for Emotion* (A Book Apart)\n- Ellen Lupton — *Thinking with Type*\n- Adobe Spectrum — *Color Foundations*\n- Nielsen-Norman — *Table of Contents Best Practices* (2023)\n- research-ops onboarding pattern: `research-ops\u002FCLAUDE.md` §8\n- Brand palette math source: `marketing\u002Flanding\u002Fskills\u002Flanding\u002Fscripts\u002Fbrand_palette_validator.py`\n",{"name":5,"tags":59,"author":67,"license":14,"version":68,"description":7,"compatible_tools":69},[5,60,61,62,63,64,65,66],"brand-palette","wcag","onboarding","customization","markdown-html","css-variables","typography","Alireza Rezvani","2.10.0",[70,71,72,73,74,75],"claude-code","codex-cli","cursor","antigravity","opencode","gemini-cli","main","068c2486ccc0f8d200a3db4d21ec137064eda3b4","skills\u002Fpublic-02-claude-skills-main-gemini-skills-design-system-skill-8e01c868","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing","https:\u002F\u002Fgithub.com\u002FJiayiV","2026-08-25 16:30:52",{"source":8,"skillName":5,"commands":83,"prompt":93,"zipAvailable":94},[84,87,90],{"tool":85,"command":86},"npx","npx skills add JiayiV\u002Fquestion_mixing --skill design-system",{"tool":88,"command":89},"bunx","bunx skills add JiayiV\u002Fquestion_mixing --skill design-system",{"tool":91,"command":92},"pnpm","pnpm dlx skills add JiayiV\u002Fquestion_mixing --skill design-system","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-gemini-skills-design-system-skill-8e01c868\u002FSKILL.md",true,[],[97,122,150,181,208,238],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":54},"01M6NN9PJS9NHWPDG4QP93BP8F","webmcpify","Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for \"webmcpify\", \"add WebMCP\", or \"expose app actions to AI agents\".","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fwebmcpify\u002FSKILL.md",[],[99,104,105,106,107,52,108,109,110,111,112,113,114,115,116,117,118,119,120,121],"github","ai agents","web","notes","browser","https","actions","manifest","inventory","verify","tool","use","ready","unrelated","app","scope","for","webmcp",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":126,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":54},"01M6NN6KZE5RBN6NGHN2WXV1RE","vardoger-analyze","Use when the user asks to personalize the GitHub Copilot CLI assistant, adapt Copilot to their style, use vardoger, or analyze their Copilot CLI conversation history. Reads the local session directory at `~\u002F.copilot\u002Fsession-state\u002F`, extracts recurring preferences and conventions, and writes a fenced personalization block into `~\u002F.copilot\u002Fcopilot-instructions.md`. Runs entirely on the user's machine via the local `vardoger` CLI (`pipx install vardoger`); no network calls and no uploads. Triggers: 'personalize my copilot', 'analyze my copilot history', 'tailor copilot to me', 'run vardoger', 'update my copilot instructions from history', 'make copilot learn my style'.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fvardoger-analyze\u002FSKILL.md",[],[130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149],"vardoger analyze","analyze","directory","cli","github copilot","copilot","run","update","learn","network","my style","install","conversation","me","local","github copilot cli","pipx","my","at","copilot instructions",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":162,"publishedAt":54},"01M6NN3CZGQP3XAJ04BM1NNYGT","transloadit-media-processing","Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS\u002FMP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftransloadit-media-processing\u002FSKILL.md",[156,159],{"categoryNo":157,"categoryName":158,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":160,"categoryName":161,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[163,164,165,166,167,168,169,170,171,172,173,174,175,115,176,177,178,179,120,180],"transloadit media processing","Media","media processing","processing","MCP","mcp server","documents","subtitles","pipeline","ocr","Video","Audio","mp4","images","files","transformation","free","hls",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":190,"publishedAt":54},"01M6NN28E92F9GH4WFYQ2H1Y15","terraform-azurerm-set-diff-analyzer","Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like Application Gateway, Load Balancer, Firewall, Front Door, NSG, and other resources with Set-type attributes that cause spurious diffs due to internal ordering changes.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fterraform-azurerm-set-diff-analyzer\u002FSKILL.md",[187],{"categoryNo":188,"categoryName":189,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[191,51,192,193,194,195,196,197,198,115,199,200,201,202,203,204,205,206,207,120],"terraform","terraform azurerm set diff analyzer","diff","analyzer","diffs","azure","gateway","firewall","only","resource changes","provider","resources","load balancer","attributes","front","load","balancer",{"skillNo":209,"name":210,"nameZh":6,"description":211,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":212,"categories":213,"keywords":221,"publishedAt":54},"01M6NN1QMH2TDYWTH3XY3N5XPV","technical-job-search","Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV\u002Fresume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-job-search\u002FSKILL.md",[214,217,220],{"categoryNo":215,"categoryName":216,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":218,"categoryName":219,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000036","内容创作者",{"categoryNo":31,"categoryName":32,"taxonomyType":28,"taxonomyTypeDesc":29},[222,223,224,225,226,227,228,229,131,230,115,37,231,232,233,234,235,236,120,237],"search","Job Search","technical job search","technical","writing","tasks","email","parsing","interview","engineer","general","activate","do","task","cv","letter",{"skillNo":239,"name":240,"nameZh":6,"description":241,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":242,"categories":243,"keywords":244,"publishedAt":54},"01M6NMZFA67XYS1GS09WT42235","steno-mode","Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says \"steno mode\", \"shorthand mode\", \"compressed responses\", \"token reduction\", \"brief structured output\", or invokes \u002Fsteno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding\u002Ftutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fsteno-mode\u002FSKILL.md",[],[245,246,247,248,249,225,250,115,234,251,252,253,254,255,256,257,258,259,120,260],"steno mode","mode","customer","brief","first","tutorial","teaching","tokens","as","trigger","structured output","machine","output","court","requests","response compression"]