[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7896KVW5GPDS2N8CEYMPNG4":3,"skill-same:01M7896KVW5GPDS2N8CEYMPNG4":56},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":13,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M7896KVW5GPDS2N8CEYMPNG4","token-map",null,"Map an extracted Figma \u002F source-code token bag onto the active OD design system, producing a deterministic mapping the generate stage can consume.","bluesman1971\u002Fopen-design","bluesman1971","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F96430007?v=4","01M788AK0TR13JE8ART2WNQZV6","01M788AK1PVB085AS9SP38WWGK",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fbluesman1971\u002Fopen-design\u002Fblob\u002Fmain\u002Fplugins\u002F_official\u002Fatoms\u002Ftoken-map\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: token-map\ndescription: Map an extracted Figma \u002F source-code token bag onto the active OD design system, producing a deterministic mapping the generate stage can consume.\nod:\n  scenario: figma-migration\n  mode: token-map\n---\n\n# Token map\n\nSpec §10 \u002F §21.3.1: every figma-migration \u002F code-migration run\ncrosses the same boundary — \"the source has its own tokens; the\ntarget uses the active OD design system; we need a deterministic\nmapping\". This atom produces that mapping.\n\n## Inputs\n\n- `figma\u002Ftokens.json` from `figma-extract` (figma-migration), OR\n- `code\u002Ftokens.json` from `design-extract` (code-migration).\n- The active design system DESIGN.md (already injected into the\n  prompt; the atom reads from the staged design-system context).\n\n## Output\n\n```text\nproject-cwd\u002F\n└── token-map\u002F\n    ├── colors.json     # { source: '#hex' | 'tokenName', target: '--ds-token' }[]\n    ├── typography.json # font + size + weight pairings\n    ├── spacing.json    # spacing scale crosswalk\n    ├── unmatched.json  # { source: ..., reason: 'no-target-equivalent' }[]\n    └── meta.json       # { sourceKind: 'figma' | 'code', generatedAt, atomDigest }\n```\n\n`unmatched.json` is the audit list a human reviews; the agent must\nnot invent target tokens silently.\n\n## Semantic token inference\n\nFigma often exports anonymous source names such as `color-3`,\n`paint\u002F17`, or raw `#5B8DEF`. Do not ask the user to rename those\nbefore mapping. First infer the semantic role from usage evidence:\n\n- Node path, component name, instance overrides, variant\u002Fstate labels,\n  frame name, layer name, and nearby text such as `Primary`,\n  `Selected`, `Link`, `Error`, `Focus`, `Nav`, `Button`, or `CTA`.\n- CSS-like position in the rendered tree: background fill, foreground\n  text\u002Ficon, border, divider, overlay, shadow tint, focus ring, status\n  badge, chart series, or brand\u002Faccent treatment.\n- Contrast relationships: a color paired repeatedly with the main\n  canvas is likely foreground; one paired with foreground inside CTA\n  components is likely primary\u002Faccent background; a thin outline around\n  interactive elements is likely border or focus-ring.\n- Reuse topology: a value that appears across primary buttons,\n  selected tabs, and active nav items is stronger evidence for\n  `--ds-color-primary` than a value that appears once in an illustration.\n\nUse that role evidence to choose among existing active design-system\ntokens and to decide whether an anonymous token should be renamed or\nleft unmatched before the executable mapping pass. Keep the on-disk\ntoken-map contract unchanged: the atom still writes the existing bucket\nfiles, `unmatched.json`, and `meta.json` only.\n\nFor example, this is a useful reasoning note for deciding whether\n`color-3` should map to the active primary token:\n\n```jsonc\n{\n  \"source\": \"color-3\",\n  \"value\": \"#5B8DEF\",\n  \"role\": \"primary\",\n  \"targetCandidates\": [\"--ds-color-primary\", \"--ds-color-link\"],\n  \"evidence\": [\n    \"Button\u002FPrimary fill\",\n    \"Selected tab indicator\",\n    \"Link text in Settings frame\"\n  ]\n}\n```\n\nThen map to an active design-system token only when the evidence is\nrole-based, not value-only. If the top candidates are too close to\ncall, or if the evidence points to conflicting roles (`primary` vs\n`link` vs `focus-ring`), leave the source token unmatched using the\nexisting `no-target-equivalent` reason and include the competing\ncandidates in the hint. This keeps automation useful for common\nanonymous-token cases while preserving human review for ambiguous\nbrand decisions.\n\n### Before \u002F after expectation\n\nWithout semantic inference, an anonymous Figma token can only produce\nan uncertain value-level mapping:\n\n```jsonc\n{\n  \"source\": \"color-3\",\n  \"value\": \"#5B8DEF\",\n  \"target\": null,\n  \"reason\": \"no-target-equivalent\"\n}\n```\n\nWith semantic inference, the same token should carry role evidence\nbefore it is accepted:\n\n```jsonc\n{\n  \"source\": \"color-3\",\n  \"value\": \"#5B8DEF\",\n  \"target\": \"--ds-color-primary\",\n  \"via\": \"name\"\n}\n```\n\nThis prompt-only v1 atom does not claim a measured accuracy lift by\nitself. Treat the expected improvement as coverage of previously\nmanual anonymous-token cases when the Figma tree contains enough role\nevidence. Real accuracy numbers require a fixture suite with known\nsource tokens, expected semantic roles, and a before\u002Fafter agent run.\nSee `examples\u002Fsemantic-inference-before-after.json` for a deterministic\nsame-token-batch simulation that compares the old value-level output\nwith the semantic inference output.\n\n## Convergence\n\nThe atom completes when every input token is either mapped or\nexplicitly recorded under `unmatched.json` with a non-empty\n`reason`. The `until` evaluator reads `tokens.unmatched.length === 0`\non strict mode; default is \"soft converge\" (proceed with\n`unmatched.json` populated).\n\n## Anti-patterns the prompt fragment forbids\n\n- Injecting a new token into DESIGN.md without explicit user\n  approval (use a `confirmation` GenUI surface for that).\n- Mapping hex colours by visual proximity alone; perceptual ΔE\n  thresholds belong in the visual-diff evaluator (Phase 7).\n- Collapsing distinct source tokens onto the same target token\n  silently; record collisions in `unmatched.json` with reason\n  `target-collision`.\n\n## Status\n\nReserved id, prompt-only fragment in v1. The deterministic mapping\nalgorithm + DESIGN.md token-extraction helper land in spec §16\nPhase 6 alongside `figma-extract`.\n","# Token map\n\nSpec §10 \u002F §21.3.1: every figma-migration \u002F code-migration run\ncrosses the same boundary — \"the source has its own tokens; the\ntarget uses the active OD design system; we need a deterministic\nmapping\". This atom produces that mapping.\n\n## Inputs\n\n- `figma\u002Ftokens.json` from `figma-extract` (figma-migration), OR\n- `code\u002Ftokens.json` from `design-extract` (code-migration).\n- The active design system DESIGN.md (already injected into the\n  prompt; the atom reads from the staged design-system context).\n\n## Output\n\n```text\nproject-cwd\u002F\n└── token-map\u002F\n    ├── colors.json     # { source: '#hex' | 'tokenName', target: '--ds-token' }[]\n    ├── typography.json # font + size + weight pairings\n    ├── spacing.json    # spacing scale crosswalk\n    ├── unmatched.json  # { source: ..., reason: 'no-target-equivalent' }[]\n    └── meta.json       # { sourceKind: 'figma' | 'code', generatedAt, atomDigest }\n```\n\n`unmatched.json` is the audit list a human reviews; the agent must\nnot invent target tokens silently.\n\n## Semantic token inference\n\nFigma often exports anonymous source names such as `color-3`,\n`paint\u002F17`, or raw `#5B8DEF`. Do not ask the user to rename those\nbefore mapping. First infer the semantic role from usage evidence:\n\n- Node path, component name, instance overrides, variant\u002Fstate labels,\n  frame name, layer name, and nearby text such as `Primary`,\n  `Selected`, `Link`, `Error`, `Focus`, `Nav`, `Button`, or `CTA`.\n- CSS-like position in the rendered tree: background fill, foreground\n  text\u002Ficon, border, divider, overlay, shadow tint, focus ring, status\n  badge, chart series, or brand\u002Faccent treatment.\n- Contrast relationships: a color paired repeatedly with the main\n  canvas is likely foreground; one paired with foreground inside CTA\n  components is likely primary\u002Faccent background; a thin outline around\n  interactive elements is likely border or focus-ring.\n- Reuse topology: a value that appears across primary buttons,\n  selected tabs, and active nav items is stronger evidence for\n  `--ds-color-primary` than a value that appears once in an illustration.\n\nUse that role evidence to choose among existing active design-system\ntokens and to decide whether an anonymous token should be renamed or\nleft unmatched before the executable mapping pass. Keep the on-disk\ntoken-map contract unchanged: the atom still writes the existing bucket\nfiles, `unmatched.json`, and `meta.json` only.\n\nFor example, this is a useful reasoning note for deciding whether\n`color-3` should map to the active primary token:\n\n```jsonc\n{\n  \"source\": \"color-3\",\n  \"value\": \"#5B8DEF\",\n  \"role\": \"primary\",\n  \"targetCandidates\": [\"--ds-color-primary\", \"--ds-color-link\"],\n  \"evidence\": [\n    \"Button\u002FPrimary fill\",\n    \"Selected tab indicator\",\n    \"Link text in Settings frame\"\n  ]\n}\n```\n\nThen map to an active design-system token only when the evidence is\nrole-based, not value-only. If the top candidates are too close to\ncall, or if the evidence points to conflicting roles (`primary` vs\n`link` vs `focus-ring`), leave the source token unmatched using the\nexisting `no-target-equivalent` reason and include the competing\ncandidates in the hint. This keeps automation useful for common\nanonymous-token cases while preserving human review for ambiguous\nbrand decisions.\n\n### Before \u002F after expectation\n\nWithout semantic inference, an anonymous Figma token can only produce\nan uncertain value-level mapping:\n\n```jsonc\n{\n  \"source\": \"color-3\",\n  \"value\": \"#5B8DEF\",\n  \"target\": null,\n  \"reason\": \"no-target-equivalent\"\n}\n```\n\nWith semantic inference, the same token should carry role evidence\nbefore it is accepted:\n\n```jsonc\n{\n  \"source\": \"color-3\",\n  \"value\": \"#5B8DEF\",\n  \"target\": \"--ds-color-primary\",\n  \"via\": \"name\"\n}\n```\n\nThis prompt-only v1 atom does not claim a measured accuracy lift by\nitself. Treat the expected improvement as coverage of previously\nmanual anonymous-token cases when the Figma tree contains enough role\nevidence. Real accuracy numbers require a fixture suite with known\nsource tokens, expected semantic roles, and a before\u002Fafter agent run.\nSee `examples\u002Fsemantic-inference-before-after.json` for a deterministic\nsame-token-batch simulation that compares the old value-level output\nwith the semantic inference output.\n\n## Convergence\n\nThe atom completes when every input token is either mapped or\nexplicitly recorded under `unmatched.json` with a non-empty\n`reason`. The `until` evaluator reads `tokens.unmatched.length === 0`\non strict mode; default is \"soft converge\" (proceed with\n`unmatched.json` populated).\n\n## Anti-patterns the prompt fragment forbids\n\n- Injecting a new token into DESIGN.md without explicit user\n  approval (use a `confirmation` GenUI surface for that).\n- Mapping hex colours by visual proximity alone; perceptual ΔE\n  thresholds belong in the visual-diff evaluator (Phase 7).\n- Collapsing distinct source tokens onto the same target token\n  silently; record collisions in `unmatched.json` with reason\n  `target-collision`.\n\n## Status\n\nReserved id, prompt-only fragment in v1. The deterministic mapping\nalgorithm + DESIGN.md token-extraction helper land in spec §16\nPhase 6 alongside `figma-extract`.\n",{"od":23,"name":5,"description":7},{"mode":5,"scenario":24},"figma-migration","main","0467f0e19df12a6994ec7fb20ff6e9e23cd704e7","plugins\u002F_official\u002Fatoms\u002Ftoken-map","https:\u002F\u002Fgithub.com\u002Fbluesman1971\u002Fopen-design","https:\u002F\u002Fopen-design.ai","https:\u002F\u002Fgithub.com\u002Fbluesman1971","2026-07-09 04:08:20",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add bluesman1971\u002Fopen-design --skill token-map",{"tool":38,"command":39},"bunx","bunx skills add bluesman1971\u002Fopen-design --skill token-map",{"tool":41,"command":42},"pnpm","pnpm dlx skills add bluesman1971\u002Fopen-design --skill token-map","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbluesman1971\u002Fopen-design\u002Fblob\u002Fmain\u002Fplugins\u002F_official\u002Fatoms\u002Ftoken-map\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"examples\u002Fsemantic-inference-before-after.json","REFERENCE","参考文档",4821,"https:\u002F\u002Fgithub.com\u002Fbluesman1971\u002Fopen-design\u002Fblob\u002Fmain\u002Fplugins\u002F_official\u002Fatoms\u002Ftoken-map\u002Fexamples\u002Fsemantic-inference-before-after.json",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"open-design.json",834,"https:\u002F\u002Fgithub.com\u002Fbluesman1971\u002Fopen-design\u002Fblob\u002Fmain\u002Fplugins\u002F_official\u002Fatoms\u002Ftoken-map\u002Fopen-design.json",[57,66,74,81,88,95],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":62,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M78AMRG8NAGKWKNDQE39ZZFQ","web-design-guidelines","Review UI code for Web Interface Guidelines compliance by the Vercel engineering team. Covers layout, typography, color, motion, and accessibility for product UI.","MIT","https:\u002F\u002Fgithub.com\u002Fbluesman1971\u002Fopen-design\u002Fblob\u002Fmain\u002Fskills\u002Fweb-design-guidelines\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fbluesman1971\u002Fopen-design\u002Fblob\u002Fmain\u002Fskills\u002Fweb-design-guidelines\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M78AMKHTFS149JGEYNQM5AXR","web-clone","网站复刻 \u002F 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互\u002FWebGL\u002FCanvas\u002FThree.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树，覆盖静态站 \u002F React-Vue-Next 内容站 \u002F WebGL-Canvas 重前端站三大分支，并强制核对任何 AI 二手分析里的可执行代码。","https:\u002F\u002Fgithub.com\u002Fbluesman1971\u002Fopen-design\u002Fblob\u002Fmain\u002Fskills\u002Fweb-clone\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fbluesman1971\u002Fopen-design\u002Fblob\u002Fmain\u002Fskills\u002Fweb-clone\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M78AMH25JH2SH3AWTRSDCM9F","venice-video","Video generation and transcription workflows via the Venice.ai API.","https:\u002F\u002Fgithub.com\u002Fbluesman1971\u002Fopen-design\u002Fblob\u002Fmain\u002Fskills\u002Fvenice-video\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M78AMF0M4FFKFWXFJ9NHTF5M","venice-image-generate","Image generation endpoints and available styles via the Venice.ai API.","https:\u002F\u002Fgithub.com\u002Fbluesman1971\u002Fopen-design\u002Fblob\u002Fmain\u002Fskills\u002Fvenice-image-generate\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M78AMCH68X46SHNZVD284KXS","threejs","Three.js skills for creating 3D elements and interactive experiences in the browser — scenes, materials, controls, and post-processing.","https:\u002F\u002Fgithub.com\u002Fbluesman1971\u002Fopen-design\u002Fblob\u002Fmain\u002Fskills\u002Fthreejs\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":18},"01M78AM7P8WSBZDNZZ42BQHGK7","taste","Brief-time anti-AI-slop taste checklist — read the room and set the\ndesign dials BEFORE generating a landing page, portfolio, or redesign,\nso the first draft doesn't need a post-generation rescue. Use at the\nstart of a visual\u002Fcreative brief, not after the artifact exists.","https:\u002F\u002Fgithub.com\u002Fbluesman1971\u002Fopen-design\u002Fblob\u002Fmain\u002Fskills\u002Ftaste\u002FSKILL.md",[],[]]