[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79F77A5P09GC5143MTSN46M":3,"skill-same:01M79F77A5P09GC5143MTSN46M":45},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M79F77A5P09GC5143MTSN46M","figma-generate-design",null,"Build\u002Fupdate Figma screens from code\u002Fdescriptions using design system components\u002Ftokens.","BumpyClock\u002Fagent-templates","BumpyClock","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1883824?v=4","01M79EW0FDP9MFXH1FKH800S7T","Aditya Sharma","01M79EW0G27TTKZWTFQ8W5HVB4",2,"MIT","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Ffigma\u002Ffigma-generate-design\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: figma-generate-design\ndescription: \"Build\u002Fupdate Figma screens from code\u002Fdescriptions using design system components\u002Ftokens.\"\ndisable-model-invocation: false\n---\n\n# Build \u002F Update Screens from Design System\n\nUse this skill to create or update full-page screens in Figma by **reusing the published design system** — components, variables, and styles — rather than drawing primitives with hardcoded values. The key insight: the Figma file likely has a published design system with components, color\u002Fspacing variables, and text\u002Feffect styles that correspond to the codebase's UI components and tokens. Find and use those instead of drawing boxes with hex colors.\n\n**MANDATORY**: You MUST also load [figma-use](..\u002Ffigma-use\u002FSKILL.md) before any `use_figma` call. That skill contains critical rules (color ranges, font loading, etc.) that apply to every script you write.\n\n**Always pass `skillNames: \"figma-generate-design\"` when calling `use_figma` as part of this skill.** This is a logging parameter — it does not affect execution.\n\n## Skill Boundaries\n\n- Use this skill when the deliverable is a **Figma screen** (new or updated) composed of design system component instances.\n- If the user wants to generate **code from a Figma design**, switch to [figma-implement-design](..\u002Ffigma-implement-design\u002FSKILL.md).\n- If the user wants to create **new reusable components or variants**, use [figma-use](..\u002Ffigma-use\u002FSKILL.md) directly.\n- If the user wants to write **Code Connect mappings**, switch to [figma-code-connect](..\u002Ffigma-code-connect\u002FSKILL.md).\n\n## Prerequisites\n\n- Figma MCP server must be connected\n- The target Figma file must have a published design system with components (or access to a team library)\n- User should provide either:\n  - A Figma file URL \u002F file key to work in\n  - Or context about which file to target (the agent can discover pages)\n- Source code or description of the screen to build\u002Fupdate\n\n## Parallel Workflow with generate_figma_design (Web Apps Only)\n\nWhen building a screen from a **web app** that can be rendered in a browser, the best results come from running both approaches in parallel:\n\n1. **In parallel:**\n   - Start building the screen using this skill's workflow (use_figma + design system components)\n   - Run `generate_figma_design` to capture a pixel-perfect screenshot of the running web app\n2. **Once both complete:** Update the use_figma output to match the pixel-perfect layout from the `generate_figma_design` capture. The capture provides the exact spacing, sizing, and visual treatment to aim for, while your use_figma output has proper component instances linked to the design system. If the capture contains images, transfer them to your use_figma output by copying `imageHash` values from the capture's image fills (see Step 5 for details).\n3. **Once confirmed looking good:** Delete the `generate_figma_design` output — it was only used as a visual reference.\n\nThis combines the best of both: `generate_figma_design` gives pixel-perfect layout accuracy, while use_figma gives proper design system component instances that stay linked and updatable.\n\n**This parallel workflow is MANDATORY when the source contains images.** The `use_figma` Plugin API cannot fetch external image URLs — it can only set image fills by copying `imageHash` values from nodes already in the file. `generate_figma_design` rasterizes all visible images into Figma, providing the hashes you need. If you skip the capture when images are present, image frames will be left blank.\n\nFor non-web apps (iOS, Android, etc.) or when updating existing screens, use the standard workflow below.\n\n## Required Workflow\n\n**Follow these steps in order. Do not skip steps.**\n\n### Step 1: Understand the Screen\n\nBefore touching Figma, understand what you're building:\n\n1. If building from code, read the relevant source files to understand the page structure, sections, and which components are used.\n2. Identify the major sections of the screen (e.g., Header, Hero, Content Panels, Pricing Grid, FAQ Accordion, Footer).\n3. For each section, list the UI components involved (buttons, inputs, cards, navigation pills, accordions, etc.).\n4. **Check whether the screen contains any images** (e.g., `\u003Cimg>`, `\u003CImage>`, background images, product photos, avatars, icons loaded from URLs). If it does and this is a web app, you **must** run the parallel `generate_figma_design` capture workflow — start it immediately alongside Step 2 so the capture runs while you discover components. See \"Parallel Workflow with generate_figma_design\" above.\n\n### Step 2: Discover Design System — Components, Variables, and Styles\n\nYou need three things from the design system: **components** (buttons, cards, etc.), **variables** (colors, spacing, radii), and **styles** (text styles, effect styles like shadows). Don't hardcode hex colors or pixel values when design system tokens exist.\n\n#### 2a: Discover components\n\n**Preferred: inspect existing screens first.** If the target file already contains screens using the same design system, skip `search_design_system` and inspect existing instances directly. A single `use_figma` call that walks an existing frame's instances gives you an exact, authoritative component map:\n\n```js\nconst frame = figma.currentPage.findOne(n => n.name === \"Existing Screen\");\nconst uniqueSets = new Map();\nframe.findAll(n => n.type === \"INSTANCE\").forEach(inst => {\n  const mc = inst.mainComponent;\n  const cs = mc?.parent?.type === \"COMPONENT_SET\" ? mc.parent : null;\n  const key = cs ? cs.key : mc?.key;\n  const name = cs ? cs.name : mc?.name;\n  if (key && !uniqueSets.has(key)) {\n    uniqueSets.set(key, { name, key, isSet: !!cs, sampleVariant: mc.name });\n  }\n});\nreturn [...uniqueSets.values()];\n```\n\nOnly fall back to `search_design_system` when the file has no existing screens to reference. When using it, **search broadly** — try multiple terms and synonyms (e.g., \"button\", \"input\", \"nav\", \"card\", \"accordion\", \"header\", \"footer\", \"tag\", \"avatar\", \"toggle\", \"icon\", etc.). Use `includeComponents: true` to focus on components.\n\n**Include component properties** in your map — you need to know which TEXT properties each component exposes for text overrides. Create a temporary instance, read its `componentProperties` (and those of nested instances), then remove the temp instance.\n\nExample component map with property info:\n\n```\nComponent Map:\n- Button → key: \"abc123\", type: COMPONENT_SET\n  Properties: { \"Label#2:0\": TEXT, \"Has Icon#4:64\": BOOLEAN }\n- PricingCard → key: \"ghi789\", type: COMPONENT_SET\n  Properties: { \"Device\": VARIANT, \"Variant\": VARIANT }\n  Nested \"Text Heading\" has: { \"Text#2104:5\": TEXT }\n  Nested \"Button\" has: { \"Label#2:0\": TEXT }\n```\n\n#### 2b: Discover variables (colors, spacing, radii)\n\n**Inspect existing screens first** (same as components). Or use `search_design_system` with `includeVariables: true`.\n\n> **WARNING: Two different variable discovery methods — do not confuse them.**\n>\n> - `use_figma` with `figma.variables.getLocalVariableCollectionsAsync()` — returns **only local variables defined in the current file**. If this returns empty, it does **not** mean no variables exist. Remote\u002Fpublished library variables are invisible to this API.\n> - `search_design_system` with `includeVariables: true` — searches across **all linked libraries**, including remote and published ones. This is the correct tool for discovering design system variables.\n>\n> **Never conclude \"no variables exist\" based solely on `getLocalVariableCollectionsAsync()` returning empty.** Always also run `search_design_system` with `includeVariables: true` to check for library variables before deciding to create your own.\n\n**Query strategy:** `search_design_system` matches against **variable names** (e.g., \"Gray\u002Fgray-9\", \"core\u002Fgray\u002F100\", \"space\u002F400\"), not categories. Run multiple short, simple queries in parallel rather than one compound query:\n\n- **Primitive colors:** \"gray\", \"red\", \"blue\", \"green\", \"white\", \"brand\"\n- **Semantic colors:** \"background\", \"foreground\", \"border\", \"surface\", \"text\"\n- **Spacing\u002Fsizing:** \"space\", \"radius\", \"gap\", \"padding\"\n\nIf initial searches return empty, try shorter fragments or different naming conventions — libraries vary widely (\"grey\" vs \"gray\", \"spacing\" vs \"space\", \"color\u002Fbg\" vs \"background\").\n\nInspect an existing screen's bound variables for the most authoritative results:\n\n```js\nconst frame = figma.currentPage.findOne(n => n.name === \"Existing Screen\");\nconst varMap = new Map();\nframe.findAll(() => true).forEach(node => {\n  const bv = node.boundVariables;\n  if (!bv) return;\n  for (const [prop, binding] of Object.entries(bv)) {\n    const bindings = Array.isArray(binding) ? binding : [binding];\n    for (const b of bindings) {\n      if (b?.id && !varMap.has(b.id)) {\n        const v = await figma.variables.getVariableByIdAsync(b.id);\n        if (v) varMap.set(b.id, { name: v.name, id: v.id, key: v.key, type: v.resolvedType, remote: v.remote });\n      }\n    }\n  }\n});\nreturn [...varMap.values()];\n```\n\nFor library variables (remote = true), import them by key with `figma.variables.importVariableByKeyAsync(key)`. For local variables, use `figma.variables.getVariableByIdAsync(id)` directly.\n\nSee [variable-patterns.md](..\u002Ffigma-use\u002Freferences\u002Fvariable-patterns.md) for binding patterns.\n\n#### 2c: Discover styles (text styles, effect styles)\n\nSearch for styles using `search_design_system` with `includeStyles: true` and terms like \"heading\", \"body\", \"shadow\", \"elevation\". Or inspect what an existing screen uses:\n\n```js\nconst frame = figma.currentPage.findOne(n => n.name === \"Existing Screen\");\nconst styles = { text: new Map(), effect: new Map() };\nframe.findAll(() => true).forEach(node => {\n  if ('textStyleId' in node && node.textStyleId) {\n    const s = figma.getStyleById(node.textStyleId);\n    if (s) styles.text.set(s.id, { name: s.name, id: s.id, key: s.key });\n  }\n  if ('effectStyleId' in node && node.effectStyleId) {\n    const s = figma.getStyleById(node.effectStyleId);\n    if (s) styles.effect.set(s.id, { name: s.name, id: s.id, key: s.key });\n  }\n});\nreturn {\n  textStyles: [...styles.text.values()],\n  effectStyles: [...styles.effect.values()]\n};\n```\n\nImport library styles with `figma.importStyleByKeyAsync(key)`, then apply with `node.textStyleId = style.id` or `node.effectStyleId = style.id`.\n\nSee [text-style-patterns.md](..\u002Ffigma-use\u002Freferences\u002Ftext-style-patterns.md) and [effect-style-patterns.md](..\u002Ffigma-use\u002Freferences\u002Feffect-style-patterns.md) for details.\n\n### Step 3: Create the Page Wrapper Frame First\n\n**Do NOT build sections as top-level page children and reparent them later** — moving nodes across `use_figma` calls with `appendChild()` silently fails and produces orphaned frames. Instead, create the wrapper first, then build each section directly inside it.\n\nCreate the page wrapper in its own `use_figma` call. Position it away from existing content and return its ID:\n\n```js\n\u002F\u002F Find clear space\nlet maxX = 0;\nfor (const child of figma.currentPage.children) {\n  maxX = Math.max(maxX, child.x + child.width);\n}\n\nconst wrapper = figma.createAutoLayout(\"VERTICAL\");\nwrapper.name = \"Homepage\";\nwrapper.primaryAxisAlignItems = \"CENTER\";\nwrapper.counterAxisAlignItems = \"CENTER\";\nwrapper.resize(1440, 100);\nwrapper.layoutSizingHorizontal = \"FIXED\";\nwrapper.x = maxX + 200;\nwrapper.y = 0;\n\nreturn { success: true, wrapperId: wrapper.id };\n```\n\n### Step 4: Build Each Section Inside the Wrapper\n\n**This is the most important step.** Build one section at a time, each in its own `use_figma` call. At the start of each script, fetch the wrapper by ID and append new content directly to it.\n\n```js\nconst createdNodeIds = [];\nconst wrapper = await figma.getNodeByIdAsync(\"WRAPPER_ID_FROM_STEP_3\");\n\n\u002F\u002F Import design system components by key\nconst buttonSet = await figma.importComponentSetByKeyAsync(\"BUTTON_SET_KEY\");\nconst primaryButton = buttonSet.children.find(c =>\n  c.type === \"COMPONENT\" && c.name.includes(\"variant=primary\")\n) || buttonSet.defaultVariant;\n\n\u002F\u002F Import design system variables for colors and spacing\nconst bgColorVar = await figma.variables.importVariableByKeyAsync(\"BG_COLOR_VAR_KEY\");\nconst spacingVar = await figma.variables.importVariableByKeyAsync(\"SPACING_VAR_KEY\");\n\n\u002F\u002F Build section frame with variable bindings (not hardcoded values)\nconst section = figma.createAutoLayout();\nsection.name = \"Header\";\nsection.setBoundVariable(\"paddingLeft\", spacingVar);\nsection.setBoundVariable(\"paddingRight\", spacingVar);\nconst bgPaint = figma.variables.setBoundVariableForPaint(\n  { type: 'SOLID', color: { r: 0, g: 0, b: 0 } }, 'color', bgColorVar\n);\nsection.fills = [bgPaint];\n\n\u002F\u002F Import and apply text\u002Feffect styles\nconst shadowStyle = await figma.importStyleByKeyAsync(\"SHADOW_STYLE_KEY\");\nsection.effectStyleId = shadowStyle.id;\n\n\u002F\u002F Create component instances inside the section\nconst btnInstance = primaryButton.createInstance();\nsection.appendChild(btnInstance);\ncreatedNodeIds.push(btnInstance.id);\n\n\u002F\u002F Append section to wrapper\nwrapper.appendChild(section);\nsection.layoutSizingHorizontal = \"FILL\"; \u002F\u002F AFTER appending\n\ncreatedNodeIds.push(section.id);\nreturn { success: true, createdNodeIds };\n```\n\nAfter each section, validate with `get_screenshot` before moving on. Look closely for cropped\u002Fclipped text (line heights cutting off content) and overlapping elements — these are the most common issues and easy to miss at a glance.\n\n#### Override instance text with setProperties()\n\nComponent instances ship with placeholder text (\"Title\", \"Heading\", \"Button\"). Use the component property keys you discovered in Step 2 to override them with `setProperties()` — this is more reliable than direct `node.characters` manipulation. See [component-patterns.md](..\u002Ffigma-use\u002Freferences\u002Fcomponent-patterns.md#overriding-text-in-a-component-instance) for the full pattern.\n\nFor nested instances that expose their own TEXT properties, call `setProperties()` on the nested instance:\n\n```js\nconst nestedHeading = cardInstance.findOne(n => n.type === \"INSTANCE\" && n.name === \"Text Heading\");\nif (nestedHeading) {\n  nestedHeading.setProperties({ \"Text#2104:5\": \"Actual heading from source code\" });\n}\n```\n\nOnly fall back to direct `node.characters` for text that is NOT managed by any component property.\n\n#### Read source code defaults carefully\n\nWhen translating code components to Figma instances, check the component's default prop values in the source code, not just what's explicitly passed. For example, `\u003CButton size=\"small\">Register\u003C\u002FButton>` with no variant prop — check the component definition to find `variant = \"primary\"` as the default. Selecting the wrong variant (e.g., Neutral instead of Primary) produces a visually incorrect result that's easy to miss.\n\n#### What to build manually vs. import from design system\n\n| Build manually | Import from design system |\n|----------------|--------------------------|\n| Page wrapper frame | **Components**: buttons, cards, inputs, nav, etc. |\n| Section container frames | **Variables**: colors (fills, strokes), spacing (padding, gap), radii |\n| Layout grids (rows, columns) | **Text styles**: heading, body, caption, etc. |\n| | **Effect styles**: shadows, blurs, etc. |\n\n**Never hardcode hex colors or pixel spacing** when a design system variable exists. Use `setBoundVariable` for spacing\u002Fradii and `setBoundVariableForPaint` for colors. Apply text styles with `node.textStyleId` and effect styles with `node.effectStyleId`.\n\n### Step 5: Validate the Full Screen and Transfer Images\n\nAfter composing all sections, call `get_screenshot` on the full page frame and compare against the source. Fix any issues with targeted `use_figma` calls — don't rebuild the entire screen.\n\n**Screenshot individual sections, not just the full page.** A full-page screenshot at reduced resolution hides text truncation, wrong colors, and placeholder text that hasn't been overridden. Take a screenshot of each section by node ID to catch:\n- **Cropped\u002Fclipped text** — line heights or frame sizing cutting off descenders, ascenders, or entire lines\n- **Overlapping content** — elements stacking on top of each other due to incorrect sizing or missing auto-layout\n- Placeholder text still showing (\"Title\", \"Heading\", \"Button\")\n- Truncated content from layout sizing bugs\n- Wrong component variants (e.g., Neutral vs Primary button)\n- **Blank image placeholders** — if images are missing, you need to transfer them from the `generate_figma_design` capture (see below)\n\n#### Transfer images from the generate_figma_design capture\n\nIf you ran `generate_figma_design` in parallel (mandatory when the source contains images), transfer the captured images into your design system output:\n\n1. Find all image nodes in the capture output by searching for fills with `type === \"IMAGE\"`:\n   ```js\n   const capture = await figma.getNodeByIdAsync(\"CAPTURE_NODE_ID\");\n   const imageNodes = [];\n   capture.findAll(n => {\n     if (n.fills && Array.isArray(n.fills)) {\n       for (const fill of n.fills) {\n         if (fill.type === \"IMAGE\") {\n           imageNodes.push({ name: n.name, id: n.id, imageHash: fill.imageHash });\n           return true;\n         }\n       }\n     }\n     return false;\n   });\n   return imageNodes;\n   ```\n2. Match each captured image to the corresponding frame in your use_figma output (by position, name, or order).\n3. Apply the image hash to the target frame:\n   ```js\n   targetFrame.fills = [{ type: \"IMAGE\", imageHash: \"hash_from_capture\", scaleMode: \"FILL\" }];\n   ```\n4. Delete the `generate_figma_design` capture output after all images are transferred.\n\n### Step 6: Updating an Existing Screen\n\nWhen updating rather than creating from scratch:\n\n1. Use `get_metadata` to inspect the existing screen structure.\n2. Identify which sections need updating and which can stay.\n3. For each section that needs changes:\n   - Locate the existing nodes by ID or name\n   - Swap component instances if the design system component changed\n   - Update text content, variant properties, or layout as needed\n   - Remove deprecated sections\n   - Add new sections\n4. Validate with `get_screenshot` after each modification.\n\n```js\n\u002F\u002F Example: Swap a button variant in an existing screen\nconst existingButton = await figma.getNodeByIdAsync(\"EXISTING_BUTTON_INSTANCE_ID\");\nif (existingButton && existingButton.type === \"INSTANCE\") {\n  \u002F\u002F Import the updated component\n  const buttonSet = await figma.importComponentSetByKeyAsync(\"BUTTON_SET_KEY\");\n  const newVariant = buttonSet.children.find(c =>\n    c.name.includes(\"variant=primary\") && c.name.includes(\"size=lg\")\n  ) || buttonSet.defaultVariant;\n  existingButton.swapComponent(newVariant);\n}\nreturn { success: true, mutatedNodeIds: [existingButton.id] };\n```\n\n## Reference Docs\n\nFor detailed API patterns and gotchas, load these from the [figma-use](..\u002Ffigma-use\u002FSKILL.md) references as needed:\n\n- [component-patterns.md](..\u002Ffigma-use\u002Freferences\u002Fcomponent-patterns.md) — importing by key, finding variants, setProperties, text overrides, working with instances\n- [variable-patterns.md](..\u002Ffigma-use\u002Freferences\u002Fvariable-patterns.md) — creating\u002Fbinding variables, importing library variables, scopes, aliasing, discovering existing variables\n- [text-style-patterns.md](..\u002Ffigma-use\u002Freferences\u002Ftext-style-patterns.md) — creating\u002Fapplying text styles, importing library text styles, type ramps\n- [effect-style-patterns.md](..\u002Ffigma-use\u002Freferences\u002Feffect-style-patterns.md) — creating\u002Fapplying effect styles (shadows), importing library effect styles\n- [gotchas.md](..\u002Ffigma-use\u002Freferences\u002Fgotchas.md) — layout pitfalls (HUG\u002FFILL interactions, counterAxisAlignItems, sizing order), paint\u002Fcolor issues, page context resets\n\n## Error Recovery\n\nFollow the error recovery process from [figma-use](..\u002Ffigma-use\u002FSKILL.md#6-error-recovery--self-correction):\n\n1. **STOP** on error — do not retry immediately.\n2. **Read the error message carefully** to understand what went wrong.\n3. If the error is unclear, call `get_metadata` or `get_screenshot` to inspect the current file state.\n4. **Fix the script** based on the error message.\n5. **Retry** the corrected script — this is safe because failed scripts are atomic (nothing is created if a script errors).\n\nBecause this skill works incrementally (one section per call), errors are naturally scoped to a single section. Previous sections from successful calls remain intact.\n\n## Best Practices\n\n- **Always search before building.** The design system likely has the component, variable, or style you need. Manual construction and hardcoded values should be the exception, not the rule.\n- **Search broadly.** Try synonyms and partial terms. A \"NavigationPill\" might be found under \"pill\", \"nav\", \"tab\", or \"chip\". For variables, search \"color\", \"spacing\", \"radius\", etc.\n- **Prefer design system tokens over hardcoded values.** Use variable bindings for colors, spacing, and radii. Use text styles for typography. Use effect styles for shadows. This keeps the screen linked to the design system.\n- **Prefer component instances over manual builds.** Instances stay linked to the source component and update automatically when the design system evolves.\n- **Work section by section.** Never build more than one major section per `use_figma` call.\n- **Return node IDs from every call.** You'll need them to compose sections and for error recovery.\n- **Validate visually after each section.** Use `get_screenshot` to catch issues early.\n- **Match existing conventions.** If the file already has screens, match their naming, sizing, and layout patterns.\n","# Build \u002F Update Screens from Design System\n\nUse this skill to create or update full-page screens in Figma by **reusing the published design system** — components, variables, and styles — rather than drawing primitives with hardcoded values. The key insight: the Figma file likely has a published design system with components, color\u002Fspacing variables, and text\u002Feffect styles that correspond to the codebase's UI components and tokens. Find and use those instead of drawing boxes with hex colors.\n\n**MANDATORY**: You MUST also load [figma-use](..\u002Ffigma-use\u002FSKILL.md) before any `use_figma` call. That skill contains critical rules (color ranges, font loading, etc.) that apply to every script you write.\n\n**Always pass `skillNames: \"figma-generate-design\"` when calling `use_figma` as part of this skill.** This is a logging parameter — it does not affect execution.\n\n## Skill Boundaries\n\n- Use this skill when the deliverable is a **Figma screen** (new or updated) composed of design system component instances.\n- If the user wants to generate **code from a Figma design**, switch to [figma-implement-design](..\u002Ffigma-implement-design\u002FSKILL.md).\n- If the user wants to create **new reusable components or variants**, use [figma-use](..\u002Ffigma-use\u002FSKILL.md) directly.\n- If the user wants to write **Code Connect mappings**, switch to [figma-code-connect](..\u002Ffigma-code-connect\u002FSKILL.md).\n\n## Prerequisites\n\n- Figma MCP server must be connected\n- The target Figma file must have a published design system with components (or access to a team library)\n- User should provide either:\n  - A Figma file URL \u002F file key to work in\n  - Or context about which file to target (the agent can discover pages)\n- Source code or description of the screen to build\u002Fupdate\n\n## Parallel Workflow with generate_figma_design (Web Apps Only)\n\nWhen building a screen from a **web app** that can be rendered in a browser, the best results come from running both approaches in parallel:\n\n1. **In parallel:**\n   - Start building the screen using this skill's workflow (use_figma + design system components)\n   - Run `generate_figma_design` to capture a pixel-perfect screenshot of the running web app\n2. **Once both complete:** Update the use_figma output to match the pixel-perfect layout from the `generate_figma_design` capture. The capture provides the exact spacing, sizing, and visual treatment to aim for, while your use_figma output has proper component instances linked to the design system. If the capture contains images, transfer them to your use_figma output by copying `imageHash` values from the capture's image fills (see Step 5 for details).\n3. **Once confirmed looking good:** Delete the `generate_figma_design` output — it was only used as a visual reference.\n\nThis combines the best of both: `generate_figma_design` gives pixel-perfect layout accuracy, while use_figma gives proper design system component instances that stay linked and updatable.\n\n**This parallel workflow is MANDATORY when the source contains images.** The `use_figma` Plugin API cannot fetch external image URLs — it can only set image fills by copying `imageHash` values from nodes already in the file. `generate_figma_design` rasterizes all visible images into Figma, providing the hashes you need. If you skip the capture when images are present, image frames will be left blank.\n\nFor non-web apps (iOS, Android, etc.) or when updating existing screens, use the standard workflow below.\n\n## Required Workflow\n\n**Follow these steps in order. Do not skip steps.**\n\n### Step 1: Understand the Screen\n\nBefore touching Figma, understand what you're building:\n\n1. If building from code, read the relevant source files to understand the page structure, sections, and which components are used.\n2. Identify the major sections of the screen (e.g., Header, Hero, Content Panels, Pricing Grid, FAQ Accordion, Footer).\n3. For each section, list the UI components involved (buttons, inputs, cards, navigation pills, accordions, etc.).\n4. **Check whether the screen contains any images** (e.g., `\u003Cimg>`, `\u003CImage>`, background images, product photos, avatars, icons loaded from URLs). If it does and this is a web app, you **must** run the parallel `generate_figma_design` capture workflow — start it immediately alongside Step 2 so the capture runs while you discover components. See \"Parallel Workflow with generate_figma_design\" above.\n\n### Step 2: Discover Design System — Components, Variables, and Styles\n\nYou need three things from the design system: **components** (buttons, cards, etc.), **variables** (colors, spacing, radii), and **styles** (text styles, effect styles like shadows). Don't hardcode hex colors or pixel values when design system tokens exist.\n\n#### 2a: Discover components\n\n**Preferred: inspect existing screens first.** If the target file already contains screens using the same design system, skip `search_design_system` and inspect existing instances directly. A single `use_figma` call that walks an existing frame's instances gives you an exact, authoritative component map:\n\n```js\nconst frame = figma.currentPage.findOne(n => n.name === \"Existing Screen\");\nconst uniqueSets = new Map();\nframe.findAll(n => n.type === \"INSTANCE\").forEach(inst => {\n  const mc = inst.mainComponent;\n  const cs = mc?.parent?.type === \"COMPONENT_SET\" ? mc.parent : null;\n  const key = cs ? cs.key : mc?.key;\n  const name = cs ? cs.name : mc?.name;\n  if (key && !uniqueSets.has(key)) {\n    uniqueSets.set(key, { name, key, isSet: !!cs, sampleVariant: mc.name });\n  }\n});\nreturn [...uniqueSets.values()];\n```\n\nOnly fall back to `search_design_system` when the file has no existing screens to reference. When using it, **search broadly** — try multiple terms and synonyms (e.g., \"button\", \"input\", \"nav\", \"card\", \"accordion\", \"header\", \"footer\", \"tag\", \"avatar\", \"toggle\", \"icon\", etc.). Use `includeComponents: true` to focus on components.\n\n**Include component properties** in your map — you need to know which TEXT properties each component exposes for text overrides. Create a temporary instance, read its `componentProperties` (and those of nested instances), then remove the temp instance.\n\nExample component map with property info:\n\n```\nComponent Map:\n- Button → key: \"abc123\", type: COMPONENT_SET\n  Properties: { \"Label#2:0\": TEXT, \"Has Icon#4:64\": BOOLEAN }\n- PricingCard → key: \"ghi789\", type: COMPONENT_SET\n  Properties: { \"Device\": VARIANT, \"Variant\": VARIANT }\n  Nested \"Text Heading\" has: { \"Text#2104:5\": TEXT }\n  Nested \"Button\" has: { \"Label#2:0\": TEXT }\n```\n\n#### 2b: Discover variables (colors, spacing, radii)\n\n**Inspect existing screens first** (same as components). Or use `search_design_system` with `includeVariables: true`.\n\n> **WARNING: Two different variable discovery methods — do not confuse them.**\n>\n> - `use_figma` with `figma.variables.getLocalVariableCollectionsAsync()` — returns **only local variables defined in the current file**. If this returns empty, it does **not** mean no variables exist. Remote\u002Fpublished library variables are invisible to this API.\n> - `search_design_system` with `includeVariables: true` — searches across **all linked libraries**, including remote and published ones. This is the correct tool for discovering design system variables.\n>\n> **Never conclude \"no variables exist\" based solely on `getLocalVariableCollectionsAsync()` returning empty.** Always also run `search_design_system` with `includeVariables: true` to check for library variables before deciding to create your own.\n\n**Query strategy:** `search_design_system` matches against **variable names** (e.g., \"Gray\u002Fgray-9\", \"core\u002Fgray\u002F100\", \"space\u002F400\"), not categories. Run multiple short, simple queries in parallel rather than one compound query:\n\n- **Primitive colors:** \"gray\", \"red\", \"blue\", \"green\", \"white\", \"brand\"\n- **Semantic colors:** \"background\", \"foreground\", \"border\", \"surface\", \"text\"\n- **Spacing\u002Fsizing:** \"space\", \"radius\", \"gap\", \"padding\"\n\nIf initial searches return empty, try shorter fragments or different naming conventions — libraries vary widely (\"grey\" vs \"gray\", \"spacing\" vs \"space\", \"color\u002Fbg\" vs \"background\").\n\nInspect an existing screen's bound variables for the most authoritative results:\n\n```js\nconst frame = figma.currentPage.findOne(n => n.name === \"Existing Screen\");\nconst varMap = new Map();\nframe.findAll(() => true).forEach(node => {\n  const bv = node.boundVariables;\n  if (!bv) return;\n  for (const [prop, binding] of Object.entries(bv)) {\n    const bindings = Array.isArray(binding) ? binding : [binding];\n    for (const b of bindings) {\n      if (b?.id && !varMap.has(b.id)) {\n        const v = await figma.variables.getVariableByIdAsync(b.id);\n        if (v) varMap.set(b.id, { name: v.name, id: v.id, key: v.key, type: v.resolvedType, remote: v.remote });\n      }\n    }\n  }\n});\nreturn [...varMap.values()];\n```\n\nFor library variables (remote = true), import them by key with `figma.variables.importVariableByKeyAsync(key)`. For local variables, use `figma.variables.getVariableByIdAsync(id)` directly.\n\nSee [variable-patterns.md](..\u002Ffigma-use\u002Freferences\u002Fvariable-patterns.md) for binding patterns.\n\n#### 2c: Discover styles (text styles, effect styles)\n\nSearch for styles using `search_design_system` with `includeStyles: true` and terms like \"heading\", \"body\", \"shadow\", \"elevation\". Or inspect what an existing screen uses:\n\n```js\nconst frame = figma.currentPage.findOne(n => n.name === \"Existing Screen\");\nconst styles = { text: new Map(), effect: new Map() };\nframe.findAll(() => true).forEach(node => {\n  if ('textStyleId' in node && node.textStyleId) {\n    const s = figma.getStyleById(node.textStyleId);\n    if (s) styles.text.set(s.id, { name: s.name, id: s.id, key: s.key });\n  }\n  if ('effectStyleId' in node && node.effectStyleId) {\n    const s = figma.getStyleById(node.effectStyleId);\n    if (s) styles.effect.set(s.id, { name: s.name, id: s.id, key: s.key });\n  }\n});\nreturn {\n  textStyles: [...styles.text.values()],\n  effectStyles: [...styles.effect.values()]\n};\n```\n\nImport library styles with `figma.importStyleByKeyAsync(key)`, then apply with `node.textStyleId = style.id` or `node.effectStyleId = style.id`.\n\nSee [text-style-patterns.md](..\u002Ffigma-use\u002Freferences\u002Ftext-style-patterns.md) and [effect-style-patterns.md](..\u002Ffigma-use\u002Freferences\u002Feffect-style-patterns.md) for details.\n\n### Step 3: Create the Page Wrapper Frame First\n\n**Do NOT build sections as top-level page children and reparent them later** — moving nodes across `use_figma` calls with `appendChild()` silently fails and produces orphaned frames. Instead, create the wrapper first, then build each section directly inside it.\n\nCreate the page wrapper in its own `use_figma` call. Position it away from existing content and return its ID:\n\n```js\n\u002F\u002F Find clear space\nlet maxX = 0;\nfor (const child of figma.currentPage.children) {\n  maxX = Math.max(maxX, child.x + child.width);\n}\n\nconst wrapper = figma.createAutoLayout(\"VERTICAL\");\nwrapper.name = \"Homepage\";\nwrapper.primaryAxisAlignItems = \"CENTER\";\nwrapper.counterAxisAlignItems = \"CENTER\";\nwrapper.resize(1440, 100);\nwrapper.layoutSizingHorizontal = \"FIXED\";\nwrapper.x = maxX + 200;\nwrapper.y = 0;\n\nreturn { success: true, wrapperId: wrapper.id };\n```\n\n### Step 4: Build Each Section Inside the Wrapper\n\n**This is the most important step.** Build one section at a time, each in its own `use_figma` call. At the start of each script, fetch the wrapper by ID and append new content directly to it.\n\n```js\nconst createdNodeIds = [];\nconst wrapper = await figma.getNodeByIdAsync(\"WRAPPER_ID_FROM_STEP_3\");\n\n\u002F\u002F Import design system components by key\nconst buttonSet = await figma.importComponentSetByKeyAsync(\"BUTTON_SET_KEY\");\nconst primaryButton = buttonSet.children.find(c =>\n  c.type === \"COMPONENT\" && c.name.includes(\"variant=primary\")\n) || buttonSet.defaultVariant;\n\n\u002F\u002F Import design system variables for colors and spacing\nconst bgColorVar = await figma.variables.importVariableByKeyAsync(\"BG_COLOR_VAR_KEY\");\nconst spacingVar = await figma.variables.importVariableByKeyAsync(\"SPACING_VAR_KEY\");\n\n\u002F\u002F Build section frame with variable bindings (not hardcoded values)\nconst section = figma.createAutoLayout();\nsection.name = \"Header\";\nsection.setBoundVariable(\"paddingLeft\", spacingVar);\nsection.setBoundVariable(\"paddingRight\", spacingVar);\nconst bgPaint = figma.variables.setBoundVariableForPaint(\n  { type: 'SOLID', color: { r: 0, g: 0, b: 0 } }, 'color', bgColorVar\n);\nsection.fills = [bgPaint];\n\n\u002F\u002F Import and apply text\u002Feffect styles\nconst shadowStyle = await figma.importStyleByKeyAsync(\"SHADOW_STYLE_KEY\");\nsection.effectStyleId = shadowStyle.id;\n\n\u002F\u002F Create component instances inside the section\nconst btnInstance = primaryButton.createInstance();\nsection.appendChild(btnInstance);\ncreatedNodeIds.push(btnInstance.id);\n\n\u002F\u002F Append section to wrapper\nwrapper.appendChild(section);\nsection.layoutSizingHorizontal = \"FILL\"; \u002F\u002F AFTER appending\n\ncreatedNodeIds.push(section.id);\nreturn { success: true, createdNodeIds };\n```\n\nAfter each section, validate with `get_screenshot` before moving on. Look closely for cropped\u002Fclipped text (line heights cutting off content) and overlapping elements — these are the most common issues and easy to miss at a glance.\n\n#### Override instance text with setProperties()\n\nComponent instances ship with placeholder text (\"Title\", \"Heading\", \"Button\"). Use the component property keys you discovered in Step 2 to override them with `setProperties()` — this is more reliable than direct `node.characters` manipulation. See [component-patterns.md](..\u002Ffigma-use\u002Freferences\u002Fcomponent-patterns.md#overriding-text-in-a-component-instance) for the full pattern.\n\nFor nested instances that expose their own TEXT properties, call `setProperties()` on the nested instance:\n\n```js\nconst nestedHeading = cardInstance.findOne(n => n.type === \"INSTANCE\" && n.name === \"Text Heading\");\nif (nestedHeading) {\n  nestedHeading.setProperties({ \"Text#2104:5\": \"Actual heading from source code\" });\n}\n```\n\nOnly fall back to direct `node.characters` for text that is NOT managed by any component property.\n\n#### Read source code defaults carefully\n\nWhen translating code components to Figma instances, check the component's default prop values in the source code, not just what's explicitly passed. For example, `\u003CButton size=\"small\">Register\u003C\u002FButton>` with no variant prop — check the component definition to find `variant = \"primary\"` as the default. Selecting the wrong variant (e.g., Neutral instead of Primary) produces a visually incorrect result that's easy to miss.\n\n#### What to build manually vs. import from design system\n\n| Build manually | Import from design system |\n|----------------|--------------------------|\n| Page wrapper frame | **Components**: buttons, cards, inputs, nav, etc. |\n| Section container frames | **Variables**: colors (fills, strokes), spacing (padding, gap), radii |\n| Layout grids (rows, columns) | **Text styles**: heading, body, caption, etc. |\n| | **Effect styles**: shadows, blurs, etc. |\n\n**Never hardcode hex colors or pixel spacing** when a design system variable exists. Use `setBoundVariable` for spacing\u002Fradii and `setBoundVariableForPaint` for colors. Apply text styles with `node.textStyleId` and effect styles with `node.effectStyleId`.\n\n### Step 5: Validate the Full Screen and Transfer Images\n\nAfter composing all sections, call `get_screenshot` on the full page frame and compare against the source. Fix any issues with targeted `use_figma` calls — don't rebuild the entire screen.\n\n**Screenshot individual sections, not just the full page.** A full-page screenshot at reduced resolution hides text truncation, wrong colors, and placeholder text that hasn't been overridden. Take a screenshot of each section by node ID to catch:\n- **Cropped\u002Fclipped text** — line heights or frame sizing cutting off descenders, ascenders, or entire lines\n- **Overlapping content** — elements stacking on top of each other due to incorrect sizing or missing auto-layout\n- Placeholder text still showing (\"Title\", \"Heading\", \"Button\")\n- Truncated content from layout sizing bugs\n- Wrong component variants (e.g., Neutral vs Primary button)\n- **Blank image placeholders** — if images are missing, you need to transfer them from the `generate_figma_design` capture (see below)\n\n#### Transfer images from the generate_figma_design capture\n\nIf you ran `generate_figma_design` in parallel (mandatory when the source contains images), transfer the captured images into your design system output:\n\n1. Find all image nodes in the capture output by searching for fills with `type === \"IMAGE\"`:\n   ```js\n   const capture = await figma.getNodeByIdAsync(\"CAPTURE_NODE_ID\");\n   const imageNodes = [];\n   capture.findAll(n => {\n     if (n.fills && Array.isArray(n.fills)) {\n       for (const fill of n.fills) {\n         if (fill.type === \"IMAGE\") {\n           imageNodes.push({ name: n.name, id: n.id, imageHash: fill.imageHash });\n           return true;\n         }\n       }\n     }\n     return false;\n   });\n   return imageNodes;\n   ```\n2. Match each captured image to the corresponding frame in your use_figma output (by position, name, or order).\n3. Apply the image hash to the target frame:\n   ```js\n   targetFrame.fills = [{ type: \"IMAGE\", imageHash: \"hash_from_capture\", scaleMode: \"FILL\" }];\n   ```\n4. Delete the `generate_figma_design` capture output after all images are transferred.\n\n### Step 6: Updating an Existing Screen\n\nWhen updating rather than creating from scratch:\n\n1. Use `get_metadata` to inspect the existing screen structure.\n2. Identify which sections need updating and which can stay.\n3. For each section that needs changes:\n   - Locate the existing nodes by ID or name\n   - Swap component instances if the design system component changed\n   - Update text content, variant properties, or layout as needed\n   - Remove deprecated sections\n   - Add new sections\n4. Validate with `get_screenshot` after each modification.\n\n```js\n\u002F\u002F Example: Swap a button variant in an existing screen\nconst existingButton = await figma.getNodeByIdAsync(\"EXISTING_BUTTON_INSTANCE_ID\");\nif (existingButton && existingButton.type === \"INSTANCE\") {\n  \u002F\u002F Import the updated component\n  const buttonSet = await figma.importComponentSetByKeyAsync(\"BUTTON_SET_KEY\");\n  const newVariant = buttonSet.children.find(c =>\n    c.name.includes(\"variant=primary\") && c.name.includes(\"size=lg\")\n  ) || buttonSet.defaultVariant;\n  existingButton.swapComponent(newVariant);\n}\nreturn { success: true, mutatedNodeIds: [existingButton.id] };\n```\n\n## Reference Docs\n\nFor detailed API patterns and gotchas, load these from the [figma-use](..\u002Ffigma-use\u002FSKILL.md) references as needed:\n\n- [component-patterns.md](..\u002Ffigma-use\u002Freferences\u002Fcomponent-patterns.md) — importing by key, finding variants, setProperties, text overrides, working with instances\n- [variable-patterns.md](..\u002Ffigma-use\u002Freferences\u002Fvariable-patterns.md) — creating\u002Fbinding variables, importing library variables, scopes, aliasing, discovering existing variables\n- [text-style-patterns.md](..\u002Ffigma-use\u002Freferences\u002Ftext-style-patterns.md) — creating\u002Fapplying text styles, importing library text styles, type ramps\n- [effect-style-patterns.md](..\u002Ffigma-use\u002Freferences\u002Feffect-style-patterns.md) — creating\u002Fapplying effect styles (shadows), importing library effect styles\n- [gotchas.md](..\u002Ffigma-use\u002Freferences\u002Fgotchas.md) — layout pitfalls (HUG\u002FFILL interactions, counterAxisAlignItems, sizing order), paint\u002Fcolor issues, page context resets\n\n## Error Recovery\n\nFollow the error recovery process from [figma-use](..\u002Ffigma-use\u002FSKILL.md#6-error-recovery--self-correction):\n\n1. **STOP** on error — do not retry immediately.\n2. **Read the error message carefully** to understand what went wrong.\n3. If the error is unclear, call `get_metadata` or `get_screenshot` to inspect the current file state.\n4. **Fix the script** based on the error message.\n5. **Retry** the corrected script — this is safe because failed scripts are atomic (nothing is created if a script errors).\n\nBecause this skill works incrementally (one section per call), errors are naturally scoped to a single section. Previous sections from successful calls remain intact.\n\n## Best Practices\n\n- **Always search before building.** The design system likely has the component, variable, or style you need. Manual construction and hardcoded values should be the exception, not the rule.\n- **Search broadly.** Try synonyms and partial terms. A \"NavigationPill\" might be found under \"pill\", \"nav\", \"tab\", or \"chip\". For variables, search \"color\", \"spacing\", \"radius\", etc.\n- **Prefer design system tokens over hardcoded values.** Use variable bindings for colors, spacing, and radii. Use text styles for typography. Use effect styles for shadows. This keeps the screen linked to the design system.\n- **Prefer component instances over manual builds.** Instances stay linked to the source component and update automatically when the design system evolves.\n- **Work section by section.** Never build more than one major section per `use_figma` call.\n- **Return node IDs from every call.** You'll need them to compose sections and for error recovery.\n- **Validate visually after each section.** Use `get_screenshot` to catch issues early.\n- **Match existing conventions.** If the file already has screens, match their naming, sizing, and layout patterns.\n",{"name":5,"description":7,"disable-model-invocation":20},"main","e24b64bdac040ad169ed16b14853eff1b20cd726","skills_archive\u002Ffigma\u002Ffigma-generate-design",0,"https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates","https:\u002F\u002Fgithub.com\u002FBumpyClock","2026-11-14 03:12:06",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add BumpyClock\u002Fagent-templates --skill figma-generate-design",{"tool":37,"command":38},"bunx","bunx skills add BumpyClock\u002Fagent-templates --skill figma-generate-design",{"tool":40,"command":41},"pnpm","pnpm dlx skills add BumpyClock\u002Fagent-templates --skill figma-generate-design","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Ffigma\u002Ffigma-generate-design\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M79FEE6E257MWVEBY43X0NVN","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M79FEB8GTJC6ZHDK67T40R20","workflow-from-chats","Extract preferences from agent chats → skills, rules, workflow docs. For learning preferences, mining feedback, personalizing workflows.","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fworkflow-from-chats\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M79FE7TMNGVZZ0M8NV4N0X6N","winui3-csharp-app","WinUI 3 \u002F Windows App SDK desktop apps in C#\u002FXAML. MVVM, bindings, navigation, Mica\u002FAcrylic, windowing, packaging, performance.","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fwinui3-csharp-app\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M79FE31HY46BHN67CQGB7MVJ","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M79FE0N7MGWDG8SCD60FWTV5","what-did-i-get-done","Summarize authored commits over a user-specified time period into a concise status update.","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fwhat-did-i-get-done\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M79FDYBJG9QNCQC0MMVBDT80","weekly-review","Produce a short weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work.","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fweekly-review\u002FSKILL.md",[],[]]