[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AT7W3DCCM4RCT7EGFTD1CD":3,"skill-same:01M7AT7W3DCCM4RCT7EGFTD1CD":65},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M7AT7W3DCCM4RCT7EGFTD1CD","stitch::generate-design",null,"Generate new screens from text prompts or images, edit existing screens with prompts and design system tokens, and generate design variants using Stitch MCP. Includes prompt enhancement pipeline, design mappings, professional UI\u002FUX terminology, design tokens and theme system capabilities.","mahik504\u002Forchestra-workflow","mahik504","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F184419817?v=4","01M7ASS7EBZ4GXTN2C42N8CJ8T","Mahaveer Singh Gehlot","01M7ASS7EYYYXDMCST6D918XPS",1,"MIT","https:\u002F\u002Fgithub.com\u002Fmahik504\u002Forchestra-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fstitch-generate-design\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: stitch::generate-design\ndescription: >-\n  Generate new screens from text prompts or images, edit existing screens\n  with prompts and design system tokens, and generate design variants using\n  Stitch MCP. Includes prompt enhancement pipeline, design mappings, professional\n  UI\u002FUX terminology, design tokens and theme system capabilities.\nallowed-tools:\n  - \"stitch*:*\"\n  - \"Bash\"\n  - \"Read\"\n  - \"Write\"\n  - \"web_fetch\"\n---\n\n# Generate Design\n\nCreate new design screens from text descriptions, images, or mockups, edit\nexisting screens with prompts and design system tokens, and generate design\nvariants using Stitch MCP.\n\n> [!NOTE]\n> Refer to your system prompt for instruction on handling MCP tool prefixes for\n> all tools mentioned in this skill (e.g., `list_projects`,\n> `generate_screen_from_text`, `edit_screens`).\n\n## 🎨 Prompt Enhancement Pipeline\n\nBefore calling any Stitch generation or editing tool, you MUST enhance the\nuser's prompt.\n\n### 1. Analyze Context\n\n- **Project**: Use `list_projects` to find the correct `projectId`. If no\n  suitable project exists, create one using `create_project`.\n- **Design System**: Check if a design system exists for the project via\n  `list_design_systems`. If one exists, design tokens (colors, fonts, roundness)\n  are already applied at the project level — do NOT include any color, font, or\n  theme instructions in the generation prompt. If none exists, delegate to the\n  **manage-design-system** skill first before generating screens.\n\n### 2. Refine UI\u002FUX Terminology\n\nConsult [Design Mappings](references\u002Fdesign-mappings.md) to replace vague terms.\n\n- Vague: \"Make a nice header\"\n- Professional: \"Sticky navigation bar with glassmorphism effect and centered\n  logo\"\n\nUse [Prompting Keywords](references\u002Fprompt-keywords.md) for component names,\nadjective palettes, color roles, and shape descriptions.\n\n### 3. Structure the Final Prompt\n\nFormat the enhanced prompt for Stitch. Focus exclusively on **layout, content,\nand structure** — never include colors, fonts, or theme instructions (these are\nhandled by the manage-design-system skill at the project level).\n\nFor **new screens**, use this template:\n\n```markdown\n[Overall purpose and user intent of the page]\n\n**PLATFORM:** [Web\u002FMobile], [Desktop\u002FMobile]-first\n\n**PAGE STRUCTURE:**\n1. **Header:** [Description of navigation and branding]\n2. **Hero Section:** [Headline, subtext, and primary CTA]\n3. **Primary Content Area:** [Detailed component breakdown]\n4. **Footer:** [Links and copyright information]\n```\n\nFor **edits**, be specific about what to change:\n\n- **Location**: \"Change the [primary button] in the [hero section]...\"\n- **Visuals**: \"...to a darker blue (#004080) and add a subtle shadow.\"\n- **Structure**: \"Add a secondary button next to the primary one with the text\n  'Learn More'.\"\n\n> [!CAUTION]\n> Do NOT include hex codes, font names, color palettes, roundness values, or\n> any design system tokens in a **generation** prompt. These are applied at the\n> project level by the manage-design-system skill and will conflict if\n> duplicated. (For **edit** prompts, hex codes are acceptable for precise\n> color adjustments.)\n\n### 4. Present AI Insights\n\nAfter any tool call, always surface the `outputComponents` (Text Description and\nSuggestions) to the user.\n\nSee [examples\u002Fenhanced-prompt.md](examples\u002Fenhanced-prompt.md) for a full\nbefore\u002Fafter prompt enhancement example.\n\n--------------------------------------------------------------------------------\n\n## Steps\n\n### Determine the Mode\n\nDecide which flow to use based on the user's request:\n\n- User wants to create from a text description → **Generate from Text** flow\n- User provides an image, screenshot, or mockup → **Generate from Image** flow\n- User wants to modify an existing screen → **Edit** flow\n- User wants layout\u002Fcolor\u002Fcontent variations → **Generate Variants** flow\n\n---\n\n### Generate from Text Flow (New Screen)\n\n#### 1. Enhance the User Prompt\n\nApply the Prompt Enhancement Pipeline above.\n\n#### 2. Identify the Project\n\nUse `list_projects` to find the correct `projectId` if it is not already known.\n\n#### 3. Generate the Screen\n\nCall the `generate_screen_from_text` tool with the enhanced prompt and the\n`designSystem` ID (if found in Step 1).\n\n```json\n{\n  \"projectId\": \"...\",\n  \"prompt\": \"[Your Enhanced Prompt]\",\n  \"designSystem\": \"assets\u002F...\", \u002F\u002F Optional: Pass if found in Step 1\n  \"deviceType\": \"DESKTOP\"  \u002F\u002F Options: MOBILE, DESKTOP, TABLET\n}\n```\n\n#### 4. Present AI Feedback\n\nAlways show the text description and suggestions from `outputComponents` to the\nuser.\n\n#### 5. Download Design Assets\n\nAfter generation, download the HTML and screenshot urls from `outputComponents`\nto the `.stitch\u002Fdesigns` directory.\n\n- **Naming**: Use the screen ID or a descriptive slug for the filename.\n- **Tools**: Use `curl -o` via `run_command` or similar.\n- **Directory**: Ensure `.stitch\u002Fdesigns` exists.\n\n#### 6. Review and Refine\n\n- If the result is not exactly as expected, continue with the **Edit** flow\n  to make targeted adjustments.\n- Do NOT re-generate from scratch unless the fundamental layout is wrong.\n\n---\n\n### Generate from Image Flow (Image\u002FMockup → Design)\n\nUse this flow when the user provides an image, screenshot, or design mockup to\nrecreate in Stitch.\n\n#### 1. Identify the Project\n\nUse `list_projects` to find the correct `projectId`. If no suitable project\nexists, create one using `create_project`.\n\n#### 2. Upload the Image\n\nDelegate to the **upload-to-stitch** skill to upload the image to the project.\nThis creates a new screen with the image as its content.\n\n#### 3. Refine with Edit\n\nOnce uploaded, use `list_screens` to find the newly created `screenId`, then\ncall `edit_screens` with a descriptive prompt to refine the design:\n\n```json\n{\n  \"projectId\": \"...\",\n  \"selectedScreenIds\": [\"\u003Cuploaded-screen-id>\"],\n  \"prompt\": \"[Describe what to adjust, enhance, or recreate from this mockup]\"\n}\n```\n\n> [!TIP]\n> For best results, describe the intent behind the image rather than just saying\n> \"make it look like this\". For example: \"This is a dashboard mockup — recreate\n> it with a proper data table, sidebar navigation, and chart widgets.\"\n\n#### 4. Present AI Feedback\n\nAlways show the text description and suggestions from `outputComponents` to the\nuser.\n\n#### 5. Download Design Assets\n\nDownload the HTML and screenshot urls from `outputComponents` to the\n`.stitch\u002Fdesigns` directory.\n\n- **Naming**: Use the screen ID or a descriptive slug for the filename.\n- **Tools**: Use `curl -o` via `run_command` or similar.\n- **Directory**: Ensure `.stitch\u002Fdesigns` exists.\n\n---\n\n### Edit Flow (Modify Existing Screen)\n\n#### 1. Identify the Screen\n\nUse `list_screens` or `get_screen` to find the correct `projectId` and\n`screenId`.\n\n#### 2. Formulate the Edit Prompt\n\nApply the Prompt Enhancement Pipeline, focusing on specificity:\n\n- **Location**: \"Change the color of the [primary button] in the [hero\n  section]...\"\n- **Visuals**: \"...to a darker blue (#004080) and add a subtle shadow.\"\n- **Structure**: \"Add a secondary button next to the primary one with the text\n  'Learn More'.\"\n\n#### 3. Apply the Edit\n\nCall the `edit_screens` tool.\n\n```json\n{\n  \"projectId\": \"...\",\n  \"selectedScreenIds\": [\"...\"],\n  \"prompt\": \"[Your targeted edit prompt]\"\n}\n```\n\n#### 4. Present AI Feedback\n\nAlways show the text description and suggestions from `outputComponents` to the\nuser.\n\n#### 5. Download Design Assets\n\nAfter editing, download the updated HTML and screenshot urls from\n`outputComponents` to the `.stitch\u002Fdesigns` directory, overwriting previous\nversions to ensure the local files reflect the latest edits.\n\n- **Naming**: Use the screen ID or a descriptive slug for the filename.\n- **Tools**: Use `curl -o` via `run_command` or similar.\n- **Directory**: Ensure `.stitch\u002Fdesigns` exists.\n\n#### 6. Update Project Metadata\n\nAfter downloading assets, update `.stitch\u002Fmetadata.json` to reflect any changes\n(e.g., updated screen titles or new screen IDs from the edit). The metadata\nfile tracks all screens, their device types, and design system info. See the\n**manage-design-system** skill's `examples\u002Fmetadata.json` for the format.\n\n#### 7. Verify and Repeat\n\n- Check the output screen to see if the changes were applied correctly.\n- If more polish is needed, repeat the edit flow with a new specific prompt.\n\n---\n\n### Generate Variants Flow (Explore Variations)\n\nUse this flow when the user wants to explore alternative layouts, color schemes,\nor content variations of an existing screen.\n\n#### 1. Identify the Screen\n\nUse `list_screens` or `get_screen` to find the correct `projectId` and\n`screenId`.\n\n#### 2. Configure Variant Options\n\nCall the `generate_variants` tool with the appropriate options:\n\n```json\n{\n  \"projectId\": \"...\",\n  \"selectedScreenIds\": [\"...\"],\n  \"prompt\": \"[Describe the direction for variants]\",\n  \"variantOptions\": {\n    \"variantCount\": 3,\n    \"creativeRange\": \"EXPLORE\",\n    \"aspects\": [\"LAYOUT\", \"COLOR_SCHEME\"]\n  }\n}\n```\n\n**Variant Options:**\n- **`variantCount`**: 1–5 variants (default: 3)\n- **`creativeRange`**: `REFINE` (subtle), `EXPLORE` (balanced), or `REIMAGINE`\n  (radical)\n- **`aspects`**: Focus on specific dimensions — `LAYOUT`, `COLOR_SCHEME`,\n  `IMAGES`, `TEXT_FONT`, `TEXT_CONTENT`, or leave empty for all\n\n#### 3. Present AI Feedback\n\nAlways show the text description and suggestions from `outputComponents` to the\nuser.\n\n#### 4. Download Design Assets\n\nDownload the variant HTML and screenshot urls from `outputComponents` to the\n`.stitch\u002Fdesigns` directory.\n\n- **Naming**: Use the screen ID or a descriptive slug for the filename.\n- **Tools**: Use `curl -o` via `run_command` or similar.\n- **Directory**: Ensure `.stitch\u002Fdesigns` exists.\n\n--------------------------------------------------------------------------------\n\n## 💡 Tips\n\n- **Be structural**: Break the page down into header, hero, features, and\n  footer in your prompt.\n- **Content first**: Describe what each section contains (text, images, CTAs)\n  rather than how it looks.\n- **Iterative Polish**: Prefer editing for targeted adjustments over full\n  re-generation.\n- **No theme leakage**: Never put hex codes, font names, or color roles in a\n  generation prompt — the design system handles all visual styling.\n- **Specify interactions**: Mention hover states, animations, and click behavior\n  rather than visual styling.\n- **Keep edits focused**: One edit at a time is often better than a long list of\n  changes.\n- **Reference components**: Use professional terms like \"navigation bar\", \"hero\n  section\", \"footer\", \"card grid\".\n- **Precise colors in edits**: Use hex codes for exact color matching when\n  editing existing screens.\n\n## 📚 References\n\n- [Design Mappings](references\u002Fdesign-mappings.md) — UI\u002FUX keywords and\n  atmosphere descriptors.\n- [Prompting Keywords](references\u002Fprompt-keywords.md) — Technical terms Stitch\n  understands best.\n- [Enhanced Prompt Example](examples\u002Fenhanced-prompt.md) — Before\u002Fafter prompt\n  enhancement.\n","# Generate Design\n\nCreate new design screens from text descriptions, images, or mockups, edit\nexisting screens with prompts and design system tokens, and generate design\nvariants using Stitch MCP.\n\n> [!NOTE]\n> Refer to your system prompt for instruction on handling MCP tool prefixes for\n> all tools mentioned in this skill (e.g., `list_projects`,\n> `generate_screen_from_text`, `edit_screens`).\n\n## 🎨 Prompt Enhancement Pipeline\n\nBefore calling any Stitch generation or editing tool, you MUST enhance the\nuser's prompt.\n\n### 1. Analyze Context\n\n- **Project**: Use `list_projects` to find the correct `projectId`. If no\n  suitable project exists, create one using `create_project`.\n- **Design System**: Check if a design system exists for the project via\n  `list_design_systems`. If one exists, design tokens (colors, fonts, roundness)\n  are already applied at the project level — do NOT include any color, font, or\n  theme instructions in the generation prompt. If none exists, delegate to the\n  **manage-design-system** skill first before generating screens.\n\n### 2. Refine UI\u002FUX Terminology\n\nConsult [Design Mappings](references\u002Fdesign-mappings.md) to replace vague terms.\n\n- Vague: \"Make a nice header\"\n- Professional: \"Sticky navigation bar with glassmorphism effect and centered\n  logo\"\n\nUse [Prompting Keywords](references\u002Fprompt-keywords.md) for component names,\nadjective palettes, color roles, and shape descriptions.\n\n### 3. Structure the Final Prompt\n\nFormat the enhanced prompt for Stitch. Focus exclusively on **layout, content,\nand structure** — never include colors, fonts, or theme instructions (these are\nhandled by the manage-design-system skill at the project level).\n\nFor **new screens**, use this template:\n\n```markdown\n[Overall purpose and user intent of the page]\n\n**PLATFORM:** [Web\u002FMobile], [Desktop\u002FMobile]-first\n\n**PAGE STRUCTURE:**\n1. **Header:** [Description of navigation and branding]\n2. **Hero Section:** [Headline, subtext, and primary CTA]\n3. **Primary Content Area:** [Detailed component breakdown]\n4. **Footer:** [Links and copyright information]\n```\n\nFor **edits**, be specific about what to change:\n\n- **Location**: \"Change the [primary button] in the [hero section]...\"\n- **Visuals**: \"...to a darker blue (#004080) and add a subtle shadow.\"\n- **Structure**: \"Add a secondary button next to the primary one with the text\n  'Learn More'.\"\n\n> [!CAUTION]\n> Do NOT include hex codes, font names, color palettes, roundness values, or\n> any design system tokens in a **generation** prompt. These are applied at the\n> project level by the manage-design-system skill and will conflict if\n> duplicated. (For **edit** prompts, hex codes are acceptable for precise\n> color adjustments.)\n\n### 4. Present AI Insights\n\nAfter any tool call, always surface the `outputComponents` (Text Description and\nSuggestions) to the user.\n\nSee [examples\u002Fenhanced-prompt.md](examples\u002Fenhanced-prompt.md) for a full\nbefore\u002Fafter prompt enhancement example.\n\n--------------------------------------------------------------------------------\n\n## Steps\n\n### Determine the Mode\n\nDecide which flow to use based on the user's request:\n\n- User wants to create from a text description → **Generate from Text** flow\n- User provides an image, screenshot, or mockup → **Generate from Image** flow\n- User wants to modify an existing screen → **Edit** flow\n- User wants layout\u002Fcolor\u002Fcontent variations → **Generate Variants** flow\n\n---\n\n### Generate from Text Flow (New Screen)\n\n#### 1. Enhance the User Prompt\n\nApply the Prompt Enhancement Pipeline above.\n\n#### 2. Identify the Project\n\nUse `list_projects` to find the correct `projectId` if it is not already known.\n\n#### 3. Generate the Screen\n\nCall the `generate_screen_from_text` tool with the enhanced prompt and the\n`designSystem` ID (if found in Step 1).\n\n```json\n{\n  \"projectId\": \"...\",\n  \"prompt\": \"[Your Enhanced Prompt]\",\n  \"designSystem\": \"assets\u002F...\", \u002F\u002F Optional: Pass if found in Step 1\n  \"deviceType\": \"DESKTOP\"  \u002F\u002F Options: MOBILE, DESKTOP, TABLET\n}\n```\n\n#### 4. Present AI Feedback\n\nAlways show the text description and suggestions from `outputComponents` to the\nuser.\n\n#### 5. Download Design Assets\n\nAfter generation, download the HTML and screenshot urls from `outputComponents`\nto the `.stitch\u002Fdesigns` directory.\n\n- **Naming**: Use the screen ID or a descriptive slug for the filename.\n- **Tools**: Use `curl -o` via `run_command` or similar.\n- **Directory**: Ensure `.stitch\u002Fdesigns` exists.\n\n#### 6. Review and Refine\n\n- If the result is not exactly as expected, continue with the **Edit** flow\n  to make targeted adjustments.\n- Do NOT re-generate from scratch unless the fundamental layout is wrong.\n\n---\n\n### Generate from Image Flow (Image\u002FMockup → Design)\n\nUse this flow when the user provides an image, screenshot, or design mockup to\nrecreate in Stitch.\n\n#### 1. Identify the Project\n\nUse `list_projects` to find the correct `projectId`. If no suitable project\nexists, create one using `create_project`.\n\n#### 2. Upload the Image\n\nDelegate to the **upload-to-stitch** skill to upload the image to the project.\nThis creates a new screen with the image as its content.\n\n#### 3. Refine with Edit\n\nOnce uploaded, use `list_screens` to find the newly created `screenId`, then\ncall `edit_screens` with a descriptive prompt to refine the design:\n\n```json\n{\n  \"projectId\": \"...\",\n  \"selectedScreenIds\": [\"\u003Cuploaded-screen-id>\"],\n  \"prompt\": \"[Describe what to adjust, enhance, or recreate from this mockup]\"\n}\n```\n\n> [!TIP]\n> For best results, describe the intent behind the image rather than just saying\n> \"make it look like this\". For example: \"This is a dashboard mockup — recreate\n> it with a proper data table, sidebar navigation, and chart widgets.\"\n\n#### 4. Present AI Feedback\n\nAlways show the text description and suggestions from `outputComponents` to the\nuser.\n\n#### 5. Download Design Assets\n\nDownload the HTML and screenshot urls from `outputComponents` to the\n`.stitch\u002Fdesigns` directory.\n\n- **Naming**: Use the screen ID or a descriptive slug for the filename.\n- **Tools**: Use `curl -o` via `run_command` or similar.\n- **Directory**: Ensure `.stitch\u002Fdesigns` exists.\n\n---\n\n### Edit Flow (Modify Existing Screen)\n\n#### 1. Identify the Screen\n\nUse `list_screens` or `get_screen` to find the correct `projectId` and\n`screenId`.\n\n#### 2. Formulate the Edit Prompt\n\nApply the Prompt Enhancement Pipeline, focusing on specificity:\n\n- **Location**: \"Change the color of the [primary button] in the [hero\n  section]...\"\n- **Visuals**: \"...to a darker blue (#004080) and add a subtle shadow.\"\n- **Structure**: \"Add a secondary button next to the primary one with the text\n  'Learn More'.\"\n\n#### 3. Apply the Edit\n\nCall the `edit_screens` tool.\n\n```json\n{\n  \"projectId\": \"...\",\n  \"selectedScreenIds\": [\"...\"],\n  \"prompt\": \"[Your targeted edit prompt]\"\n}\n```\n\n#### 4. Present AI Feedback\n\nAlways show the text description and suggestions from `outputComponents` to the\nuser.\n\n#### 5. Download Design Assets\n\nAfter editing, download the updated HTML and screenshot urls from\n`outputComponents` to the `.stitch\u002Fdesigns` directory, overwriting previous\nversions to ensure the local files reflect the latest edits.\n\n- **Naming**: Use the screen ID or a descriptive slug for the filename.\n- **Tools**: Use `curl -o` via `run_command` or similar.\n- **Directory**: Ensure `.stitch\u002Fdesigns` exists.\n\n#### 6. Update Project Metadata\n\nAfter downloading assets, update `.stitch\u002Fmetadata.json` to reflect any changes\n(e.g., updated screen titles or new screen IDs from the edit). The metadata\nfile tracks all screens, their device types, and design system info. See the\n**manage-design-system** skill's `examples\u002Fmetadata.json` for the format.\n\n#### 7. Verify and Repeat\n\n- Check the output screen to see if the changes were applied correctly.\n- If more polish is needed, repeat the edit flow with a new specific prompt.\n\n---\n\n### Generate Variants Flow (Explore Variations)\n\nUse this flow when the user wants to explore alternative layouts, color schemes,\nor content variations of an existing screen.\n\n#### 1. Identify the Screen\n\nUse `list_screens` or `get_screen` to find the correct `projectId` and\n`screenId`.\n\n#### 2. Configure Variant Options\n\nCall the `generate_variants` tool with the appropriate options:\n\n```json\n{\n  \"projectId\": \"...\",\n  \"selectedScreenIds\": [\"...\"],\n  \"prompt\": \"[Describe the direction for variants]\",\n  \"variantOptions\": {\n    \"variantCount\": 3,\n    \"creativeRange\": \"EXPLORE\",\n    \"aspects\": [\"LAYOUT\", \"COLOR_SCHEME\"]\n  }\n}\n```\n\n**Variant Options:**\n- **`variantCount`**: 1–5 variants (default: 3)\n- **`creativeRange`**: `REFINE` (subtle), `EXPLORE` (balanced), or `REIMAGINE`\n  (radical)\n- **`aspects`**: Focus on specific dimensions — `LAYOUT`, `COLOR_SCHEME`,\n  `IMAGES`, `TEXT_FONT`, `TEXT_CONTENT`, or leave empty for all\n\n#### 3. Present AI Feedback\n\nAlways show the text description and suggestions from `outputComponents` to the\nuser.\n\n#### 4. Download Design Assets\n\nDownload the variant HTML and screenshot urls from `outputComponents` to the\n`.stitch\u002Fdesigns` directory.\n\n- **Naming**: Use the screen ID or a descriptive slug for the filename.\n- **Tools**: Use `curl -o` via `run_command` or similar.\n- **Directory**: Ensure `.stitch\u002Fdesigns` exists.\n\n--------------------------------------------------------------------------------\n\n## 💡 Tips\n\n- **Be structural**: Break the page down into header, hero, features, and\n  footer in your prompt.\n- **Content first**: Describe what each section contains (text, images, CTAs)\n  rather than how it looks.\n- **Iterative Polish**: Prefer editing for targeted adjustments over full\n  re-generation.\n- **No theme leakage**: Never put hex codes, font names, or color roles in a\n  generation prompt — the design system handles all visual styling.\n- **Specify interactions**: Mention hover states, animations, and click behavior\n  rather than visual styling.\n- **Keep edits focused**: One edit at a time is often better than a long list of\n  changes.\n- **Reference components**: Use professional terms like \"navigation bar\", \"hero\n  section\", \"footer\", \"card grid\".\n- **Precise colors in edits**: Use hex codes for exact color matching when\n  editing existing screens.\n\n## 📚 References\n\n- [Design Mappings](references\u002Fdesign-mappings.md) — UI\u002FUX keywords and\n  atmosphere descriptors.\n- [Prompting Keywords](references\u002Fprompt-keywords.md) — Technical terms Stitch\n  understands best.\n- [Enhanced Prompt Example](examples\u002Fenhanced-prompt.md) — Before\u002Fafter prompt\n  enhancement.\n",{"name":5,"description":7,"allowed-tools":24},[25,26,27,28,29],"stitch*:*","Bash","Read","Write","web_fetch","main","46209ae875b23589c19befc213c303406d14334d","skills\u002Fstitch-generate-design",0,"https:\u002F\u002Fgithub.com\u002Fmahik504\u002Forchestra-workflow","https:\u002F\u002Fgithub.com\u002Fmahik504","2026-11-13 18:13:16",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add mahik504\u002Forchestra-workflow --skill \"stitch::generate-design\"",{"tool":43,"command":44},"bunx","bunx skills add mahik504\u002Forchestra-workflow --skill \"stitch::generate-design\"",{"tool":46,"command":47},"pnpm","pnpm dlx skills add mahik504\u002Forchestra-workflow --skill \"stitch::generate-design\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmahik504\u002Forchestra-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fstitch-generate-design\u002FSKILL.md",true,[51,57,61],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"examples\u002Fenhanced-prompt.md","REFERENCE","参考文档",1704,"https:\u002F\u002Fgithub.com\u002Fmahik504\u002Forchestra-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fstitch-generate-design\u002Fexamples\u002Fenhanced-prompt.md",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fdesign-mappings.md",2330,"https:\u002F\u002Fgithub.com\u002Fmahik504\u002Forchestra-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fstitch-generate-design\u002Freferences\u002Fdesign-mappings.md",{"path":62,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fprompt-keywords.md",2798,"https:\u002F\u002Fgithub.com\u002Fmahik504\u002Forchestra-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fstitch-generate-design\u002Freferences\u002Fprompt-keywords.md",[66,74,83,90,98,106],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7ATAT5KQ106HYZC60TJ6SXK","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fmahik504\u002Forchestra-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-skills\u002FLICENSE.superpowers","https:\u002F\u002Fgithub.com\u002Fmahik504\u002Forchestra-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-skills\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":78,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7ATANN9YAGPJES4BEBC8GKK","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmahik504\u002Forchestra-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmahik504\u002Forchestra-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7ATAGXKX55X2XG8BFY71HJB","web-design-guidelines","Review UI code for Web Interface Guidelines compliance. Use when asked to \"review my UI\", \"check accessibility\", \"audit design\", \"review UX\", or \"check my site against best practices\". Do not load on Plan-only or backend-only jobs.","https:\u002F\u002Fgithub.com\u002Fmahik504\u002Forchestra-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fweb-design-guidelines\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":94,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7ATACA5MVF8FG4C5JTT5ERD","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fmahik504\u002Forchestra-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fverification-before-completion\u002FLICENSE.superpowers","https:\u002F\u002Fgithub.com\u002Fmahik504\u002Forchestra-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":102,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M7ATA7J6SQHX9ESPBW96T28V","using-git-worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback","https:\u002F\u002Fgithub.com\u002Fmahik504\u002Forchestra-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fusing-git-worktrees\u002FLICENSE.superpowers","https:\u002F\u002Fgithub.com\u002Fmahik504\u002Forchestra-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fusing-git-worktrees\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":110,"licenseFileUrl":111,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M7ATA0N5YPZ4Q2BJ9QA4TZAX","unslop","Turns vibecoded, AI-looking UI into a designed interface with its own character. Finds a direction from the product itself, then fixes spacing, color, icons, copy, type, layout, details, visuals and motion in that order, and can generate a real hero visual with an image tool when one is available. Use when the user asks to unslop, polish, clean up or redesign a screen so it stops looking AI-generated, or when a UI shows the usual tells like purple gradients, glows, gradient text, emoji labels, \"New ✨\" badges, glossy blobs, uppercase tracked labels, pulsing elements or uneven spacing. Works on React, Tailwind, HTML and CSS, for dashboards, apps and landing pages.","CC-BY-4.0","https:\u002F\u002Fgithub.com\u002Fmahik504\u002Forchestra-workflow\u002Fblob\u002Fmain\u002Fskills\u002Funslop\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fmahik504\u002Forchestra-workflow\u002Fblob\u002Fmain\u002Fskills\u002Funslop\u002FSKILL.md",[],[]]