[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EMF6DMS93F0Y91FTGJVRDP":3,"skill-same:01M7EMF6DMS93F0Y91FTGJVRDP":62},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7EMF6DMS93F0Y91FTGJVRDP","design-to-code",null,"Pixel-perfect Figma to React conversion using coderio. Generates production-ready code (TypeScript, Vite, TailwindCSS V4) with high visual fidelity. Features robust error handling, checkpoint recovery, and streamlined execution via helper script.","marnixGeerkens\u002Frocketlauncher-claude-code","marnixGeerkens","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F143275741?v=4","01M7EJY825SFPHDDZNFDAJHCA9","Marnix Geerkens","01M7EJY82TBA6ABXJ62JWR9B9F",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fdesign-to-code\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fdesign-to-code\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: design-to-code\ndescription: Pixel-perfect Figma to React conversion using coderio. Generates production-ready code (TypeScript, Vite, TailwindCSS V4) with high visual fidelity. Features robust error handling, checkpoint recovery, and streamlined execution via helper script.\n---\n\n# Design to Code\n\nHigh-fidelity UI restoration from Figma designs to production-ready React + TypeScript components.\nThis SKILL uses a **robust helper script** to minimize manual errors and ensure pixel-perfect results.\n\n## Prerequisites\n\n1.  **Figma API Token**: Get from Figma → Settings → Personal Access Tokens\n2.  **Node.js**: Version 18+\n3.  **coderio**: Installed in `scripts\u002F` folder (handled by Setup phase)\n\n## Workflow Overview\n\n```\nPhase 0: SETUP    → Create helper script and script environment\nPhase 1: PROTOCOL → Generate design protocol (Structure & Props)\nPhase 2: CODE     → Generate components and assets\n```\n\n---\n\n# Phase 0: Setup\n\n## Step 0.1: Initialize Helper Script\n\n**User Action**: Run these commands to create the execution helper and isolate its dependencies.\n\n```bash\nmkdir -p scripts\n\n# 1. Copy script files\n# Note: Ensure you have the 'skills\u002Fdesign-to-code\u002Fscripts' directory available\ncp skills\u002Fdesign-to-code\u002Fscripts\u002Fpackage.json scripts\u002Fpackage.json\ncp skills\u002Fdesign-to-code\u002Fscripts\u002Fcoderio-skill.mjs scripts\u002Fcoderio-skill.mjs\n\n# 2. Install coderio in scripts directory (adjust version if needed)\ncd scripts && pnpm install && cd ..\n```\n\n## Step 0.2: Scaffold Project (Optional)\n\nIf starting a new project:\n\n1.  Run: `node scripts\u002Fcoderio-skill.mjs scaffold-prompt \"MyApp\"`\n2.  **AI Task**: Follow the instructions output by the command to create files.\n\n---\n\n# Phase 1: Protocol Generation\n\n## Step 1.1: Fetch Data\n\n```bash\n# Replace with your URL and Token\nnode scripts\u002Fcoderio-skill.mjs fetch-figma \"https:\u002F\u002Ffigma.com\u002Ffile\u002F...\" \"figd_...\"\n```\n\n**Verify**: `process\u002Fthumbnail.png` should exist.\n\n## Step 1.2: Generate Structure\n\n1.  **Generate Prompt**:\n\n    ```bash\n    node scripts\u002Fcoderio-skill.mjs structure-prompt > scripts\u002Fstructure-prompt.md\n    ```\n\n2.  **AI Task (Structure)**:\n    - **ATTACH**: `process\u002Fthumbnail.png` (MANDATORY)\n    - **READ**: `scripts\u002Fstructure-prompt.md`\n    - **INSTRUCTION**: \"Generate the component structure JSON based on the prompt and the attached thumbnail. Focus on visual grouping. **Use text content to name components accurately (e.g. 'SafeProducts', not 'FAQ').**\"\n    - **SAVE**: Paste the JSON result into `scripts\u002Fstructure-output.json`.\n\n3.  **Process Result**:\n    ```bash\n    node scripts\u002Fcoderio-skill.mjs save-structure\n    ```\n\n## Step 1.3: Extract Props (Iterative)\n\n1.  **List Components**:\n\n    ```bash\n    node scripts\u002Fcoderio-skill.mjs list-components\n    ```\n\n2.  **For EACH component in the list**:\n\n    a. **Generate Prompt**:\n\n    ```bash\n    node scripts\u002Fcoderio-skill.mjs props-prompt \"ComponentName\" > scripts\u002Fcurrent-props-prompt.md\n    ```\n\n    b. **AI Task (Props)**:\n    - **ATTACH**: `process\u002Fthumbnail.png` (MANDATORY)\n    - **READ**: `scripts\u002Fcurrent-props-prompt.md`\n    - **INSTRUCTION**: \"Extract props and state data. Be pixel-perfect with text and image paths.\"\n    - **SAVE**: Paste the JSON result into `scripts\u002FComponentName-props.json`.\n\n    c. **Save & Validate**:\n\n    ```bash\n    node scripts\u002Fcoderio-skill.mjs save-props \"ComponentName\"\n    # If this fails, re-do step 'b' with better attention to the thumbnail\n    ```\n\n---\n\n# Phase 2: Code Generation\n\n## Step 2.1: Plan Tasks\n\n```bash\nnode scripts\u002Fcoderio-skill.mjs list-gen-tasks\n```\n\nThis outputs a list of tasks with indices (0, 1, 2...).\n\n## Step 2.2: Generate Components (Iterative)\n\n**For EACH task index (starting from 0)**:\n\n1.  **Generate Prompt**:\n\n    ```bash\n    node scripts\u002Fcoderio-skill.mjs code-prompt 0 > scripts\u002Fcode-prompt.md\n    # Replace '0' with current task index\n    ```\n\n2.  **AI Task (Code)**:\n    - **ATTACH**: `process\u002Fthumbnail.png` (MANDATORY)\n    - **READ**: `scripts\u002Fcode-prompt.md`\n    - **INSTRUCTION**: \"Generate the React component code. Match the thumbnail EXACTLY. **Use STRICT text content from input data, do not hallucinate.**\"\n    - **SAVE**: Paste the code block into `scripts\u002Fcode-output.txt`.\n\n3.  **Save Code**:\n    ```bash\n    node scripts\u002Fcoderio-skill.mjs save-code 0\n    # Replace '0' with current task index\n    ```\n\n## Step 2.3: Final Integration\n\nInject the root component into `App.tsx`. Use the path found in the last task of Phase 2.1.\n\n---\n\n# Troubleshooting\n\n- **\"Props validation failed\"**: The AI generated empty props. Check if `process\u002Fthumbnail.png` was attached and visible to the AI. Retry the props generation step.\n- **\"Module not found\"**: Ensure `node scripts\u002Fcoderio-skill.mjs save-code` was run for the child component before the parent component. Phase 2 must be done in order (0, 1, 2...).\n- **\"Visuals don't match\"**: Did you attach the thumbnail? The AI relies on it for spacing and layout nuances not present in the raw data.\n","# Design to Code\n\nHigh-fidelity UI restoration from Figma designs to production-ready React + TypeScript components.\nThis SKILL uses a **robust helper script** to minimize manual errors and ensure pixel-perfect results.\n\n## Prerequisites\n\n1.  **Figma API Token**: Get from Figma → Settings → Personal Access Tokens\n2.  **Node.js**: Version 18+\n3.  **coderio**: Installed in `scripts\u002F` folder (handled by Setup phase)\n\n## Workflow Overview\n\n```\nPhase 0: SETUP    → Create helper script and script environment\nPhase 1: PROTOCOL → Generate design protocol (Structure & Props)\nPhase 2: CODE     → Generate components and assets\n```\n\n---\n\n# Phase 0: Setup\n\n## Step 0.1: Initialize Helper Script\n\n**User Action**: Run these commands to create the execution helper and isolate its dependencies.\n\n```bash\nmkdir -p scripts\n\n# 1. Copy script files\n# Note: Ensure you have the 'skills\u002Fdesign-to-code\u002Fscripts' directory available\ncp skills\u002Fdesign-to-code\u002Fscripts\u002Fpackage.json scripts\u002Fpackage.json\ncp skills\u002Fdesign-to-code\u002Fscripts\u002Fcoderio-skill.mjs scripts\u002Fcoderio-skill.mjs\n\n# 2. Install coderio in scripts directory (adjust version if needed)\ncd scripts && pnpm install && cd ..\n```\n\n## Step 0.2: Scaffold Project (Optional)\n\nIf starting a new project:\n\n1.  Run: `node scripts\u002Fcoderio-skill.mjs scaffold-prompt \"MyApp\"`\n2.  **AI Task**: Follow the instructions output by the command to create files.\n\n---\n\n# Phase 1: Protocol Generation\n\n## Step 1.1: Fetch Data\n\n```bash\n# Replace with your URL and Token\nnode scripts\u002Fcoderio-skill.mjs fetch-figma \"https:\u002F\u002Ffigma.com\u002Ffile\u002F...\" \"figd_...\"\n```\n\n**Verify**: `process\u002Fthumbnail.png` should exist.\n\n## Step 1.2: Generate Structure\n\n1.  **Generate Prompt**:\n\n    ```bash\n    node scripts\u002Fcoderio-skill.mjs structure-prompt > scripts\u002Fstructure-prompt.md\n    ```\n\n2.  **AI Task (Structure)**:\n    - **ATTACH**: `process\u002Fthumbnail.png` (MANDATORY)\n    - **READ**: `scripts\u002Fstructure-prompt.md`\n    - **INSTRUCTION**: \"Generate the component structure JSON based on the prompt and the attached thumbnail. Focus on visual grouping. **Use text content to name components accurately (e.g. 'SafeProducts', not 'FAQ').**\"\n    - **SAVE**: Paste the JSON result into `scripts\u002Fstructure-output.json`.\n\n3.  **Process Result**:\n    ```bash\n    node scripts\u002Fcoderio-skill.mjs save-structure\n    ```\n\n## Step 1.3: Extract Props (Iterative)\n\n1.  **List Components**:\n\n    ```bash\n    node scripts\u002Fcoderio-skill.mjs list-components\n    ```\n\n2.  **For EACH component in the list**:\n\n    a. **Generate Prompt**:\n\n    ```bash\n    node scripts\u002Fcoderio-skill.mjs props-prompt \"ComponentName\" > scripts\u002Fcurrent-props-prompt.md\n    ```\n\n    b. **AI Task (Props)**:\n    - **ATTACH**: `process\u002Fthumbnail.png` (MANDATORY)\n    - **READ**: `scripts\u002Fcurrent-props-prompt.md`\n    - **INSTRUCTION**: \"Extract props and state data. Be pixel-perfect with text and image paths.\"\n    - **SAVE**: Paste the JSON result into `scripts\u002FComponentName-props.json`.\n\n    c. **Save & Validate**:\n\n    ```bash\n    node scripts\u002Fcoderio-skill.mjs save-props \"ComponentName\"\n    # If this fails, re-do step 'b' with better attention to the thumbnail\n    ```\n\n---\n\n# Phase 2: Code Generation\n\n## Step 2.1: Plan Tasks\n\n```bash\nnode scripts\u002Fcoderio-skill.mjs list-gen-tasks\n```\n\nThis outputs a list of tasks with indices (0, 1, 2...).\n\n## Step 2.2: Generate Components (Iterative)\n\n**For EACH task index (starting from 0)**:\n\n1.  **Generate Prompt**:\n\n    ```bash\n    node scripts\u002Fcoderio-skill.mjs code-prompt 0 > scripts\u002Fcode-prompt.md\n    # Replace '0' with current task index\n    ```\n\n2.  **AI Task (Code)**:\n    - **ATTACH**: `process\u002Fthumbnail.png` (MANDATORY)\n    - **READ**: `scripts\u002Fcode-prompt.md`\n    - **INSTRUCTION**: \"Generate the React component code. Match the thumbnail EXACTLY. **Use STRICT text content from input data, do not hallucinate.**\"\n    - **SAVE**: Paste the code block into `scripts\u002Fcode-output.txt`.\n\n3.  **Save Code**:\n    ```bash\n    node scripts\u002Fcoderio-skill.mjs save-code 0\n    # Replace '0' with current task index\n    ```\n\n## Step 2.3: Final Integration\n\nInject the root component into `App.tsx`. Use the path found in the last task of Phase 2.1.\n\n---\n\n# Troubleshooting\n\n- **\"Props validation failed\"**: The AI generated empty props. Check if `process\u002Fthumbnail.png` was attached and visible to the AI. Retry the props generation step.\n- **\"Module not found\"**: Ensure `node scripts\u002Fcoderio-skill.mjs save-code` was run for the child component before the parent component. Phase 2 must be done in order (0, 1, 2...).\n- **\"Visuals don't match\"**: Did you attach the thumbnail? The AI relies on it for spacing and layout nuances not present in the raw data.\n",{"name":5,"description":7},"main","4e647b68aabe849e143b6950971c380f7adccdef","components\u002Fskills\u002Fdesign-to-code","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code","https:\u002F\u002Frocketlauncher.ai\u002Fclaude-code","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens","CEO of Rocketlauncher.ai\r\n\r\nObsessed with AI\r\n\r\njoin  https:\u002F\u002Fwww.skool.com\u002Frocketlauncher-university\r\n👉🏻 it's free ","2026-10-13 00:52:14",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add marnixGeerkens\u002Frocketlauncher-claude-code --skill design-to-code",{"tool":39,"command":40},"bunx","bunx skills add marnixGeerkens\u002Frocketlauncher-claude-code --skill design-to-code",{"tool":42,"command":43},"pnpm","pnpm dlx skills add marnixGeerkens\u002Frocketlauncher-claude-code --skill design-to-code","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fdesign-to-code\u002FSKILL.md",true,[47,52,58],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":16},"LICENSE.txt","LICENSE","许可证",10880,{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"scripts\u002Fcoderio-skill.mjs","SCRIPT","脚本",13059,"https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fdesign-to-code\u002Fscripts\u002Fcoderio-skill.mjs",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"scripts\u002Fpackage.json",122,"https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fdesign-to-code\u002Fscripts\u002Fpackage.json",[63,71,79,86,93,100],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":20},"01M7EQFDF4T3K89WMFVFQVT3C8","zapier-make-patterns","No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points.  This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power","MIT","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fzapier-make-patterns\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":75,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":20},"01M7EQFA5XQ0811Q4Q0WCFASZG","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":20},"01M7EQF4J6C2WKQWD9E2RQC6MJ","workflow-automation","Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off.  This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation.  Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fworkflow-automation\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":20},"01M7EQF1AT655CYYZBEQ8V6Z9D","trigger-dev","Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task.","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Ftrigger-dev\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":20},"01M7EQEY9ENH0G2EJ1WD6C1CE8","slack-automation","Automate Slack workspace operations including messaging, search, channel management, and reaction workflows through Composio's Slack toolkit.","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fslack-automation\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":20},"01M7EQESHEKPTE0QPW9R6XV5K2","rote","Compile a proven agent skill (a SKILL.md plus references) into a deterministic pipeline that runs without an LLM in the loop, then serve it back to Claude as an MCP tool. Use when: rote, compile this skill, turn this skill into a workflow, make this skill deterministic, make this skill cheaper or faster, harden this skill for production, run this skill as a background job.","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Frote\u002FSKILL.md",[],[]]