[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71T2CES1RQ1FWKC0VCBWX2F":3,"skill-same:01M71T2CES1RQ1FWKC0VCBWX2F":85},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":59,"commitSha":60,"skillDirectory":61,"forksCount":13,"repositoryHtmlUrl":62,"repositoryHomepageUrl":6,"ownerHtmlUrl":63,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":64,"install":65,"resources":78},"01M71T2CES1RQ1FWKC0VCBWX2F","prompt-engineer",null,"Transforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, GROW)","javiertarazon\u002Fide-agente-free-jt7-","javiertarazon","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F153141207?v=4","01M71R52TB3S9HXKH6WSNT8A7V","01M71R52VG5KS2DKDDH4GDQ30A",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjaviertarazon\u002Fide-agente-free-jt7-\u002Fblob\u002Frelease\u002Fv4.2.11-panel-pro\u002F.github\u002Fskills\u002Fprompt-engineer\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"engineer","prompt","prompt engineer","transforms","github","cli","codex","code","automation","chain of thought","github-copilot","2025","copilot","frameworks","Optimization","STAR","soap","chain","prompt-engineering","community","2026-11-10 13:02:02",false,"---\nname: prompt-engineer\ndescription: \"Transforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, GROW)\"\nversion: 1.1.0\nauthor: Eric Andrade\ncreated: 2025-02-01\nupdated: 2026-02-04\nplatforms: [github-copilot-cli, claude-code, codex]\ncategory: automation\ntags: [prompt-engineering, optimization, frameworks, ai-enhancement]\nrisk: safe\nsource: community\n---\n\n## Purpose\n\nThis skill transforms raw, unstructured user prompts into highly optimized prompts using established prompting frameworks. It analyzes user intent, identifies task complexity, and intelligently selects the most appropriate framework(s) to maximize Claude\u002FChatGPT output quality.\n\nThe skill operates in \"magic mode\" - it works silently behind the scenes, only interacting with users when clarification is critically needed. Users receive polished, ready-to-use prompts without technical explanations or framework jargon.\n\nThis is a **universal skill** that works in any terminal context, not limited to Obsidian vaults or specific project structures.\n\n## When to Use\n\nInvoke this skill when:\n\n- User provides a vague or generic prompt (e.g., \"help me code Python\")\n- User has a complex idea but struggles to articulate it clearly\n- User's prompt lacks structure, context, or specific requirements\n- Task requires step-by-step reasoning (debugging, analysis, design)\n- User needs a prompt for a specific AI task but doesn't know prompting frameworks\n- User wants to improve an existing prompt's effectiveness\n- User asks variations of \"how do I ask AI to...\" or \"create a prompt for...\"\n\n## Workflow\n\n### Step 1: Analyze Intent\n\n**Objective:** Understand what the user truly wants to accomplish.\n\n**Actions:**\n1. Read the raw prompt provided by the user\n2. Detect task characteristics:\n   - **Type:** coding, writing, analysis, design, learning, planning, decision-making, creative, etc.\n   - **Complexity:** simple (one-step), moderate (multi-step), complex (requires reasoning\u002Fdesign)\n   - **Clarity:** clear intention vs. ambiguous\u002Fvague\n   - **Domain:** technical, business, creative, academic, personal, etc.\n3. Identify implicit requirements:\n   - Does user need examples?\n   - Is output format specified?\n   - Are there constraints (time, resources, scope)?\n   - Is this exploratory or execution-focused?\n\n**Detection Patterns:**\n- **Simple tasks:** Short prompts (\u003C50 chars), single verb, no context\n- **Complex tasks:** Long prompts (>200 chars), multiple requirements, conditional logic\n- **Ambiguous tasks:** Generic verbs (\"help\", \"improve\"), missing object\u002Fcontext\n- **Structured tasks:** Mentions steps, phases, deliverables, stakeholders\n\n\n### Step 3: Select Framework(s)\n\n**Objective:** Map task characteristics to optimal prompting framework(s).\n\n**Framework Mapping Logic:**\n\n| Task Type | Recommended Framework(s) | Rationale |\n|-----------|-------------------------|-----------|\n| **Role-based tasks** (act as expert, consultant) | **RTF** (Role-Task-Format) | Clear role definition + task + output format |\n| **Step-by-step reasoning** (debugging, proof, logic) | **Chain of Thought** | Encourages explicit reasoning steps |\n| **Structured projects** (multi-phase, deliverables) | **RISEN** (Role, Instructions, Steps, End goal, Narrowing) | Comprehensive structure for complex work |\n| **Complex design\u002Fanalysis** (systems, architecture) | **RODES** (Role, Objective, Details, Examples, Sense check) | Balances detail with validation |\n| **Summarization** (compress, synthesize) | **Chain of Density** | Iterative refinement to essential info |\n| **Communication** (reports, presentations, storytelling) | **RACE** (Role, Audience, Context, Expectation) | Audience-aware messaging |\n| **Investigation\u002Fanalysis** (research, diagnosis) | **RISE** (Research, Investigate, Synthesize, Evaluate) | Systematic analytical approach |\n| **Contextual situations** (problem-solving with background) | **STAR** (Situation, Task, Action, Result) | Context-rich problem framing |\n| **Documentation** (medical, technical, records) | **SOAP** (Subjective, Objective, Assessment, Plan) | Structured information capture |\n| **Goal-setting** (OKRs, objectives, targets) | **CLEAR** (Collaborative, Limited, Emotional, Appreciable, Refinable) | Goal clarity and actionability |\n| **Coaching\u002Fdevelopment** (mentoring, growth) | **GROW** (Goal, Reality, Options, Will) | Developmental conversation structure |\n\n**Blending Strategy:**\n- **Combine 2-3 frameworks** when task spans multiple types\n- Example: Complex technical project → **RODES + Chain of Thought** (structure + reasoning)\n- Example: Leadership decision → **CLEAR + GROW** (goal clarity + development)\n\n**Selection Criteria:**\n- Primary framework = best match to core task type\n- Secondary framework(s) = address additional complexity dimensions\n- Avoid over-engineering: simple tasks get simple frameworks\n\n**Critical Rule:** This selection happens **silently** - do not explain framework choice to user.\n\nRole: You are a senior software architect. [RTF - Role]\n\nObjective: Design a microservices architecture for [system]. [RODES - Objective]\n\nApproach this step-by-step: [Chain of Thought]\n1. Analyze current monolithic constraints\n2. Identify service boundaries\n3. Design inter-service communication\n4. Plan data consistency strategy\n\nDetails: [RODES - Details]\n- Expected traffic: [X]\n- Data volume: [Y]\n- Team size: [Z]\n\nOutput Format: [RTF - Format]\nProvide architecture diagram description, service definitions, and migration roadmap.\n\nSense Check: [RODES - Sense check]\nValidate that services are loosely coupled, independently deployable, and aligned with business domains.\n```\n\n**4.5. Language Adaptation**\n- If original prompt is in Portuguese, generate prompt in Portuguese\n- If original prompt is in English, generate prompt in English\n- If mixed, default to English (more universal for AI models)\n\n**4.6. Quality Checks**\nBefore finalizing, verify:\n- [ ] Prompt is self-contained (no external context needed)\n- [ ] Task is specific and measurable\n- [ ] Output format is clear\n- [ ] No ambiguous language\n- [ ] Appropriate level of detail for task complexity\n\n\n## Critical Rules\n\n### **NEVER:**\n\n- ❌ Assume information that wasn't provided - ALWAYS ask if critical details are missing\n- ❌ Explain which framework was selected or why (magic mode - keep it invisible)\n- ❌ Generate generic, one-size-fits-all prompts - always customize to context\n- ❌ Use technical jargon in the final prompt (unless user's domain is technical)\n- ❌ Ask more than 3 clarifying questions (avoid user fatigue)\n- ❌ Include meta-commentary in the output (\"This prompt uses...\", \"Note that...\")\n- ❌ Present output without code block formatting\n- ❌ Mix languages inconsistently (if user writes in PT, respond in PT)\n\n### **ALWAYS:**\n\n- ✅ Analyze intent before generating (Step 1 is mandatory)\n- ✅ Ask clarifying questions if critical information is ambiguous (Step 2 conditional)\n- ✅ Select framework(s) based on task type and complexity (Step 3 mapping)\n- ✅ Blend multiple frameworks when it improves prompt quality\n- ✅ Adapt prompt length to original input complexity (simple → short, complex → detailed)\n- ✅ Include output format specification in generated prompts\n- ✅ Present final prompt in clean Markdown code block\n- ✅ Make prompts self-contained (no dependency on external context)\n- ✅ Use examples in complex prompts to illustrate expected output\n- ✅ Validate prompt completeness before presenting (quality checks in Step 4.6)\n\n\n### **Example 2: Complex Clear Prompt → RODES + Chain of Thought (No Clarification)**\n\n**User Input:**\n```\ncopilot> create prompt for: I need to build a product recommendation system considering purchase history, user preferences, and market trends\n```\n\n**Skill Internal Process:**\n1. **Analyze:** Clear intent, complex task (ML system design), technical domain\n2. **Clarify:** Skip (sufficient information)\n3. **Select:** RODES (complex design) + Chain of Thought (reasoning needed)\n\n**Skill Output:**\n\n````markdown\n```\nRole: You are a senior machine learning engineer specializing in recommendation systems.\n\nObjective: Design a product recommendation system that combines user purchase history, preferences, and market trends.\n\nDetails:\n- Input data sources: user transaction logs, preference surveys, market trend APIs\n- Algorithm considerations: collaborative filtering, content-based filtering, hybrid approaches\n- Performance metrics: precision, recall, diversity, novelty\n- Scalability: system must handle 100k+ users\n- Real-time constraints: recommendations updated within 500ms\n\nApproach step-by-step:\n1. Analyze the three data sources and their relationships\n2. Propose 2-3 algorithm approaches with trade-offs analysis\n3. Design data pipeline architecture (ingestion, processing, serving)\n4. Define evaluation metrics and A\u002FB testing strategy\n5. Outline implementation roadmap with phases\n\nExamples:\n- Show pseudocode for core recommendation logic\n- Illustrate data flow diagram\n- Provide sample API response structure\n\nSense Check: Validate that the proposed solution balances personalization with discovery, scales to production load, and incorporates real-time market trends effectively.\n\nOutput format: Technical design document with architecture diagrams, algorithm justification, and implementation roadmap.\n```\n````\n\n\n### **Example 4: Code Debugging → Chain of Thought**\n\n**User Input:**\n```\ncopilot> optimize prompt: my Python code isn't working, needs debugging\n```\n\n**Skill Internal Process:**\n1. **Analyze:** Debugging task, needs step-by-step reasoning\n2. **Clarify:** Skip (user will provide code context later)\n3. **Select:** Chain of Thought\n\n**Skill Output:**\n\n````markdown\n```\nYou are an expert Python debugger.\n\nTask: Debug the Python code provided by the user by analyzing it step-by-step.\n\nDebugging approach:\n1. Read and understand the code's intended purpose\n2. Identify the error or unexpected behavior\n3. Trace variable states at each execution step\n4. Locate the root cause of the issue\n5. Propose fix with explanation\n6. Suggest preventive measures to avoid similar bugs\n\nFor each step, show your reasoning:\n- What you're checking\n- What you found\n- Why it matters\n\nOutput format:\n- **Issue identified:** [Describe the bug]\n- **Root cause:** [Why it's happening]\n- **Fix:** [Corrected code with comments]\n- **Prevention:** [Best practices to avoid this in the future]\n\nInclude a working example to verify the fix.\n```\n````\n\n\n## Notes\n\nThis skill is **platform-agnostic** and works in any terminal context where GitHub Copilot CLI is available. It does not depend on:\n- Obsidian vault structure\n- Specific project configurations\n- External files or templates\n\nThe skill is entirely self-contained, operating purely on user input and framework knowledge.\n","## Purpose\n\nThis skill transforms raw, unstructured user prompts into highly optimized prompts using established prompting frameworks. It analyzes user intent, identifies task complexity, and intelligently selects the most appropriate framework(s) to maximize Claude\u002FChatGPT output quality.\n\nThe skill operates in \"magic mode\" - it works silently behind the scenes, only interacting with users when clarification is critically needed. Users receive polished, ready-to-use prompts without technical explanations or framework jargon.\n\nThis is a **universal skill** that works in any terminal context, not limited to Obsidian vaults or specific project structures.\n\n## When to Use\n\nInvoke this skill when:\n\n- User provides a vague or generic prompt (e.g., \"help me code Python\")\n- User has a complex idea but struggles to articulate it clearly\n- User's prompt lacks structure, context, or specific requirements\n- Task requires step-by-step reasoning (debugging, analysis, design)\n- User needs a prompt for a specific AI task but doesn't know prompting frameworks\n- User wants to improve an existing prompt's effectiveness\n- User asks variations of \"how do I ask AI to...\" or \"create a prompt for...\"\n\n## Workflow\n\n### Step 1: Analyze Intent\n\n**Objective:** Understand what the user truly wants to accomplish.\n\n**Actions:**\n1. Read the raw prompt provided by the user\n2. Detect task characteristics:\n   - **Type:** coding, writing, analysis, design, learning, planning, decision-making, creative, etc.\n   - **Complexity:** simple (one-step), moderate (multi-step), complex (requires reasoning\u002Fdesign)\n   - **Clarity:** clear intention vs. ambiguous\u002Fvague\n   - **Domain:** technical, business, creative, academic, personal, etc.\n3. Identify implicit requirements:\n   - Does user need examples?\n   - Is output format specified?\n   - Are there constraints (time, resources, scope)?\n   - Is this exploratory or execution-focused?\n\n**Detection Patterns:**\n- **Simple tasks:** Short prompts (\u003C50 chars), single verb, no context\n- **Complex tasks:** Long prompts (>200 chars), multiple requirements, conditional logic\n- **Ambiguous tasks:** Generic verbs (\"help\", \"improve\"), missing object\u002Fcontext\n- **Structured tasks:** Mentions steps, phases, deliverables, stakeholders\n\n\n### Step 3: Select Framework(s)\n\n**Objective:** Map task characteristics to optimal prompting framework(s).\n\n**Framework Mapping Logic:**\n\n| Task Type | Recommended Framework(s) | Rationale |\n|-----------|-------------------------|-----------|\n| **Role-based tasks** (act as expert, consultant) | **RTF** (Role-Task-Format) | Clear role definition + task + output format |\n| **Step-by-step reasoning** (debugging, proof, logic) | **Chain of Thought** | Encourages explicit reasoning steps |\n| **Structured projects** (multi-phase, deliverables) | **RISEN** (Role, Instructions, Steps, End goal, Narrowing) | Comprehensive structure for complex work |\n| **Complex design\u002Fanalysis** (systems, architecture) | **RODES** (Role, Objective, Details, Examples, Sense check) | Balances detail with validation |\n| **Summarization** (compress, synthesize) | **Chain of Density** | Iterative refinement to essential info |\n| **Communication** (reports, presentations, storytelling) | **RACE** (Role, Audience, Context, Expectation) | Audience-aware messaging |\n| **Investigation\u002Fanalysis** (research, diagnosis) | **RISE** (Research, Investigate, Synthesize, Evaluate) | Systematic analytical approach |\n| **Contextual situations** (problem-solving with background) | **STAR** (Situation, Task, Action, Result) | Context-rich problem framing |\n| **Documentation** (medical, technical, records) | **SOAP** (Subjective, Objective, Assessment, Plan) | Structured information capture |\n| **Goal-setting** (OKRs, objectives, targets) | **CLEAR** (Collaborative, Limited, Emotional, Appreciable, Refinable) | Goal clarity and actionability |\n| **Coaching\u002Fdevelopment** (mentoring, growth) | **GROW** (Goal, Reality, Options, Will) | Developmental conversation structure |\n\n**Blending Strategy:**\n- **Combine 2-3 frameworks** when task spans multiple types\n- Example: Complex technical project → **RODES + Chain of Thought** (structure + reasoning)\n- Example: Leadership decision → **CLEAR + GROW** (goal clarity + development)\n\n**Selection Criteria:**\n- Primary framework = best match to core task type\n- Secondary framework(s) = address additional complexity dimensions\n- Avoid over-engineering: simple tasks get simple frameworks\n\n**Critical Rule:** This selection happens **silently** - do not explain framework choice to user.\n\nRole: You are a senior software architect. [RTF - Role]\n\nObjective: Design a microservices architecture for [system]. [RODES - Objective]\n\nApproach this step-by-step: [Chain of Thought]\n1. Analyze current monolithic constraints\n2. Identify service boundaries\n3. Design inter-service communication\n4. Plan data consistency strategy\n\nDetails: [RODES - Details]\n- Expected traffic: [X]\n- Data volume: [Y]\n- Team size: [Z]\n\nOutput Format: [RTF - Format]\nProvide architecture diagram description, service definitions, and migration roadmap.\n\nSense Check: [RODES - Sense check]\nValidate that services are loosely coupled, independently deployable, and aligned with business domains.\n```\n\n**4.5. Language Adaptation**\n- If original prompt is in Portuguese, generate prompt in Portuguese\n- If original prompt is in English, generate prompt in English\n- If mixed, default to English (more universal for AI models)\n\n**4.6. Quality Checks**\nBefore finalizing, verify:\n- [ ] Prompt is self-contained (no external context needed)\n- [ ] Task is specific and measurable\n- [ ] Output format is clear\n- [ ] No ambiguous language\n- [ ] Appropriate level of detail for task complexity\n\n\n## Critical Rules\n\n### **NEVER:**\n\n- ❌ Assume information that wasn't provided - ALWAYS ask if critical details are missing\n- ❌ Explain which framework was selected or why (magic mode - keep it invisible)\n- ❌ Generate generic, one-size-fits-all prompts - always customize to context\n- ❌ Use technical jargon in the final prompt (unless user's domain is technical)\n- ❌ Ask more than 3 clarifying questions (avoid user fatigue)\n- ❌ Include meta-commentary in the output (\"This prompt uses...\", \"Note that...\")\n- ❌ Present output without code block formatting\n- ❌ Mix languages inconsistently (if user writes in PT, respond in PT)\n\n### **ALWAYS:**\n\n- ✅ Analyze intent before generating (Step 1 is mandatory)\n- ✅ Ask clarifying questions if critical information is ambiguous (Step 2 conditional)\n- ✅ Select framework(s) based on task type and complexity (Step 3 mapping)\n- ✅ Blend multiple frameworks when it improves prompt quality\n- ✅ Adapt prompt length to original input complexity (simple → short, complex → detailed)\n- ✅ Include output format specification in generated prompts\n- ✅ Present final prompt in clean Markdown code block\n- ✅ Make prompts self-contained (no dependency on external context)\n- ✅ Use examples in complex prompts to illustrate expected output\n- ✅ Validate prompt completeness before presenting (quality checks in Step 4.6)\n\n\n### **Example 2: Complex Clear Prompt → RODES + Chain of Thought (No Clarification)**\n\n**User Input:**\n```\ncopilot> create prompt for: I need to build a product recommendation system considering purchase history, user preferences, and market trends\n```\n\n**Skill Internal Process:**\n1. **Analyze:** Clear intent, complex task (ML system design), technical domain\n2. **Clarify:** Skip (sufficient information)\n3. **Select:** RODES (complex design) + Chain of Thought (reasoning needed)\n\n**Skill Output:**\n\n````markdown\n```\nRole: You are a senior machine learning engineer specializing in recommendation systems.\n\nObjective: Design a product recommendation system that combines user purchase history, preferences, and market trends.\n\nDetails:\n- Input data sources: user transaction logs, preference surveys, market trend APIs\n- Algorithm considerations: collaborative filtering, content-based filtering, hybrid approaches\n- Performance metrics: precision, recall, diversity, novelty\n- Scalability: system must handle 100k+ users\n- Real-time constraints: recommendations updated within 500ms\n\nApproach step-by-step:\n1. Analyze the three data sources and their relationships\n2. Propose 2-3 algorithm approaches with trade-offs analysis\n3. Design data pipeline architecture (ingestion, processing, serving)\n4. Define evaluation metrics and A\u002FB testing strategy\n5. Outline implementation roadmap with phases\n\nExamples:\n- Show pseudocode for core recommendation logic\n- Illustrate data flow diagram\n- Provide sample API response structure\n\nSense Check: Validate that the proposed solution balances personalization with discovery, scales to production load, and incorporates real-time market trends effectively.\n\nOutput format: Technical design document with architecture diagrams, algorithm justification, and implementation roadmap.\n```\n````\n\n\n### **Example 4: Code Debugging → Chain of Thought**\n\n**User Input:**\n```\ncopilot> optimize prompt: my Python code isn't working, needs debugging\n```\n\n**Skill Internal Process:**\n1. **Analyze:** Debugging task, needs step-by-step reasoning\n2. **Clarify:** Skip (user will provide code context later)\n3. **Select:** Chain of Thought\n\n**Skill Output:**\n\n````markdown\n```\nYou are an expert Python debugger.\n\nTask: Debug the Python code provided by the user by analyzing it step-by-step.\n\nDebugging approach:\n1. Read and understand the code's intended purpose\n2. Identify the error or unexpected behavior\n3. Trace variable states at each execution step\n4. Locate the root cause of the issue\n5. Propose fix with explanation\n6. Suggest preventive measures to avoid similar bugs\n\nFor each step, show your reasoning:\n- What you're checking\n- What you found\n- Why it matters\n\nOutput format:\n- **Issue identified:** [Describe the bug]\n- **Root cause:** [Why it's happening]\n- **Fix:** [Corrected code with comments]\n- **Prevention:** [Best practices to avoid this in the future]\n\nInclude a working example to verify the fix.\n```\n````\n\n\n## Notes\n\nThis skill is **platform-agnostic** and works in any terminal context where GitHub Copilot CLI is available. It does not depend on:\n- Obsidian vault structure\n- Specific project configurations\n- External files or templates\n\nThe skill is entirely self-contained, operating purely on user input and framework knowledge.\n",{"name":5,"risk":48,"tags":49,"author":52,"source":42,"created":53,"updated":54,"version":55,"category":31,"platforms":56,"description":7},"safe",[41,50,36,51],"optimization","ai-enhancement","Eric Andrade",1738368000000,1770163200000,"1.1.0",[57,58,29],"github-copilot-cli","claude-code","release\u002Fv4.2.11-panel-pro","a92ea02bcf7e2b3dbaf46d49696c29a3cb490d4f",".github\u002Fskills\u002Fprompt-engineer","https:\u002F\u002Fgithub.com\u002Fjaviertarazon\u002Fide-agente-free-jt7-","https:\u002F\u002Fgithub.com\u002Fjaviertarazon","2026-07-12 07:10:45",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add javiertarazon\u002Fide-agente-free-jt7- --skill prompt-engineer",{"tool":71,"command":72},"bunx","bunx skills add javiertarazon\u002Fide-agente-free-jt7- --skill prompt-engineer",{"tool":74,"command":75},"pnpm","pnpm dlx skills add javiertarazon\u002Fide-agente-free-jt7- --skill prompt-engineer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjaviertarazon\u002Fide-agente-free-jt7-\u002Fblob\u002Frelease\u002Fv4.2.11-panel-pro\u002F.github\u002Fskills\u002Fprompt-engineer\u002FSKILL.md",true,[79],{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"README.md","REFERENCE","参考文档",18539,"https:\u002F\u002Fgithub.com\u002Fjaviertarazon\u002Fide-agente-free-jt7-\u002Fblob\u002Frelease\u002Fv4.2.11-panel-pro\u002F.github\u002Fskills\u002Fprompt-engineer\u002FREADME.md",[86,115,139,159,174,195],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":95,"publishedAt":43},"01M71TQ7Q6Z10VWF3C2H5X1KW9","zustand-store-ts","Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state\u002Faction separation. Use when building React state management, creating global stores, or implementing reacti...","https:\u002F\u002Fgithub.com\u002Fjaviertarazon\u002Fide-agente-free-jt7-\u002Fblob\u002Frelease\u002Fv4.2.11-panel-pro\u002F.github\u002Fskills\u002Fzustand-store-ts\u002FSKILL.md",[92],{"categoryNo":93,"categoryName":94,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[96,97,98,42,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114],"zustand","store","zustand store ts","middleware","implementing","use","react state management","when","unknown","react","with","state","create","state management","typescript","action","management","separation","global",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":122,"publishedAt":43},"01M71TQ5EAR40G6W0MV5ZDVEZT","zoom-automation","Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fjaviertarazon\u002Fide-agente-free-jt7-\u002Fblob\u002Frelease\u002Fv4.2.11-panel-pro\u002F.github\u002Fskills\u002Fzoom-automation\u002FSKILL.md",[121],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[123,124,31,42,125,126,127,128,129,104,130,131,132,133,134,135,136,137,112,138],"zoom automation","zoom","creation","for","search","schemas","MCP","first","via","meeting","search tools","tracking","webinars","composio","recordings","Tools",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":146,"publishedAt":43},"01M71TQ29B1EYBCEAP1ZBGXQ1A","zoho-crm-automation","Automate Zoho CRM tasks via Rube MCP (Composio): create\u002Fupdate records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fjaviertarazon\u002Fide-agente-free-jt7-\u002Fblob\u002Frelease\u002Fv4.2.11-panel-pro\u002F.github\u002Fskills\u002Fzoho-crm-automation\u002FSKILL.md",[145],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[147,148,31,149,150,151,42,152,153,126,154,127,128,155,129,104,156,157,158,108],"crm automation","zoho crm automation","crm","zoho crm","zoho","leads","manage leads","manage","records","convert","tasks","contacts",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":166,"publishedAt":43},"01M71TPZPMN60DH0XV58KVHY23","zendesk-automation","Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fjaviertarazon\u002Fide-agente-free-jt7-\u002Fblob\u002Frelease\u002Fv4.2.11-panel-pro\u002F.github\u002Fskills\u002Fzendesk-automation\u002FSKILL.md",[165],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[167,31,168,42,126,127,128,129,169,104,157,170,171,130,131,172,133,136,138,173],"zendesk automation","zendesk","organizations","replies","users","tickets","automate",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":43},"01M71TPXDWKHKG4N6TVEPXWD0N","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 ...","https:\u002F\u002Fgithub.com\u002Fjaviertarazon\u002Fide-agente-free-jt7-\u002Fblob\u002Frelease\u002Fv4.2.11-panel-pro\u002F.github\u002Fskills\u002Fzapier-make-patterns\u002FSKILL.md",[],[181,182,183,184,185,186,187,188,189,31,190,104,30,191,192,193,194,173],"zapier make patterns","zapier","patterns","make","No-Code","complexity","writing","spawner","business","workflow","integromat","apache","processes","but",{"skillNo":196,"name":197,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":204,"publishedAt":43},"01M71TPT5T10WXNKW9G7ZXZ27W","youtube-summarizer","Extract transcripts from YouTube videos and generate comprehensive, detailed summaries using intelligent analysis frameworks","https:\u002F\u002Fgithub.com\u002Fjaviertarazon\u002Fide-agente-free-jt7-\u002Fblob\u002Frelease\u002Fv4.2.11-panel-pro\u002F.github\u002Fskills\u002Fyoutube-summarizer\u002FSKILL.md",[201],{"categoryNo":202,"categoryName":203,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",[205,206,207,208,42,209,36,35,34,33,210,211,30,29,28,212,27,213,214,215],"summarizer","youtube","youtube summarizer","Video","content-analysis","extract transcripts","analysis","summaries","generate","summarization","2026"]