[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72A71DQRCQDP32W8N89JPV2":3,"skill-same:01M72A71DQRCQDP32W8N89JPV2":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":13,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M72A71DQRCQDP32W8N89JPV2","skill-router",null,"Use when the user is unsure which skill to use or where to start. Interviews the user with targeted questions and recommends the best skill(s) from the installed library for their goal.","Sansar35\u002Fclaude-agent","Sansar35","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F145020281?v=4","01M724CQ2SCC86MGNSD87D0D4K","01M724CQ3965G9WJ3QXE3AJ5YY",1,"MIT","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fantigravity\u002Fskill-router\u002FSKILL.md",[],[],"2026-11-10 18:39:20",false,"---\nname: skill-router\ndescription: \"Use when the user is unsure which skill to use or where to start. Interviews the user with targeted questions and recommends the best skill(s) from the installed library for their goal.\"\nrisk: safe\nsource: self\n---\n\n# Skill Router\n\n## When to Use\nUse this skill when:\n- The user says \"I don't know where to start\" or \"which skill should I use\"\n- The user has a vague goal without a clear method\n- The user asks \"what should I use for...\" or \"I'm not sure how to approach this\"\n- The user is new to the skill library and needs guidance\n\n## Goal\n\nHelp users who are unsure of what they want to do or which skill to use.\nInterview them with a short structured conversation, then recommend the most\nrelevant skill(s) from the installed library — with a clear explanation of\nwhy each skill fits and exactly how to invoke it.\n\n---\n\n## Instructions\n\n### Step 1 — Acknowledge and open the interview\n\nRespond warmly and tell the user you'll ask a few quick questions to find\nthe right skill for them. Do NOT suggest any skills yet.\n\nExample opener:\n> \"No problem — let me ask you a few quick questions so I can point you to\n> exactly the right skill.\"\n\n---\n\n### Step 2 — Ask the Funnel Questions (one at a time, in order)\n\nAsk only what you need. If an earlier answer makes a later question\nirrelevant, skip it.\n\n**Q1 — What is the broad area of the task?**\nPresent these as numbered options:\n1. Building \u002F coding something (app, feature, component, script)\n2. Fixing or debugging something that's broken\n3. Security, pentesting, or vulnerability assessment\n4. AI agents, LLMs, or automation pipelines\n5. Marketing, SEO, content, or growth\n6. DevOps, infrastructure, deployment, or git\n7. Design, UI\u002FUX, or creative output\n8. Planning, strategy, or documentation\n9. Something else (ask them to describe it)\n\n**Q2 — How specific is the task?**\n1. I have a clear spec \u002F I know exactly what I want built\n2. I have a rough idea but need help shaping it\n3. I'm totally starting from scratch with no clear direction\n\n**Q3 — What tech stack or domain is involved?** (only ask if relevant)\nExamples: React \u002F Next.js, Node.js, Python, AWS, Stripe, AI\u002FLLM, no-code, etc.\nIf they say \"not sure\" or \"any\", that's fine — move on.\n\n**Q4 — Do you want to work autonomously (agent does everything) or\ncollaboratively (you stay in the loop)?**\n1. Fully autonomous — just go\n2. Collaborative — I want to review\u002Fapprove steps\n3. Not sure yet\n\n---\n\n### Step 3 — Recommend skills\n\nBased on their answers, recommend **1 primary skill** and up to **2 secondary\nskills**. Structure your recommendation exactly like this:\n\n**✅ Primary Skill: `@skill-name`**\n*Why:* [1–2 sentences explaining why this is the best fit for what they described]\n*Invoke it like this:*\n```\n@skill-name [paste their goal here]\n```\n\n**🔁 Also consider:**\n- `@skill-name-2` — [one sentence on when to layer this in]\n- `@skill-name-3` — [one sentence on when to layer this in]\n\n---\n\n### Step 4 — Offer a ready-made prompt\n\nAfter the recommendation, offer to write them a ready-to-use prompt they\ncan paste directly into Antigravity. Ask:\n\n> \"Want me to write the full prompt for you so you can just paste it in?\"\n\nIf yes, compose a complete, specific prompt using the recommended skill and\neverything you learned about their goal from the interview.\n\n---\n\n## Example Interaction\n\n```\nUser: @skill-router I want to build something but I'm not sure where to start\n\nAgent: No problem — let me ask a few quick questions.\n       What is the broad area?\n       (1) Building  (2) Debugging  (3) Security  (4) AI\u002FLLM\n       (5) Marketing  (6) DevOps  (7) Design  (8) Planning\n\nUser: 1 - building something\n\nAgent: How specific is the task?\n       (1) Clear spec  (2) Rough idea  (3) Starting from scratch\n\nUser: 2 - rough idea\n\nAgent: What tech stack? (React, Node, Python, etc. — or \"not sure\")\n\nUser: Next.js\n\nAgent: ✅ Primary Skill: @brainstorming\n       Why: You have a rough idea that needs shaping before building.\n       Brainstorming asks structured questions and produces a clear spec.\n\n       @brainstorming help me design a [your app idea] using Next.js\n\n       🔁 Also consider:\n       - @plan-writing — once brainstorming produces a spec, break it into tasks\n       - @senior-fullstack — when you are ready to start building\n\n       Want me to write the full prompt for you?\n```\n\n---\n\n## Skill Routing Reference\n\n### Building a full product or app from scratch\n- Primary: `@app-builder`\n- If they want to plan first: `@brainstorming` → `@plan-writing` → `@app-builder`\n- If they want it fully autonomous: `@loki-mode`\n\n### Building a specific frontend feature \u002F UI\n- Primary: `@senior-fullstack` or `@frontend-design`\n- Stack-specific: `@react-patterns`, `@nextjs-best-practices`, `@tailwind-patterns`\n- If they want a full design system: `@ui-ux-pro-max` + `@core-components`\n\n### Building a backend API or service\n- Primary: `@backend-dev-guidelines`\n- Stack-specific: `@nodejs-best-practices`, `@python-patterns`, `@nestjs-expert`\n- API design: `@api-patterns`\n- Database: `@database-design` + `@prisma-expert`\n\n### Debugging something broken\n- Primary: `@systematic-debugging`\n- If tests are failing: `@test-fixing`\n- If it's a code quality issue: `@clean-code`\n\n### Writing tests \u002F TDD\n- Primary: `@tdd`\n- For Playwright\u002Fbrowser tests: `@playwright-skill`\n- For Jest patterns: `@testing-patterns`\n\n### Integrating a third-party service\n- Payments: `@stripe-integration`\n- Auth: `@clerk-auth` or `@nextjs-supabase-auth`\n- Database: `@neon-postgres` or `@firebase`\n- Messaging: `@twilio-communications`\n- Bots: `@slack-bot-builder`, `@discord-bot-architect`, `@telegram-bot-builder`\n- File storage: `@file-uploads`\n- Analytics: `@analytics-tracking`\n\n### AI \u002F LLM \u002F agents\n- Architecture: `@ai-agents-architect`\n- RAG pipelines: `@rag-engineer`\n- Prompts: `@prompt-engineer`\n- Multi-agent: `@langgraph` or `@crewai`\n- Observability: `@langfuse`\n- Voice: `@voice-agents`\n\n### Security \u002F pentesting\n- Start here: `@ethical-hacking-methodology` + `@pentest-checklist`\n- Web app testing: `@burp-suite-testing`, `@sql-injection-testing`, `@xss-html-injection`\n- Network\u002Finfra: `@aws-penetration-testing`, `@linux-privilege-escalation`\n- Reference: `@top-web-vulnerabilities`\n\n### DevOps \u002F infrastructure \u002F deployment\n- Docker: `@docker-expert`\n- Cloud: `@aws-serverless`, `@gcp-cloud-run`, `@vercel-deployment`\n- Git workflow: `@git-pushing`, `@using-git-worktrees`, `@github-workflow-automation`\n- Scripting: `@linux-shell-scripting`\n\n### Marketing \u002F growth \u002F SEO\n- Copy: `@copywriting`\n- Landing pages: `@page-cro`\n- SEO: `@seo-fundamentals` + `@seo-audit`\n- Email: `@email-sequence`\n- Ads: `@paid-ads`\n- Launch: `@launch-strategy`\n\n### Planning \u002F architecture \u002F strategy\n- Quick plan: `@concise-planning`\n- Full plan: `@plan-writing` → `@executing-plans`\n- Architecture: `@software-architecture` or `@senior-architect`\n- Product strategy: `@product-manager-toolkit`\n\n### Creative \u002F design \u002F visuals\n- UI: `@frontend-design`\n- Data viz: `@claude-d3js-skill`\n- Generative art: `@algorithmic-art`\n- Presentations: `@pptx-official`\n\n### Fully autonomous \u002F parallel execution\n- Full startup mode: `@loki-mode`\n- Independent parallel tasks: `@dispatching-parallel-agents`\n- Plan then execute: `@subagent-driven-development`\n\n### Document creation\n- Word doc: `@docx-official`\n- PDF: `@pdf-official`\n- Spreadsheet: `@xlsx-official`\n- Presentation: `@pptx-official`\n\n---\n\n## Constraints\n\n- Never recommend more than 1 primary skill and 2 secondary skills at a time.\n- Always include the exact `@invoke` syntax so users can copy-paste it.\n- If the user's goal spans multiple categories, pick the most upstream skill\n  (e.g. `@brainstorming` before `@senior-fullstack`).\n- Do not overwhelm the user with the full skill list. Recommend only what is\n  relevant to their specific answers.\n- If the user is totally lost, default to `@brainstorming` for open-ended\n  goals, or `@app-builder` for anything involving building something.\n- After recommending, always offer to write a ready-made prompt for them.\n\n---\n\n## Limitations\n\n- Only recommends skills from the installed library. If a skill is not\n  installed, the recommendation may not work.\n- Routing is based on natural language matching. Highly ambiguous goals\n  may require follow-up clarification.\n- Does not execute the recommended skill — it only recommends it. The user\n  must invoke the skill themselves.\n- The routing reference covers the most common skills but does not include\n  every skill in the library.","# Skill Router\n\n## When to Use\nUse this skill when:\n- The user says \"I don't know where to start\" or \"which skill should I use\"\n- The user has a vague goal without a clear method\n- The user asks \"what should I use for...\" or \"I'm not sure how to approach this\"\n- The user is new to the skill library and needs guidance\n\n## Goal\n\nHelp users who are unsure of what they want to do or which skill to use.\nInterview them with a short structured conversation, then recommend the most\nrelevant skill(s) from the installed library — with a clear explanation of\nwhy each skill fits and exactly how to invoke it.\n\n---\n\n## Instructions\n\n### Step 1 — Acknowledge and open the interview\n\nRespond warmly and tell the user you'll ask a few quick questions to find\nthe right skill for them. Do NOT suggest any skills yet.\n\nExample opener:\n> \"No problem — let me ask you a few quick questions so I can point you to\n> exactly the right skill.\"\n\n---\n\n### Step 2 — Ask the Funnel Questions (one at a time, in order)\n\nAsk only what you need. If an earlier answer makes a later question\nirrelevant, skip it.\n\n**Q1 — What is the broad area of the task?**\nPresent these as numbered options:\n1. Building \u002F coding something (app, feature, component, script)\n2. Fixing or debugging something that's broken\n3. Security, pentesting, or vulnerability assessment\n4. AI agents, LLMs, or automation pipelines\n5. Marketing, SEO, content, or growth\n6. DevOps, infrastructure, deployment, or git\n7. Design, UI\u002FUX, or creative output\n8. Planning, strategy, or documentation\n9. Something else (ask them to describe it)\n\n**Q2 — How specific is the task?**\n1. I have a clear spec \u002F I know exactly what I want built\n2. I have a rough idea but need help shaping it\n3. I'm totally starting from scratch with no clear direction\n\n**Q3 — What tech stack or domain is involved?** (only ask if relevant)\nExamples: React \u002F Next.js, Node.js, Python, AWS, Stripe, AI\u002FLLM, no-code, etc.\nIf they say \"not sure\" or \"any\", that's fine — move on.\n\n**Q4 — Do you want to work autonomously (agent does everything) or\ncollaboratively (you stay in the loop)?**\n1. Fully autonomous — just go\n2. Collaborative — I want to review\u002Fapprove steps\n3. Not sure yet\n\n---\n\n### Step 3 — Recommend skills\n\nBased on their answers, recommend **1 primary skill** and up to **2 secondary\nskills**. Structure your recommendation exactly like this:\n\n**✅ Primary Skill: `@skill-name`**\n*Why:* [1–2 sentences explaining why this is the best fit for what they described]\n*Invoke it like this:*\n```\n@skill-name [paste their goal here]\n```\n\n**🔁 Also consider:**\n- `@skill-name-2` — [one sentence on when to layer this in]\n- `@skill-name-3` — [one sentence on when to layer this in]\n\n---\n\n### Step 4 — Offer a ready-made prompt\n\nAfter the recommendation, offer to write them a ready-to-use prompt they\ncan paste directly into Antigravity. Ask:\n\n> \"Want me to write the full prompt for you so you can just paste it in?\"\n\nIf yes, compose a complete, specific prompt using the recommended skill and\neverything you learned about their goal from the interview.\n\n---\n\n## Example Interaction\n\n```\nUser: @skill-router I want to build something but I'm not sure where to start\n\nAgent: No problem — let me ask a few quick questions.\n       What is the broad area?\n       (1) Building  (2) Debugging  (3) Security  (4) AI\u002FLLM\n       (5) Marketing  (6) DevOps  (7) Design  (8) Planning\n\nUser: 1 - building something\n\nAgent: How specific is the task?\n       (1) Clear spec  (2) Rough idea  (3) Starting from scratch\n\nUser: 2 - rough idea\n\nAgent: What tech stack? (React, Node, Python, etc. — or \"not sure\")\n\nUser: Next.js\n\nAgent: ✅ Primary Skill: @brainstorming\n       Why: You have a rough idea that needs shaping before building.\n       Brainstorming asks structured questions and produces a clear spec.\n\n       @brainstorming help me design a [your app idea] using Next.js\n\n       🔁 Also consider:\n       - @plan-writing — once brainstorming produces a spec, break it into tasks\n       - @senior-fullstack — when you are ready to start building\n\n       Want me to write the full prompt for you?\n```\n\n---\n\n## Skill Routing Reference\n\n### Building a full product or app from scratch\n- Primary: `@app-builder`\n- If they want to plan first: `@brainstorming` → `@plan-writing` → `@app-builder`\n- If they want it fully autonomous: `@loki-mode`\n\n### Building a specific frontend feature \u002F UI\n- Primary: `@senior-fullstack` or `@frontend-design`\n- Stack-specific: `@react-patterns`, `@nextjs-best-practices`, `@tailwind-patterns`\n- If they want a full design system: `@ui-ux-pro-max` + `@core-components`\n\n### Building a backend API or service\n- Primary: `@backend-dev-guidelines`\n- Stack-specific: `@nodejs-best-practices`, `@python-patterns`, `@nestjs-expert`\n- API design: `@api-patterns`\n- Database: `@database-design` + `@prisma-expert`\n\n### Debugging something broken\n- Primary: `@systematic-debugging`\n- If tests are failing: `@test-fixing`\n- If it's a code quality issue: `@clean-code`\n\n### Writing tests \u002F TDD\n- Primary: `@tdd`\n- For Playwright\u002Fbrowser tests: `@playwright-skill`\n- For Jest patterns: `@testing-patterns`\n\n### Integrating a third-party service\n- Payments: `@stripe-integration`\n- Auth: `@clerk-auth` or `@nextjs-supabase-auth`\n- Database: `@neon-postgres` or `@firebase`\n- Messaging: `@twilio-communications`\n- Bots: `@slack-bot-builder`, `@discord-bot-architect`, `@telegram-bot-builder`\n- File storage: `@file-uploads`\n- Analytics: `@analytics-tracking`\n\n### AI \u002F LLM \u002F agents\n- Architecture: `@ai-agents-architect`\n- RAG pipelines: `@rag-engineer`\n- Prompts: `@prompt-engineer`\n- Multi-agent: `@langgraph` or `@crewai`\n- Observability: `@langfuse`\n- Voice: `@voice-agents`\n\n### Security \u002F pentesting\n- Start here: `@ethical-hacking-methodology` + `@pentest-checklist`\n- Web app testing: `@burp-suite-testing`, `@sql-injection-testing`, `@xss-html-injection`\n- Network\u002Finfra: `@aws-penetration-testing`, `@linux-privilege-escalation`\n- Reference: `@top-web-vulnerabilities`\n\n### DevOps \u002F infrastructure \u002F deployment\n- Docker: `@docker-expert`\n- Cloud: `@aws-serverless`, `@gcp-cloud-run`, `@vercel-deployment`\n- Git workflow: `@git-pushing`, `@using-git-worktrees`, `@github-workflow-automation`\n- Scripting: `@linux-shell-scripting`\n\n### Marketing \u002F growth \u002F SEO\n- Copy: `@copywriting`\n- Landing pages: `@page-cro`\n- SEO: `@seo-fundamentals` + `@seo-audit`\n- Email: `@email-sequence`\n- Ads: `@paid-ads`\n- Launch: `@launch-strategy`\n\n### Planning \u002F architecture \u002F strategy\n- Quick plan: `@concise-planning`\n- Full plan: `@plan-writing` → `@executing-plans`\n- Architecture: `@software-architecture` or `@senior-architect`\n- Product strategy: `@product-manager-toolkit`\n\n### Creative \u002F design \u002F visuals\n- UI: `@frontend-design`\n- Data viz: `@claude-d3js-skill`\n- Generative art: `@algorithmic-art`\n- Presentations: `@pptx-official`\n\n### Fully autonomous \u002F parallel execution\n- Full startup mode: `@loki-mode`\n- Independent parallel tasks: `@dispatching-parallel-agents`\n- Plan then execute: `@subagent-driven-development`\n\n### Document creation\n- Word doc: `@docx-official`\n- PDF: `@pdf-official`\n- Spreadsheet: `@xlsx-official`\n- Presentation: `@pptx-official`\n\n---\n\n## Constraints\n\n- Never recommend more than 1 primary skill and 2 secondary skills at a time.\n- Always include the exact `@invoke` syntax so users can copy-paste it.\n- If the user's goal spans multiple categories, pick the most upstream skill\n  (e.g. `@brainstorming` before `@senior-fullstack`).\n- Do not overwhelm the user with the full skill list. Recommend only what is\n  relevant to their specific answers.\n- If the user is totally lost, default to `@brainstorming` for open-ended\n  goals, or `@app-builder` for anything involving building something.\n- After recommending, always offer to write a ready-made prompt for them.\n\n---\n\n## Limitations\n\n- Only recommends skills from the installed library. If a skill is not\n  installed, the recommendation may not work.\n- Routing is based on natural language matching. Highly ambiguous goals\n  may require follow-up clarification.\n- Does not execute the recommended skill — it only recommends it. The user\n  must invoke the skill themselves.\n- The routing reference covers the most common skills but does not include\n  every skill in the library.",{"name":5,"risk":23,"source":24,"description":7},"safe","self","main","d046d088ce5a79a083f0abc0fe1b7ded73bc5b1f","claude-config\u002Fskills\u002Fantigravity\u002Fskill-router","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent","https:\u002F\u002Fgithub.com\u002FSansar35","2026-05-10 16:04:53",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add Sansar35\u002Fclaude-agent --skill skill-router",{"tool":37,"command":38},"bunx","bunx skills add Sansar35\u002Fclaude-agent --skill skill-router",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Sansar35\u002Fclaude-agent --skill skill-router","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fantigravity\u002Fskill-router\u002FSKILL.md",true,[],[46,53,60,67,74,82],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M72DVAN1JYEA302MT0C5MGD6","zustand-store-ts","Create Zustand stores following established patterns with proper TypeScript types and middleware.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzustand-store-ts\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M72DV8J5NBRRM4RPDFRV95N7","zod-validation-expert","Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzod-validation-expert\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M72DV5EMHW0BHP9BZ167MDCB","zinc-database","Access ZINC (230M+ purchasable compounds). Search by ZINC ID\u002FSMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzinc-database\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M72DV216QY0E693ZPEVQ0DBS","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":78,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M72DTXQREMCRKA8NHCVKHN4W","zapier-workflows","Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to \"run\" any process. Also handles Perplexity-based research and Google Sheets data tracking.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-workflows\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-workflows\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M72DTT17TBSJ0Y8J2XZ4C9TZ","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","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-make-patterns\u002FSKILL.md",[],[]]