[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6F7V94397QKCDHK3CVDZMBG":3,"skill-same:01M6F7V94397QKCDHK3CVDZMBG":67},{"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":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6F7V94397QKCDHK3CVDZMBG","lindy-performance-tuning",null,"Optimize Lindy AI agent performance and response times.\nUse when improving latency, optimizing throughput,\nor reducing response times.\nTrigger with phrases like \"lindy performance\", \"lindy slow\",\n\"optimize lindy\", \"lindy latency\".","Dicklesworthstone\u002Fpi_agent_rust","Dicklesworthstone","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F35050222?v=4","01M6CG26AR942CSVMN1M5E3DSE","Jeff Emanuel","01M6CG26EPP71PSHW1VDS71121",1992,"MIT","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fsaas-packs\u002Flindy-pack\u002Fskills\u002Flindy-performance-tuning\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"performance","tuning","performance tuning","lindy performance tuning","ai agent","read","write","edit","use","optimize","latency","io","trigger","throughput","with","when","2026-11-10 10:12:30",false,"---\nname: lindy-performance-tuning\ndescription: |\n  Optimize Lindy AI agent performance and response times.\n  Use when improving latency, optimizing throughput,\n  or reducing response times.\n  Trigger with phrases like \"lindy performance\", \"lindy slow\",\n  \"optimize lindy\", \"lindy latency\".\nallowed-tools: Read, Write, Edit\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\n---\n\n# Lindy Performance Tuning\n\n## Overview\nOptimize Lindy AI agent performance for faster response times and higher throughput.\n\n## Prerequisites\n- Production Lindy integration\n- Baseline performance metrics\n- Access to monitoring tools\n\n## Instructions\n\n### Step 1: Measure Baseline Performance\n```typescript\nimport { Lindy } from '@lindy-ai\u002Fsdk';\n\ninterface PerformanceMetrics {\n  avgLatency: number;\n  p95Latency: number;\n  p99Latency: number;\n  throughput: number;\n  errorRate: number;\n}\n\nasync function measureBaseline(agentId: string, iterations = 100): Promise\u003CPerformanceMetrics> {\n  const lindy = new Lindy({ apiKey: process.env.LINDY_API_KEY });\n  const latencies: number[] = [];\n  let errors = 0;\n\n  const start = Date.now();\n\n  for (let i = 0; i \u003C iterations; i++) {\n    const runStart = Date.now();\n    try {\n      await lindy.agents.run(agentId, { input: 'Benchmark test' });\n      latencies.push(Date.now() - runStart);\n    } catch (e) {\n      errors++;\n    }\n  }\n\n  const totalTime = (Date.now() - start) \u002F 1000;\n  latencies.sort((a, b) => a - b);\n\n  return {\n    avgLatency: latencies.reduce((a, b) => a + b, 0) \u002F latencies.length,\n    p95Latency: latencies[Math.floor(latencies.length * 0.95)],\n    p99Latency: latencies[Math.floor(latencies.length * 0.99)],\n    throughput: iterations \u002F totalTime,\n    errorRate: errors \u002F iterations,\n  };\n}\n```\n\n### Step 2: Optimize Agent Instructions\n```typescript\n\u002F\u002F BEFORE: Verbose instructions (slow)\nconst slowAgent = {\n  instructions: `\n    You are a helpful assistant that should carefully consider\n    each request and provide detailed, comprehensive responses.\n    Think step by step about each query. Consider all possibilities.\n    Provide examples and explanations for everything.\n  `,\n};\n\n\u002F\u002F AFTER: Concise instructions (fast)\nconst fastAgent = {\n  instructions: `\n    Be concise. Answer directly. Skip pleasantries.\n    Format: [Answer] (1-2 sentences)\n  `,\n  config: {\n    maxTokens: 100, \u002F\u002F Limit response length\n  },\n};\n```\n\n### Step 3: Enable Streaming\n```typescript\n\u002F\u002F Non-streaming (waits for full response)\nconst result = await lindy.agents.run(agentId, { input });\nconsole.log(result.output); \u002F\u002F Logs after full response\n\n\u002F\u002F Streaming (immediate partial responses)\nconst stream = await lindy.agents.runStream(agentId, { input });\n\nfor await (const chunk of stream) {\n  process.stdout.write(chunk.delta); \u002F\u002F Real-time output\n}\n```\n\n### Step 4: Implement Caching\n```typescript\nimport NodeCache from 'node-cache';\n\nconst cache = new NodeCache({ stdTTL: 300 }); \u002F\u002F 5 minute TTL\n\nasync function runWithCache(agentId: string, input: string) {\n  const cacheKey = `${agentId}:${crypto.createHash('md5').update(input).digest('hex')}`;\n\n  \u002F\u002F Check cache\n  const cached = cache.get(cacheKey);\n  if (cached) {\n    return cached;\n  }\n\n  \u002F\u002F Run agent\n  const lindy = new Lindy({ apiKey: process.env.LINDY_API_KEY });\n  const result = await lindy.agents.run(agentId, { input });\n\n  \u002F\u002F Cache result\n  cache.set(cacheKey, result);\n\n  return result;\n}\n```\n\n### Step 5: Optimize Concurrency\n```typescript\n\u002F\u002F Poor: Sequential execution\nfor (const input of inputs) {\n  await lindy.agents.run(agentId, { input }); \u002F\u002F Slow!\n}\n\n\u002F\u002F Better: Parallel with controlled concurrency\nimport pLimit from 'p-limit';\n\nconst limit = pLimit(5); \u002F\u002F Max 5 concurrent\n\nconst results = await Promise.all(\n  inputs.map(input =>\n    limit(() => lindy.agents.run(agentId, { input }))\n  )\n);\n```\n\n## Performance Checklist\n```markdown\n[ ] Baseline metrics captured\n[ ] Instructions are concise\n[ ] Max tokens configured appropriately\n[ ] Streaming enabled for long responses\n[ ] Caching implemented for repeated queries\n[ ] Concurrency optimized\n[ ] Connection pooling enabled\n[ ] Timeout values tuned\n```\n\n## Output\n- Baseline performance metrics\n- Optimized agent configuration\n- Caching implementation\n- Concurrency patterns\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| High latency | Verbose instructions | Simplify prompts |\n| Timeouts | Response too long | Add max tokens |\n| Throttling | Too concurrent | Limit parallelism |\n\n## Examples\n\n### Complete Performance Client\n```typescript\nclass PerformantLindyClient {\n  private lindy: Lindy;\n  private cache: NodeCache;\n  private limiter: any;\n\n  constructor() {\n    this.lindy = new Lindy({ apiKey: process.env.LINDY_API_KEY });\n    this.cache = new NodeCache({ stdTTL: 300 });\n    this.limiter = pLimit(5);\n  }\n\n  async run(agentId: string, input: string) {\n    const cacheKey = `${agentId}:${input}`;\n    const cached = this.cache.get(cacheKey);\n    if (cached) return cached;\n\n    const result = await this.limiter(() =>\n      this.lindy.agents.run(agentId, { input })\n    );\n\n    this.cache.set(cacheKey, result);\n    return result;\n  }\n}\n```\n\n## Resources\n- [Lindy Performance Guide](https:\u002F\u002Fdocs.lindy.ai\u002Fperformance)\n- [Best Practices](https:\u002F\u002Fdocs.lindy.ai\u002Fbest-practices)\n- [Caching Strategies](https:\u002F\u002Fdocs.lindy.ai\u002Fperformance\u002Fcaching)\n\n## Next Steps\nProceed to `lindy-cost-tuning` for cost optimization.\n","# Lindy Performance Tuning\n\n## Overview\nOptimize Lindy AI agent performance for faster response times and higher throughput.\n\n## Prerequisites\n- Production Lindy integration\n- Baseline performance metrics\n- Access to monitoring tools\n\n## Instructions\n\n### Step 1: Measure Baseline Performance\n```typescript\nimport { Lindy } from '@lindy-ai\u002Fsdk';\n\ninterface PerformanceMetrics {\n  avgLatency: number;\n  p95Latency: number;\n  p99Latency: number;\n  throughput: number;\n  errorRate: number;\n}\n\nasync function measureBaseline(agentId: string, iterations = 100): Promise\u003CPerformanceMetrics> {\n  const lindy = new Lindy({ apiKey: process.env.LINDY_API_KEY });\n  const latencies: number[] = [];\n  let errors = 0;\n\n  const start = Date.now();\n\n  for (let i = 0; i \u003C iterations; i++) {\n    const runStart = Date.now();\n    try {\n      await lindy.agents.run(agentId, { input: 'Benchmark test' });\n      latencies.push(Date.now() - runStart);\n    } catch (e) {\n      errors++;\n    }\n  }\n\n  const totalTime = (Date.now() - start) \u002F 1000;\n  latencies.sort((a, b) => a - b);\n\n  return {\n    avgLatency: latencies.reduce((a, b) => a + b, 0) \u002F latencies.length,\n    p95Latency: latencies[Math.floor(latencies.length * 0.95)],\n    p99Latency: latencies[Math.floor(latencies.length * 0.99)],\n    throughput: iterations \u002F totalTime,\n    errorRate: errors \u002F iterations,\n  };\n}\n```\n\n### Step 2: Optimize Agent Instructions\n```typescript\n\u002F\u002F BEFORE: Verbose instructions (slow)\nconst slowAgent = {\n  instructions: `\n    You are a helpful assistant that should carefully consider\n    each request and provide detailed, comprehensive responses.\n    Think step by step about each query. Consider all possibilities.\n    Provide examples and explanations for everything.\n  `,\n};\n\n\u002F\u002F AFTER: Concise instructions (fast)\nconst fastAgent = {\n  instructions: `\n    Be concise. Answer directly. Skip pleasantries.\n    Format: [Answer] (1-2 sentences)\n  `,\n  config: {\n    maxTokens: 100, \u002F\u002F Limit response length\n  },\n};\n```\n\n### Step 3: Enable Streaming\n```typescript\n\u002F\u002F Non-streaming (waits for full response)\nconst result = await lindy.agents.run(agentId, { input });\nconsole.log(result.output); \u002F\u002F Logs after full response\n\n\u002F\u002F Streaming (immediate partial responses)\nconst stream = await lindy.agents.runStream(agentId, { input });\n\nfor await (const chunk of stream) {\n  process.stdout.write(chunk.delta); \u002F\u002F Real-time output\n}\n```\n\n### Step 4: Implement Caching\n```typescript\nimport NodeCache from 'node-cache';\n\nconst cache = new NodeCache({ stdTTL: 300 }); \u002F\u002F 5 minute TTL\n\nasync function runWithCache(agentId: string, input: string) {\n  const cacheKey = `${agentId}:${crypto.createHash('md5').update(input).digest('hex')}`;\n\n  \u002F\u002F Check cache\n  const cached = cache.get(cacheKey);\n  if (cached) {\n    return cached;\n  }\n\n  \u002F\u002F Run agent\n  const lindy = new Lindy({ apiKey: process.env.LINDY_API_KEY });\n  const result = await lindy.agents.run(agentId, { input });\n\n  \u002F\u002F Cache result\n  cache.set(cacheKey, result);\n\n  return result;\n}\n```\n\n### Step 5: Optimize Concurrency\n```typescript\n\u002F\u002F Poor: Sequential execution\nfor (const input of inputs) {\n  await lindy.agents.run(agentId, { input }); \u002F\u002F Slow!\n}\n\n\u002F\u002F Better: Parallel with controlled concurrency\nimport pLimit from 'p-limit';\n\nconst limit = pLimit(5); \u002F\u002F Max 5 concurrent\n\nconst results = await Promise.all(\n  inputs.map(input =>\n    limit(() => lindy.agents.run(agentId, { input }))\n  )\n);\n```\n\n## Performance Checklist\n```markdown\n[ ] Baseline metrics captured\n[ ] Instructions are concise\n[ ] Max tokens configured appropriately\n[ ] Streaming enabled for long responses\n[ ] Caching implemented for repeated queries\n[ ] Concurrency optimized\n[ ] Connection pooling enabled\n[ ] Timeout values tuned\n```\n\n## Output\n- Baseline performance metrics\n- Optimized agent configuration\n- Caching implementation\n- Concurrency patterns\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| High latency | Verbose instructions | Simplify prompts |\n| Timeouts | Response too long | Add max tokens |\n| Throttling | Too concurrent | Limit parallelism |\n\n## Examples\n\n### Complete Performance Client\n```typescript\nclass PerformantLindyClient {\n  private lindy: Lindy;\n  private cache: NodeCache;\n  private limiter: any;\n\n  constructor() {\n    this.lindy = new Lindy({ apiKey: process.env.LINDY_API_KEY });\n    this.cache = new NodeCache({ stdTTL: 300 });\n    this.limiter = pLimit(5);\n  }\n\n  async run(agentId: string, input: string) {\n    const cacheKey = `${agentId}:${input}`;\n    const cached = this.cache.get(cacheKey);\n    if (cached) return cached;\n\n    const result = await this.limiter(() =>\n      this.lindy.agents.run(agentId, { input })\n    );\n\n    this.cache.set(cacheKey, result);\n    return result;\n  }\n}\n```\n\n## Resources\n- [Lindy Performance Guide](https:\u002F\u002Fdocs.lindy.ai\u002Fperformance)\n- [Best Practices](https:\u002F\u002Fdocs.lindy.ai\u002Fbest-practices)\n- [Caching Strategies](https:\u002F\u002Fdocs.lindy.ai\u002Fperformance\u002Fcaching)\n\n## Next Steps\nProceed to `lindy-cost-tuning` for cost optimization.\n",{"name":5,"author":40,"license":15,"version":41,"description":42,"allowed-tools":43},"Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Optimize Lindy AI agent performance and response times.\nUse when improving latency, optimizing throughput,\nor reducing response times.\nTrigger with phrases like \"lindy performance\", \"lindy slow\",\n\"optimize lindy\", \"lindy latency\".\n","Read, Write, Edit","main","90b50ed0778745a80fd5bfb13b1843d45b9e82f7","tests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fsaas-packs\u002Flindy-pack\u002Fskills\u002Flindy-performance-tuning",233,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust","https:\u002F\u002Fgithub.com\u002FDicklesworthstone","https:\u002F\u002Fwww.jeffreyemanuel.com\u002F","Building in NY","2026-11-15 01:54:15",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add Dicklesworthstone\u002Fpi_agent_rust --skill lindy-performance-tuning",{"tool":59,"command":60},"bunx","bunx skills add Dicklesworthstone\u002Fpi_agent_rust --skill lindy-performance-tuning",{"tool":62,"command":63},"pnpm","pnpm dlx skills add Dicklesworthstone\u002Fpi_agent_rust --skill lindy-performance-tuning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fsaas-packs\u002Flindy-pack\u002Fskills\u002Flindy-performance-tuning\u002FSKILL.md",true,[],[68,101,136,159,185,212],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":73,"sourceHtmlUrl":74,"categories":75,"keywords":81,"publishedAt":100},"01M6FCR7G5A005P364Z6ZWCJDP","theme-factory","Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors\u002Ffonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fcreative-design\u002Ftheme-factory\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fcreative-design\u002Ftheme-factory\u002FSKILL.md",[76],{"categoryNo":77,"categoryName":78,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",[82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,33,98,99],"theme factory","factory","theme","docs","toolkit","generate","artifacts","SET","fly","slides","landing","html","styling","artifact","pages","themes","you","fonts","2026-11-11 15:11:14",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":105,"sourceHtmlUrl":106,"categories":107,"keywords":111,"publishedAt":35},"01M6FEGPPK0ZTKCCM0R3E3KS33","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[108],{"categoryNo":109,"categoryName":110,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000009","前端开发",[112,113,88,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,27,93,129,130,131,132,133,134,135],"web artifacts builder","web","artifacts builder","builder","frontend","css","components","react","component","routing","state management","state","shadcn","file","ui","Tools","Tailwind","single-file","simple","ui components","multi","for","jsx","suite",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":140,"sourceHtmlUrl":141,"categories":142,"keywords":147,"publishedAt":35},"01M6FEE9VTK1W4GY21AKREJXRG","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.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[143,146],{"categoryNo":144,"categoryName":145,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":109,"categoryName":110,"taxonomyType":79,"taxonomyTypeDesc":80},[148,149,150,116,151,152,113,153,86,154,126,155,156,157,158,33,133],"testing","webapp testing","webapp","screenshots","playwright","debugging","browser","logs","applications","behavior","local",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":163,"sourceHtmlUrl":164,"categories":165,"keywords":166,"publishedAt":35},"01M6FE20F7ZTQBFWKF4MPJ2SBX","neuropixels-analysis","Neuropixels neural recording analysis. Load SpikeGLX\u002FOpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen\u002FIBL curation, AI-assisted visual analysis, for Neuropixels 1.0\u002F2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FSKILL.md",[],[167,168,169,170,171,172,173,174,27,175,176,177,178,179,180,181,33,182,183,184,133,34],"analysis","neuropixels analysis","spike","metrics","data","open","quality","user","recordings","Neural","motion","visual","quality metrics","unit","sorting","curation","recording","load",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":189,"sourceHtmlUrl":190,"categories":191,"keywords":195,"publishedAt":35},"01M6FDP0PDK6F1GGX395C7625Z","skill-creator","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fskill-creator\u002FSKILL.md",[192],{"categoryNo":193,"categoryName":194,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000023","Skill与智能体开发",[196,197,198,199,200,201,202,203,204,205,206,207,208,209,33,133,210,34,211],"skill creator","creator","workflows","create","update","capabilities","knowledge","tool","integrations","specialized","guide","new skill","existing skill","users","Existing","new",{"skillNo":213,"name":214,"nameZh":6,"description":215,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":216,"sourceHtmlUrl":217,"categories":218,"keywords":220,"publishedAt":35},"01M6FDM8Y7VK7NYG9SM7QPA3PW","notebooklm","Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fnotebooklm\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fnotebooklm\u002FSKILL.md",[219],{"categoryNo":193,"categoryName":194,"taxonomyType":79,"taxonomyTypeDesc":80},[214,221,222,223,224,225,226,154,227,228,27,229,230,231,232,133,233],"google","browser automation","gemini","automation","auth","code","library","management","only","document","query","Citation","source"]