[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79A1TK3TR3B4R0YXZP2G62V":3,"skill-same:01M79A1TK3TR3B4R0YXZP2G62V":157},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":14,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":52,"install":53,"resources":66},"01M79A1TK3TR3B4R0YXZP2G62V","claude-api",null,"Anthropic Messages API (Claude API) for integrations, streaming, prompt caching, tool use, vision. Use for chatbots, assistants, or encountering rate limits, 429 errors.","Elogic360\u002Fsoftware-factory","Elogic360","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F156535519?v=4","01M74NH3F0RB13PWB7JZDE2V80","elogic360","01M74NH3FPC65082MDZVMFHDM3",0,"MIT","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: claude-api\ndescription: \"Anthropic Messages API (Claude API) for integrations, streaming, prompt caching, tool use, vision. Use for chatbots, assistants, or encountering rate limits, 429 errors.\"\nlicense: MIT\nmetadata:\n  version: \"2.0.0\"\n  last_verified: \"2025-11-21\"\n  sdk_version: \"@anthropic-ai\u002Fsdk@0.70.1\"\n  templates_included: 12\n  references_included: 7\n  keywords:\n    - claude api\n    - anthropic api\n    - messages api\n    - \"@anthropic-ai\u002Fsdk\"\n    - claude streaming\n    - prompt caching\n    - tool use\n    - vision\n    - extended thinking\n    - claude 3.5 sonnet\n    - claude 3.7 sonnet\n    - claude sonnet 4\n    - function calling\n    - SSE\n    - rate limits\n    - 429 errors\n---\n# Claude API (Anthropic Messages API)\n\n**Status**: Production Ready | **SDK**: @anthropic-ai\u002Fsdk@0.70.1\n\n---\n\n## Quick Start (5 Minutes)\n\n### Node.js\n\n```typescript\nimport Anthropic from '@anthropic-ai\u002Fsdk';\n\nconst client = new Anthropic({\n  apiKey: process.env.ANTHROPIC_API_KEY,\n});\n\nconst message = await client.messages.create({\n  model: 'claude-sonnet-4-5-20250929',\n  max_tokens: 1024,\n  messages: [\n    { role: 'user', content: 'Hello, Claude!' },\n  ],\n});\n\nconsole.log(message.content[0].text);\n```\n\n### Cloudflare Workers\n\n```typescript\nconst response = await fetch('https:\u002F\u002Fapi.anthropic.com\u002Fv1\u002Fmessages', {\n  method: 'POST',\n  headers: {\n    'x-api-key': env.ANTHROPIC_API_KEY,\n    'anthropic-version': '2023-06-01',\n    'content-type': 'application\u002Fjson',\n  },\n  body: JSON.stringify({\n    model: 'claude-sonnet-4-5-20250929',\n    max_tokens: 1024,\n    messages: [{ role: 'user', content: 'Hello!' }],\n  }),\n});\n\nconst data = await response.json();\nconsole.log(data.content[0].text);\n```\n\n**Load `references\u002Fsetup-guide.md` for complete setup with streaming, caching, and tools.**\n\n---\n\n## Critical Rules\n\n### Always Do ✅\n\n1. **Use environment variables** for API keys (NEVER hardcode)\n2. **Set max_tokens** explicitly (required parameter)\n3. **Pin model version** (`claude-sonnet-4-5-20250929`, not `claude-3-5-sonnet-latest`)\n4. **Enable prompt caching** for repeated content (90% cost savings)\n5. **Stream long responses** (`stream: true`) for better UX\n6. **Handle errors** - Implement retry logic for 429, 529 errors\n7. **Validate inputs** - Sanitize user messages before sending\n8. **Monitor costs** - Track token usage\n9. **Set timeouts** - Prevent hanging requests\n10. **Use tool use properly** - Return tool_result in follow-up message\n\n### Never Do ❌\n\n1. **Never expose API key** in client-side code\n2. **Never skip max_tokens** - API will error without it\n3. **Never ignore stop_reason** - Check for `tool_use`, `end_turn`, `max_tokens`\n4. **Never assume single content block** - `content` is an array\n5. **Never use outdated models** - Pin to specific version\n6. **Never skip error handling** - API calls can fail\n7. **Never mix message roles** - Alternate user\u002Fassistant correctly\n8. **Never ignore rate limits** - Implement exponential backoff\n9. **Never store API keys** in logs or databases\n10. **Never skip input validation** - Prevent injection attacks\n\n---\n\n## Top 3 Errors (Prevent 80% of Issues)\n\n### Error #1: Rate Limit 429\n\n**Symptom**: `429 Too Many Requests: Number of request tokens has exceeded your per-minute rate limit`\n\n**Solution**: Implement exponential backoff with retry-after header\n\n```typescript\nasync function handleRateLimit(requestFn, maxRetries = 3) {\n  for (let attempt = 0; attempt \u003C maxRetries; attempt++) {\n    try {\n      return await requestFn();\n    } catch (error) {\n      if (error.status === 429) {\n        const retryAfter = error.response?.headers?.['retry-after'];\n        const delay = retryAfter ? parseInt(retryAfter) * 1000 : 1000 * Math.pow(2, attempt);\n        await new Promise(resolve => setTimeout(resolve, delay));\n      } else {\n        throw error;\n      }\n    }\n  }\n}\n```\n\n**Prevention**: Monitor rate limit headers, upgrade tier, implement backoff\n\n---\n\n### Error #2: Prompt Caching Not Activating\n\n**Symptom**: High costs despite `cache_control` blocks, `cache_read_input_tokens: 0`\n\n**Solution**: Place `cache_control` on LAST block with >= 1024 tokens\n\n```typescript\n\u002F\u002F ❌ Wrong - cache_control not at end\n{\n  type: 'text',\n  text: DOCUMENT,\n  cache_control: { type: 'ephemeral' },  \u002F\u002F Wrong position\n},\n{\n  type: 'text',\n  text: 'Additional text',\n}\n\n\u002F\u002F ✅ Correct - cache_control at end\n{\n  type: 'text',\n  text: DOCUMENT + '\\n\\nAdditional text',\n  cache_control: { type: 'ephemeral' },  \u002F\u002F Correct position\n}\n```\n\n**Prevention**: Ensure content >= 1024 tokens, keep cached content identical, monitor usage\n\n**Load `references\u002Fprompt-caching-guide.md` for complete caching strategy.**\n\n---\n\n### Error #3: Tool Use Response Format Errors\n\n**Symptom**: `invalid_request_error: tools[0].input_schema is invalid`\n\n**Solution**: Valid tool schema with proper JSON Schema\n\n```typescript\n\u002F\u002F ✅ Valid tool schema\n{\n  name: 'get_weather',\n  description: 'Get current weather',\n  input_schema: {\n    type: 'object',           \u002F\u002F Must be 'object'\n    properties: {\n      location: {\n        type: 'string',       \u002F\u002F Valid JSON Schema types\n        description: 'City'   \u002F\u002F Optional but recommended\n      }\n    },\n    required: ['location']    \u002F\u002F List required fields\n  }\n}\n\n\u002F\u002F ✅ Valid tool result\n{\n  type: 'tool_result',\n  tool_use_id: block.id,      \u002F\u002F Must match tool_use id\n  content: JSON.stringify(result)  \u002F\u002F Convert to string\n}\n```\n\n**Prevention**: Validate schemas, match tool_use_id exactly, stringify results\n\n**Load `references\u002Ftool-use-patterns.md` + `references\u002Ftop-errors.md` for all 12 errors.**\n\n---\n\n## Common Use Cases (Quick Patterns)\n\n### Streaming Responses\n\n```typescript\nconst stream = await client.messages.stream({\n  model: 'claude-sonnet-4-5-20250929',\n  max_tokens: 1024,\n  messages: [{ role: 'user', content: 'Write a story.' }],\n});\n\nfor await (const event of stream) {\n  if (event.type === 'content_block_delta' && event.delta.type === 'text_delta') {\n    process.stdout.write(event.delta.text);\n  }\n}\n```\n\n**Load**: `templates\u002Fstreaming-chat.ts`\n\n---\n\n### Prompt Caching (90% Cost Savings)\n\n```typescript\nconst message = await client.messages.create({\n  model: 'claude-sonnet-4-5-20250929',\n  max_tokens: 1024,\n  system: [\n    {\n      type: 'text',\n      text: 'Long system prompt...',\n      cache_control: { type: 'ephemeral' },\n    },\n  ],\n  messages: [{ role: 'user', content: 'Question?' }],\n});\n```\n\n**Cache lasts 5 minutes, 90% savings on cached tokens**\n\n**Load**: `references\u002Fprompt-caching-guide.md` + `templates\u002Fprompt-caching.ts`\n\n---\n\n### Tool Use (Function Calling)\n\n```typescript\nconst message = await client.messages.create({\n  model: 'claude-sonnet-4-5-20250929',\n  max_tokens: 1024,\n  tools: [{\n    name: 'get_weather',\n    description: 'Get weather for a location',\n    input_schema: {\n      type: 'object',\n      properties: { location: { type: 'string' } },\n      required: ['location'],\n    },\n  }],\n  messages: [{ role: 'user', content: 'Weather in SF?' }],\n});\n\nif (message.stop_reason === 'tool_use') {\n  const toolUse = message.content.find(b => b.type === 'tool_use');\n  \u002F\u002F Execute tool and send result back...\n}\n```\n\n**Load**: `references\u002Ftool-use-patterns.md` + `templates\u002Ftool-use-basic.ts`\n\n---\n\n### Vision (Image Understanding)\n\n```typescript\nconst message = await client.messages.create({\n  model: 'claude-sonnet-4-5-20250929',\n  max_tokens: 1024,\n  messages: [{\n    role: 'user',\n    content: [\n      {\n        type: 'image',\n        source: {\n          type: 'base64',\n          media_type: 'image\u002Fjpeg',\n          data: base64Image,\n        },\n      },\n      { type: 'text', text: 'What is in this image?' },\n    ],\n  }],\n});\n```\n\n**Supports**: JPEG, PNG, WebP, GIF (max 5MB)\n\n**Load**: `references\u002Fvision-capabilities.md` + `templates\u002Fvision-image.ts`\n\n---\n\n### Extended Thinking Mode\n\n```typescript\nconst message = await client.messages.create({\n  model: 'claude-sonnet-4-5-20250929',\n  max_tokens: 4096,\n  thinking: {\n    type: 'enabled',\n    budget_tokens: 2000,\n  },\n  messages: [{ role: 'user', content: 'Solve complex problem...' }],\n});\n\nconst thinking = message.content.find(b => b.type === 'thinking')?.thinking;\nconst answer = message.content.find(b => b.type === 'text')?.text;\n```\n\n**Load**: `templates\u002Fextended-thinking.ts`\n\n---\n\n## Model Versions (Current)\n\n**Latest models:**\n- `claude-sonnet-4-5-20250929` - Recommended (best performance)\n- `claude-sonnet-4-20250514` - Stable version\n- `claude-3-7-sonnet-20250219` - Previous generation\n- `claude-3-5-sonnet-20241022` - Legacy\n\n**Always pin to specific version** (not `-latest` suffix)\n\n---\n\n## When to Load References\n\n### Load `references\u002Fsetup-guide.md` when:\n- First-time Claude API user needing complete setup walkthrough\n- Setting up Node.js or Cloudflare Workers from scratch\n- Need production deployment checklist and platform-specific tips\n- Troubleshooting basic setup issues (API keys, authentication, environment)\n\n### Load `references\u002Fprompt-caching-guide.md` when:\n- Want to reduce costs by 90% on repeated content\n- Using large system prompts, documents, or codebases in context\n- Need detailed caching strategy with benchmarks and cost calculations\n- Optimizing multi-turn conversations with conversation history caching\n- Troubleshooting cache activation issues or cache misses\n\n### Load `references\u002Ftool-use-patterns.md` when:\n- Implementing function calling and tool definitions\n- Need tool execution loop patterns and multi-turn tool use\n- Want Zod validation examples for type-safe tools\n- Troubleshooting tool use response format errors\n\n### Load `references\u002Fvision-capabilities.md` when:\n- Processing images with Claude (OCR, analysis, description)\n- Need image format requirements and validation logic\n- Want vision use cases and best practices\n- Combining vision with tools or prompt caching\n\n### Load `references\u002Fapi-reference.md` when:\n- Need complete API parameter reference and request\u002Fresponse schemas\n- Looking up specific fields or content block types\n- Want endpoint details, authentication headers, or model IDs\n- Need streaming event types and SSE format details\n\n### Load `references\u002Ftop-errors.md` when:\n- Encountering API errors (all 12 documented errors with solutions)\n- Need error code reference (400, 401, 429, 529, etc.)\n- Want comprehensive prevention strategies\n- Implementing robust error handling and retry logic\n\n### Load `references\u002Frate-limits.md` when:\n- Planning high-volume usage and scaling strategy\n- Encountering 429 rate limit errors repeatedly\n- Need tier limits information and upgrade path\n- Optimizing request patterns to stay within limits\n\n---\n\n## Using Bundled Resources\n\n### References (references\u002F)\n\n- **setup-guide.md** - Complete setup (Node.js + Cloudflare Workers + Next.js)\n- **api-reference.md** - Complete API parameter reference + schemas\n- **prompt-caching-guide.md** - 90% cost savings guide + benchmarks\n- **tool-use-patterns.md** - Function calling patterns + Zod examples\n- **vision-capabilities.md** - Image understanding guide + validation\n- **top-errors.md** - All 12 errors with solutions + prevention\n- **rate-limits.md** - Limits by tier + best practices\n\n### Templates (templates\u002F)\n\n- **basic-chat.ts** - Simple chat example\n- **streaming-chat.ts** - Streaming implementation with SSE\n- **prompt-caching.ts** - Caching example with benchmarks\n- **tool-use-basic.ts** - Basic tool use pattern\n- **tool-use-advanced.ts** - Advanced multi-turn tool patterns\n- **vision-image.ts** - Vision example with validation\n- **extended-thinking.ts** - Extended thinking mode\n- **error-handling.ts** - Complete error handling\n- **nodejs-example.ts** - Complete Node.js app\n- **cloudflare-worker.ts** - Complete CF Worker\n- **nextjs-api-route.ts** - Next.js API route\n- **package.json** - Dependencies\n\n---\n\n## Platform Integration\n\n**Node.js**: `bun add @anthropic-ai\u002Fsdk` → Use templates: `nodejs-example.ts`, `basic-chat.ts`\n\n**Cloudflare Workers**: Use fetch API → Use templates: `cloudflare-worker.ts`\n\n**Next.js**: `bun add @anthropic-ai\u002Fsdk` → Use templates: `nextjs-api-route.ts`\n\n---\n\n## Production Checklist\n\n- [ ] API key stored securely (environment variable)\n- [ ] Error handling implemented (401, 429, 400, 529)\n- [ ] Rate limiting with exponential backoff\n- [ ] Prompt caching enabled for repeated content\n- [ ] Streaming for long responses\n- [ ] Input validation + output sanitization\n- [ ] Monitoring and cost tracking\n- [ ] Timeouts configured\n- [ ] Model version pinned\n- [ ] max_tokens set appropriately\n\n---\n\n## Related Skills\n\n- **openai-api** - OpenAI Chat Completions for comparison\n- **claude-agent-sdk** - Higher-level Claude SDK\n- **ai-sdk-core** - Vercel AI SDK (supports Claude)\n\n---\n\n## Official Documentation\n\n- **Messages API**: https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fapi\u002Fmessages\n- **Prompt Caching**: https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fdocs\u002Fbuild-with-claude\u002Fprompt-caching\n- **Tool Use**: https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fdocs\u002Fbuild-with-claude\u002Ftool-use\n- **Vision**: https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fdocs\u002Fbuild-with-claude\u002Fvision\n- **Extended Thinking**: https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fdocs\u002Fbuild-with-claude\u002Fextended-thinking\n\n---\n\n**Questions? Issues?**\n\n1. Check `references\u002Ftop-errors.md` for error solutions\n2. Review `references\u002Fsetup-guide.md` for complete setup\n3. See `references\u002Fprompt-caching-guide.md` for cost optimization\n4. Load templates from `templates\u002F` for working examples\n","# Claude API (Anthropic Messages API)\n\n**Status**: Production Ready | **SDK**: @anthropic-ai\u002Fsdk@0.70.1\n\n---\n\n## Quick Start (5 Minutes)\n\n### Node.js\n\n```typescript\nimport Anthropic from '@anthropic-ai\u002Fsdk';\n\nconst client = new Anthropic({\n  apiKey: process.env.ANTHROPIC_API_KEY,\n});\n\nconst message = await client.messages.create({\n  model: 'claude-sonnet-4-5-20250929',\n  max_tokens: 1024,\n  messages: [\n    { role: 'user', content: 'Hello, Claude!' },\n  ],\n});\n\nconsole.log(message.content[0].text);\n```\n\n### Cloudflare Workers\n\n```typescript\nconst response = await fetch('https:\u002F\u002Fapi.anthropic.com\u002Fv1\u002Fmessages', {\n  method: 'POST',\n  headers: {\n    'x-api-key': env.ANTHROPIC_API_KEY,\n    'anthropic-version': '2023-06-01',\n    'content-type': 'application\u002Fjson',\n  },\n  body: JSON.stringify({\n    model: 'claude-sonnet-4-5-20250929',\n    max_tokens: 1024,\n    messages: [{ role: 'user', content: 'Hello!' }],\n  }),\n});\n\nconst data = await response.json();\nconsole.log(data.content[0].text);\n```\n\n**Load `references\u002Fsetup-guide.md` for complete setup with streaming, caching, and tools.**\n\n---\n\n## Critical Rules\n\n### Always Do ✅\n\n1. **Use environment variables** for API keys (NEVER hardcode)\n2. **Set max_tokens** explicitly (required parameter)\n3. **Pin model version** (`claude-sonnet-4-5-20250929`, not `claude-3-5-sonnet-latest`)\n4. **Enable prompt caching** for repeated content (90% cost savings)\n5. **Stream long responses** (`stream: true`) for better UX\n6. **Handle errors** - Implement retry logic for 429, 529 errors\n7. **Validate inputs** - Sanitize user messages before sending\n8. **Monitor costs** - Track token usage\n9. **Set timeouts** - Prevent hanging requests\n10. **Use tool use properly** - Return tool_result in follow-up message\n\n### Never Do ❌\n\n1. **Never expose API key** in client-side code\n2. **Never skip max_tokens** - API will error without it\n3. **Never ignore stop_reason** - Check for `tool_use`, `end_turn`, `max_tokens`\n4. **Never assume single content block** - `content` is an array\n5. **Never use outdated models** - Pin to specific version\n6. **Never skip error handling** - API calls can fail\n7. **Never mix message roles** - Alternate user\u002Fassistant correctly\n8. **Never ignore rate limits** - Implement exponential backoff\n9. **Never store API keys** in logs or databases\n10. **Never skip input validation** - Prevent injection attacks\n\n---\n\n## Top 3 Errors (Prevent 80% of Issues)\n\n### Error #1: Rate Limit 429\n\n**Symptom**: `429 Too Many Requests: Number of request tokens has exceeded your per-minute rate limit`\n\n**Solution**: Implement exponential backoff with retry-after header\n\n```typescript\nasync function handleRateLimit(requestFn, maxRetries = 3) {\n  for (let attempt = 0; attempt \u003C maxRetries; attempt++) {\n    try {\n      return await requestFn();\n    } catch (error) {\n      if (error.status === 429) {\n        const retryAfter = error.response?.headers?.['retry-after'];\n        const delay = retryAfter ? parseInt(retryAfter) * 1000 : 1000 * Math.pow(2, attempt);\n        await new Promise(resolve => setTimeout(resolve, delay));\n      } else {\n        throw error;\n      }\n    }\n  }\n}\n```\n\n**Prevention**: Monitor rate limit headers, upgrade tier, implement backoff\n\n---\n\n### Error #2: Prompt Caching Not Activating\n\n**Symptom**: High costs despite `cache_control` blocks, `cache_read_input_tokens: 0`\n\n**Solution**: Place `cache_control` on LAST block with >= 1024 tokens\n\n```typescript\n\u002F\u002F ❌ Wrong - cache_control not at end\n{\n  type: 'text',\n  text: DOCUMENT,\n  cache_control: { type: 'ephemeral' },  \u002F\u002F Wrong position\n},\n{\n  type: 'text',\n  text: 'Additional text',\n}\n\n\u002F\u002F ✅ Correct - cache_control at end\n{\n  type: 'text',\n  text: DOCUMENT + '\\n\\nAdditional text',\n  cache_control: { type: 'ephemeral' },  \u002F\u002F Correct position\n}\n```\n\n**Prevention**: Ensure content >= 1024 tokens, keep cached content identical, monitor usage\n\n**Load `references\u002Fprompt-caching-guide.md` for complete caching strategy.**\n\n---\n\n### Error #3: Tool Use Response Format Errors\n\n**Symptom**: `invalid_request_error: tools[0].input_schema is invalid`\n\n**Solution**: Valid tool schema with proper JSON Schema\n\n```typescript\n\u002F\u002F ✅ Valid tool schema\n{\n  name: 'get_weather',\n  description: 'Get current weather',\n  input_schema: {\n    type: 'object',           \u002F\u002F Must be 'object'\n    properties: {\n      location: {\n        type: 'string',       \u002F\u002F Valid JSON Schema types\n        description: 'City'   \u002F\u002F Optional but recommended\n      }\n    },\n    required: ['location']    \u002F\u002F List required fields\n  }\n}\n\n\u002F\u002F ✅ Valid tool result\n{\n  type: 'tool_result',\n  tool_use_id: block.id,      \u002F\u002F Must match tool_use id\n  content: JSON.stringify(result)  \u002F\u002F Convert to string\n}\n```\n\n**Prevention**: Validate schemas, match tool_use_id exactly, stringify results\n\n**Load `references\u002Ftool-use-patterns.md` + `references\u002Ftop-errors.md` for all 12 errors.**\n\n---\n\n## Common Use Cases (Quick Patterns)\n\n### Streaming Responses\n\n```typescript\nconst stream = await client.messages.stream({\n  model: 'claude-sonnet-4-5-20250929',\n  max_tokens: 1024,\n  messages: [{ role: 'user', content: 'Write a story.' }],\n});\n\nfor await (const event of stream) {\n  if (event.type === 'content_block_delta' && event.delta.type === 'text_delta') {\n    process.stdout.write(event.delta.text);\n  }\n}\n```\n\n**Load**: `templates\u002Fstreaming-chat.ts`\n\n---\n\n### Prompt Caching (90% Cost Savings)\n\n```typescript\nconst message = await client.messages.create({\n  model: 'claude-sonnet-4-5-20250929',\n  max_tokens: 1024,\n  system: [\n    {\n      type: 'text',\n      text: 'Long system prompt...',\n      cache_control: { type: 'ephemeral' },\n    },\n  ],\n  messages: [{ role: 'user', content: 'Question?' }],\n});\n```\n\n**Cache lasts 5 minutes, 90% savings on cached tokens**\n\n**Load**: `references\u002Fprompt-caching-guide.md` + `templates\u002Fprompt-caching.ts`\n\n---\n\n### Tool Use (Function Calling)\n\n```typescript\nconst message = await client.messages.create({\n  model: 'claude-sonnet-4-5-20250929',\n  max_tokens: 1024,\n  tools: [{\n    name: 'get_weather',\n    description: 'Get weather for a location',\n    input_schema: {\n      type: 'object',\n      properties: { location: { type: 'string' } },\n      required: ['location'],\n    },\n  }],\n  messages: [{ role: 'user', content: 'Weather in SF?' }],\n});\n\nif (message.stop_reason === 'tool_use') {\n  const toolUse = message.content.find(b => b.type === 'tool_use');\n  \u002F\u002F Execute tool and send result back...\n}\n```\n\n**Load**: `references\u002Ftool-use-patterns.md` + `templates\u002Ftool-use-basic.ts`\n\n---\n\n### Vision (Image Understanding)\n\n```typescript\nconst message = await client.messages.create({\n  model: 'claude-sonnet-4-5-20250929',\n  max_tokens: 1024,\n  messages: [{\n    role: 'user',\n    content: [\n      {\n        type: 'image',\n        source: {\n          type: 'base64',\n          media_type: 'image\u002Fjpeg',\n          data: base64Image,\n        },\n      },\n      { type: 'text', text: 'What is in this image?' },\n    ],\n  }],\n});\n```\n\n**Supports**: JPEG, PNG, WebP, GIF (max 5MB)\n\n**Load**: `references\u002Fvision-capabilities.md` + `templates\u002Fvision-image.ts`\n\n---\n\n### Extended Thinking Mode\n\n```typescript\nconst message = await client.messages.create({\n  model: 'claude-sonnet-4-5-20250929',\n  max_tokens: 4096,\n  thinking: {\n    type: 'enabled',\n    budget_tokens: 2000,\n  },\n  messages: [{ role: 'user', content: 'Solve complex problem...' }],\n});\n\nconst thinking = message.content.find(b => b.type === 'thinking')?.thinking;\nconst answer = message.content.find(b => b.type === 'text')?.text;\n```\n\n**Load**: `templates\u002Fextended-thinking.ts`\n\n---\n\n## Model Versions (Current)\n\n**Latest models:**\n- `claude-sonnet-4-5-20250929` - Recommended (best performance)\n- `claude-sonnet-4-20250514` - Stable version\n- `claude-3-7-sonnet-20250219` - Previous generation\n- `claude-3-5-sonnet-20241022` - Legacy\n\n**Always pin to specific version** (not `-latest` suffix)\n\n---\n\n## When to Load References\n\n### Load `references\u002Fsetup-guide.md` when:\n- First-time Claude API user needing complete setup walkthrough\n- Setting up Node.js or Cloudflare Workers from scratch\n- Need production deployment checklist and platform-specific tips\n- Troubleshooting basic setup issues (API keys, authentication, environment)\n\n### Load `references\u002Fprompt-caching-guide.md` when:\n- Want to reduce costs by 90% on repeated content\n- Using large system prompts, documents, or codebases in context\n- Need detailed caching strategy with benchmarks and cost calculations\n- Optimizing multi-turn conversations with conversation history caching\n- Troubleshooting cache activation issues or cache misses\n\n### Load `references\u002Ftool-use-patterns.md` when:\n- Implementing function calling and tool definitions\n- Need tool execution loop patterns and multi-turn tool use\n- Want Zod validation examples for type-safe tools\n- Troubleshooting tool use response format errors\n\n### Load `references\u002Fvision-capabilities.md` when:\n- Processing images with Claude (OCR, analysis, description)\n- Need image format requirements and validation logic\n- Want vision use cases and best practices\n- Combining vision with tools or prompt caching\n\n### Load `references\u002Fapi-reference.md` when:\n- Need complete API parameter reference and request\u002Fresponse schemas\n- Looking up specific fields or content block types\n- Want endpoint details, authentication headers, or model IDs\n- Need streaming event types and SSE format details\n\n### Load `references\u002Ftop-errors.md` when:\n- Encountering API errors (all 12 documented errors with solutions)\n- Need error code reference (400, 401, 429, 529, etc.)\n- Want comprehensive prevention strategies\n- Implementing robust error handling and retry logic\n\n### Load `references\u002Frate-limits.md` when:\n- Planning high-volume usage and scaling strategy\n- Encountering 429 rate limit errors repeatedly\n- Need tier limits information and upgrade path\n- Optimizing request patterns to stay within limits\n\n---\n\n## Using Bundled Resources\n\n### References (references\u002F)\n\n- **setup-guide.md** - Complete setup (Node.js + Cloudflare Workers + Next.js)\n- **api-reference.md** - Complete API parameter reference + schemas\n- **prompt-caching-guide.md** - 90% cost savings guide + benchmarks\n- **tool-use-patterns.md** - Function calling patterns + Zod examples\n- **vision-capabilities.md** - Image understanding guide + validation\n- **top-errors.md** - All 12 errors with solutions + prevention\n- **rate-limits.md** - Limits by tier + best practices\n\n### Templates (templates\u002F)\n\n- **basic-chat.ts** - Simple chat example\n- **streaming-chat.ts** - Streaming implementation with SSE\n- **prompt-caching.ts** - Caching example with benchmarks\n- **tool-use-basic.ts** - Basic tool use pattern\n- **tool-use-advanced.ts** - Advanced multi-turn tool patterns\n- **vision-image.ts** - Vision example with validation\n- **extended-thinking.ts** - Extended thinking mode\n- **error-handling.ts** - Complete error handling\n- **nodejs-example.ts** - Complete Node.js app\n- **cloudflare-worker.ts** - Complete CF Worker\n- **nextjs-api-route.ts** - Next.js API route\n- **package.json** - Dependencies\n\n---\n\n## Platform Integration\n\n**Node.js**: `bun add @anthropic-ai\u002Fsdk` → Use templates: `nodejs-example.ts`, `basic-chat.ts`\n\n**Cloudflare Workers**: Use fetch API → Use templates: `cloudflare-worker.ts`\n\n**Next.js**: `bun add @anthropic-ai\u002Fsdk` → Use templates: `nextjs-api-route.ts`\n\n---\n\n## Production Checklist\n\n- [ ] API key stored securely (environment variable)\n- [ ] Error handling implemented (401, 429, 400, 529)\n- [ ] Rate limiting with exponential backoff\n- [ ] Prompt caching enabled for repeated content\n- [ ] Streaming for long responses\n- [ ] Input validation + output sanitization\n- [ ] Monitoring and cost tracking\n- [ ] Timeouts configured\n- [ ] Model version pinned\n- [ ] max_tokens set appropriately\n\n---\n\n## Related Skills\n\n- **openai-api** - OpenAI Chat Completions for comparison\n- **claude-agent-sdk** - Higher-level Claude SDK\n- **ai-sdk-core** - Vercel AI SDK (supports Claude)\n\n---\n\n## Official Documentation\n\n- **Messages API**: https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fapi\u002Fmessages\n- **Prompt Caching**: https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fdocs\u002Fbuild-with-claude\u002Fprompt-caching\n- **Tool Use**: https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fdocs\u002Fbuild-with-claude\u002Ftool-use\n- **Vision**: https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fdocs\u002Fbuild-with-claude\u002Fvision\n- **Extended Thinking**: https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fdocs\u002Fbuild-with-claude\u002Fextended-thinking\n\n---\n\n**Questions? Issues?**\n\n1. Check `references\u002Ftop-errors.md` for error solutions\n2. Review `references\u002Fsetup-guide.md` for complete setup\n3. See `references\u002Fprompt-caching-guide.md` for cost optimization\n4. Load templates from `templates\u002F` for working examples\n",{"name":5,"license":15,"metadata":24,"description":7},{"version":25,"keywords":26,"sdk_version":43,"last_verified":44,"templates_included":45,"references_included":46},"2.0.0",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"claude api","anthropic api","messages api","@anthropic-ai\u002Fsdk","claude streaming","prompt caching","tool use","vision","extended thinking","claude 3.5 sonnet","claude 3.7 sonnet","claude sonnet 4","function calling","SSE","rate limits","429 errors","@anthropic-ai\u002Fsdk@0.70.1","2025-11-21",12,7,"main","c475fc64e94e803b50d14a791dfee8853fbb2c5c","integrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory","https:\u002F\u002Fgithub.com\u002FElogic360","2026-11-08 22:21:22",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add Elogic360\u002Fsoftware-factory --skill claude-api",{"tool":59,"command":60},"bunx","bunx skills add Elogic360\u002Fsoftware-factory --skill claude-api",{"tool":62,"command":63},"pnpm","pnpm dlx skills add Elogic360\u002Fsoftware-factory --skill claude-api","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002FSKILL.md",true,[67,73,77,81,85,89,93,97,103,107,111,115,119,123,127,131,135,139,143,147,151],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fapi-reference.md","REFERENCE","参考文档",4988,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Freferences\u002Fapi-reference.md",{"path":74,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fprompt-caching-guide.md",8953,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Freferences\u002Fprompt-caching-guide.md",{"path":78,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Frate-limits.md",2115,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Freferences\u002Frate-limits.md",{"path":82,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fsetup-guide.md",8891,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Freferences\u002Fsetup-guide.md",{"path":86,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Ftool-use-patterns.md",2608,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Freferences\u002Ftool-use-patterns.md",{"path":90,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Ftop-errors.md",10996,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Freferences\u002Ftop-errors.md",{"path":94,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fvision-capabilities.md",2130,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Freferences\u002Fvision-capabilities.md",{"path":98,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":101,"sourceHtmlUrl":102},"scripts\u002Fcheck-versions.sh","SCRIPT","脚本",2613,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Fscripts\u002Fcheck-versions.sh",{"path":104,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":105,"sourceHtmlUrl":106},"templates\u002Fbasic-chat.ts",3090,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Ftemplates\u002Fbasic-chat.ts",{"path":108,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":109,"sourceHtmlUrl":110},"templates\u002Fcloudflare-worker.ts",7081,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Ftemplates\u002Fcloudflare-worker.ts",{"path":112,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":113,"sourceHtmlUrl":114},"templates\u002Ferror-handling.ts",10203,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Ftemplates\u002Ferror-handling.ts",{"path":116,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":117,"sourceHtmlUrl":118},"templates\u002Fextended-thinking.ts",8854,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Ftemplates\u002Fextended-thinking.ts",{"path":120,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":121,"sourceHtmlUrl":122},"templates\u002Fnextjs-api-route.ts",8238,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Ftemplates\u002Fnextjs-api-route.ts",{"path":124,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":125,"sourceHtmlUrl":126},"templates\u002Fnodejs-example.ts",10204,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Ftemplates\u002Fnodejs-example.ts",{"path":128,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":129,"sourceHtmlUrl":130},"templates\u002Fpackage.json",1161,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Ftemplates\u002Fpackage.json",{"path":132,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":133,"sourceHtmlUrl":134},"templates\u002Fprompt-caching.ts",8546,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Ftemplates\u002Fprompt-caching.ts",{"path":136,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":137,"sourceHtmlUrl":138},"templates\u002Fstreaming-chat.ts",4775,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Ftemplates\u002Fstreaming-chat.ts",{"path":140,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":141,"sourceHtmlUrl":142},"templates\u002Ftool-use-advanced.ts",8345,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Ftemplates\u002Ftool-use-advanced.ts",{"path":144,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":145,"sourceHtmlUrl":146},"templates\u002Ftool-use-basic.ts",8807,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Ftemplates\u002Ftool-use-basic.ts",{"path":148,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":149,"sourceHtmlUrl":150},"templates\u002Fvision-image.ts",10162,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Ftemplates\u002Fvision-image.ts",{"path":152,"resourceType":153,"resourceTypeDesc":154,"sizeBytes":155,"sourceHtmlUrl":156},"templates\u002Fwrangler.jsonc","OTHER","其他",1582,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fclaude-api\u002Fskills\u002Fclaude-api\u002Ftemplates\u002Fwrangler.jsonc",[158,166,173,180,187,194],{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":162,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":165,"publishedAt":19},"01M79G206MT3J6S0GY3C45P2KV","vss-summarize-video","Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-summarize-video\u002FSKILL.md",[],[],{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":162,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":172,"publishedAt":19},"01M79G1WN63PGRE8CKD47WEBQ5","vss-setup-video-analytics-api","Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-video-analytics-api\u002FSKILL.md",[],[],{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":162,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":19},"01M79G1S9F7VY3EF6H53PRP5AN","vss-setup-behavior-analytics","Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-behavior-analytics\u002FSKILL.md",[],[],{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":162,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":186,"publishedAt":19},"01M79G1N1S1Y27PFZPYMNK1MTQ","vss-search-archive","Use this skill to run top-level VSS fusion search on archived video, or to ingest video files \u002F RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-deploy-dense-captioning), or video summarization and reports (use vss-summarize-video).","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-search-archive\u002FSKILL.md",[],[],{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":162,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":193,"publishedAt":19},"01M79G1H6WN0Q6C0VCAXCZX6B7","vss-query-analytics","Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-query-analytics\u002FSKILL.md",[],[],{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":162,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":200,"publishedAt":19},"01M79G1DYPNXQS7QHZ0AAF5FX5","vss-manage-video-io-storage","Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add\u002Fdelete sensors and streams). Not for VLM inference or search.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-manage-video-io-storage\u002FSKILL.md",[],[]]