[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79APJA2KBZYKW506S2RN462":3,"skill-same:01M79APJA2KBZYKW506S2RN462":104},{"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":44,"commitSha":45,"skillDirectory":46,"forksCount":14,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":49,"install":50,"resources":63},"01M79APJA2KBZYKW506S2RN462","vercel-blob",null,"Vercel Blob object storage with CDN for Next.js. Use for file uploads (images, PDFs, videos), presigned URLs, user-generated content, file management, or encountering BLOB_READ_WRITE_TOKEN errors, file size limits, client upload token 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\u002Fvercel-blob\u002Fskills\u002Fvercel-blob\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: vercel-blob\ndescription: \"Vercel Blob object storage with CDN for Next.js. Use for file uploads (images, PDFs, videos), presigned URLs, user-generated content, file management, or encountering BLOB_READ_WRITE_TOKEN errors, file size limits, client upload token errors.\"\n\nmetadata:\n  keywords:\n    - vercel blob\n    - \"@vercel\u002Fblob\"\n    - vercel storage\n    - vercel file upload\n    - vercel cdn\n    - blob storage vercel\n    - client upload vercel\n    - presigned url vercel\n    - file upload nextjs\n    - image upload vercel\n    - pdf upload\n    - video upload\n    - user uploads\n    - multipart upload\n    - streaming upload\n    - blob cdn\n    - vercel assets\n    - file download\n\nlicense: MIT\n---\n# Vercel Blob (Object Storage)\n\n**Status**: Production Ready\n**Last Updated**: 2025-12-14\n**Dependencies**: None\n**Latest Versions**: `@vercel\u002Fblob@2.0.0`\n\n---\n\n## Quick Start (3 Minutes)\n\n### 1. Create & Configure\n\n```bash\n# In Vercel dashboard: Storage → Create Database → Blob\nvercel env pull .env.local\n```\n\nCreates: `BLOB_READ_WRITE_TOKEN`\n\n### 2. Install\n\n```bash\nbun add @vercel\u002Fblob\n```\n\n### 3. Upload File (Server Action)\n\n```typescript\n'use server';\n\nimport { put } from '@vercel\u002Fblob';\n\nexport async function uploadFile(formData: FormData) {\n  const file = formData.get('file') as File;\n\n  const blob = await put(file.name, file, {\n    access: 'public',\n    contentType: file.type\n  });\n\n  return blob.url;\n}\n```\n\n### 4. Basic Operations\n\n```typescript\nimport { put, del, list } from '@vercel\u002Fblob';\n\n\u002F\u002F Upload\nconst blob = await put('path\u002Ffile.jpg', file, { access: 'public' });\n\n\u002F\u002F Delete\nawait del(blob.url);\n\n\u002F\u002F List with pagination\nconst { blobs, cursor } = await list({ prefix: 'uploads\u002F', limit: 100 });\n```\n\n---\n\n## Critical Rules\n\n### Always Do\n\n| Rule | Why |\n|------|-----|\n| Use client upload tokens for client-side uploads | Never expose `BLOB_READ_WRITE_TOKEN` to client |\n| Set `contentType` explicitly | Correct browser handling for PDFs, videos |\n| Use `access: 'public'` for CDN caching | Private files bypass CDN |\n| Validate file type and size before upload | Prevent invalid uploads |\n| Use pathname organization | `avatars\u002F`, `uploads\u002F`, `documents\u002F` |\n| Delete old files when replacing | Manage storage costs |\n\n### Never Do\n\n| Rule | Why |\n|------|-----|\n| Expose `BLOB_READ_WRITE_TOKEN` to client | Security vulnerability |\n| Upload files >500MB without multipart | Use `createMultipartUpload` API |\n| Use generic filenames | Use `${Date.now()}-${name}` or `addRandomSuffix: true` |\n| Skip file validation | Always validate type\u002Fsize |\n| Store sensitive data unencrypted | Encrypt before upload |\n| Forget to handle pagination | `list()` returns max 1000 files |\n\n---\n\n## Known Issues Prevention\n\nThis skill prevents **10 documented issues**:\n\n| # | Error | Quick Fix |\n|---|-------|-----------|\n| 1 | `BLOB_READ_WRITE_TOKEN not defined` | Run `vercel env pull .env.local` |\n| 2 | Client token exposed | Use `handleUpload()` for client uploads |\n| 3 | File size exceeded (500MB) | Use multipart upload API |\n| 4 | Wrong content-type | Set `contentType: file.type` |\n| 5 | No CDN caching | Use `access: 'public'` |\n| 6 | Missing files in list | Use cursor pagination |\n| 7 | Delete fails silently | Use exact URL from `put()` |\n| 8 | Upload timeout | Use client-side upload for large files |\n| 9 | Filename collisions | Add timestamp or `addRandomSuffix: true` |\n| 10 | State not updated | Use `onUploadCompleted` callback |\n\n**See**: `references\u002Fknown-issues.md` for complete solutions with code examples.\n\n---\n\n## Common Patterns Summary\n\n| Pattern | Use Case | Key API |\n|---------|----------|---------|\n| **Avatar Upload** | User profile images | `put`, `del` |\n| **Protected Upload** | Private documents | `put` with `access: 'private'` |\n| **Image Gallery** | List & paginate | `list` with cursor |\n| **Client Upload** | Large files, progress | `upload`, `handleUpload` |\n| **Multipart Upload** | Files >500MB | `createMultipartUpload`, `uploadPart` |\n| **Batch Operations** | Multiple files | `Promise.all`, `del([...])` |\n| **Image Processing** | Optimize before upload | `sharp` + `put` |\n\n**See**: `references\u002Fcommon-patterns.md` for complete implementations.\n\n---\n\n## Client-Side Upload (Essential Pattern)\n\n**Server Action (Token Generation):**\n```typescript\n'use server';\n\nimport { handleUpload, type HandleUploadBody } from '@vercel\u002Fblob\u002Fclient';\n\nexport async function generateUploadToken(body: HandleUploadBody) {\n  return await handleUpload({\n    body,\n    request: new Request('https:\u002F\u002Fdummy'),\n    onBeforeGenerateToken: async (pathname) => ({\n      allowedContentTypes: ['image\u002Fjpeg', 'image\u002Fpng', 'image\u002Fwebp'],\n      maximumSizeInBytes: 5 * 1024 * 1024\n    }),\n    onUploadCompleted: async ({ blob }) => {\n      \u002F\u002F Save to database\n      await db.insert(uploads).values({ url: blob.url, pathname: blob.pathname });\n    }\n  });\n}\n```\n\n**Client Component:**\n```typescript\n'use client';\n\nimport { upload } from '@vercel\u002Fblob\u002Fclient';\n\nconst blob = await upload(file.name, file, {\n  access: 'public',\n  handleUploadUrl: '\u002Fapi\u002Fupload'\n});\n```\n\n---\n\n## Configuration\n\n### .env.local\n\n```bash\n# Created by: vercel env pull .env.local\nBLOB_READ_WRITE_TOKEN=\"vercel_blob_rw_xxxxx\"\n```\n\n### .gitignore\n\n```\n.env.local\n.env*.local\n```\n\n---\n\n## When to Load References\n\n| Reference | Load When... |\n|-----------|--------------|\n| `references\u002Fknown-issues.md` | Debugging upload errors, token issues, or CDN caching problems |\n| `references\u002Fcommon-patterns.md` | Implementing avatar uploads, galleries, client uploads, or multipart uploads |\n\n---\n\n## Dependencies\n\n```json\n{\n  \"dependencies\": {\n    \"@vercel\u002Fblob\": \"^2.0.0\"\n  }\n}\n```\n\n**Free Tier Limits**: 100GB bandwidth\u002Fmonth, 500MB max file size\n\n---\n\n## Official Documentation\n\n- **Vercel Blob**: https:\u002F\u002Fvercel.com\u002Fdocs\u002Fstorage\u002Fvercel-blob\n- **Client Upload**: https:\u002F\u002Fvercel.com\u002Fdocs\u002Fstorage\u002Fvercel-blob\u002Fclient-upload\n- **SDK Reference**: https:\u002F\u002Fvercel.com\u002Fdocs\u002Fstorage\u002Fvercel-blob\u002Fusing-blob-sdk\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fvercel\u002Fstorage\n\n---\n\n## Troubleshooting\n\n| Problem | Solution |\n|---------|----------|\n| `BLOB_READ_WRITE_TOKEN not defined` | Run `vercel env pull .env.local` |\n| File size exceeded (>500MB) | Use multipart upload API |\n| Client upload fails | Use `handleUpload()` server-side |\n| Files not deleting | Use exact URL from `put()` response |\n\n---\n\n**Token Savings**: ~60% (patterns extracted to references)\n**Error Prevention**: 100% (all 10 documented issues)\n**Ready for production!**\n","# Vercel Blob (Object Storage)\n\n**Status**: Production Ready\n**Last Updated**: 2025-12-14\n**Dependencies**: None\n**Latest Versions**: `@vercel\u002Fblob@2.0.0`\n\n---\n\n## Quick Start (3 Minutes)\n\n### 1. Create & Configure\n\n```bash\n# In Vercel dashboard: Storage → Create Database → Blob\nvercel env pull .env.local\n```\n\nCreates: `BLOB_READ_WRITE_TOKEN`\n\n### 2. Install\n\n```bash\nbun add @vercel\u002Fblob\n```\n\n### 3. Upload File (Server Action)\n\n```typescript\n'use server';\n\nimport { put } from '@vercel\u002Fblob';\n\nexport async function uploadFile(formData: FormData) {\n  const file = formData.get('file') as File;\n\n  const blob = await put(file.name, file, {\n    access: 'public',\n    contentType: file.type\n  });\n\n  return blob.url;\n}\n```\n\n### 4. Basic Operations\n\n```typescript\nimport { put, del, list } from '@vercel\u002Fblob';\n\n\u002F\u002F Upload\nconst blob = await put('path\u002Ffile.jpg', file, { access: 'public' });\n\n\u002F\u002F Delete\nawait del(blob.url);\n\n\u002F\u002F List with pagination\nconst { blobs, cursor } = await list({ prefix: 'uploads\u002F', limit: 100 });\n```\n\n---\n\n## Critical Rules\n\n### Always Do\n\n| Rule | Why |\n|------|-----|\n| Use client upload tokens for client-side uploads | Never expose `BLOB_READ_WRITE_TOKEN` to client |\n| Set `contentType` explicitly | Correct browser handling for PDFs, videos |\n| Use `access: 'public'` for CDN caching | Private files bypass CDN |\n| Validate file type and size before upload | Prevent invalid uploads |\n| Use pathname organization | `avatars\u002F`, `uploads\u002F`, `documents\u002F` |\n| Delete old files when replacing | Manage storage costs |\n\n### Never Do\n\n| Rule | Why |\n|------|-----|\n| Expose `BLOB_READ_WRITE_TOKEN` to client | Security vulnerability |\n| Upload files >500MB without multipart | Use `createMultipartUpload` API |\n| Use generic filenames | Use `${Date.now()}-${name}` or `addRandomSuffix: true` |\n| Skip file validation | Always validate type\u002Fsize |\n| Store sensitive data unencrypted | Encrypt before upload |\n| Forget to handle pagination | `list()` returns max 1000 files |\n\n---\n\n## Known Issues Prevention\n\nThis skill prevents **10 documented issues**:\n\n| # | Error | Quick Fix |\n|---|-------|-----------|\n| 1 | `BLOB_READ_WRITE_TOKEN not defined` | Run `vercel env pull .env.local` |\n| 2 | Client token exposed | Use `handleUpload()` for client uploads |\n| 3 | File size exceeded (500MB) | Use multipart upload API |\n| 4 | Wrong content-type | Set `contentType: file.type` |\n| 5 | No CDN caching | Use `access: 'public'` |\n| 6 | Missing files in list | Use cursor pagination |\n| 7 | Delete fails silently | Use exact URL from `put()` |\n| 8 | Upload timeout | Use client-side upload for large files |\n| 9 | Filename collisions | Add timestamp or `addRandomSuffix: true` |\n| 10 | State not updated | Use `onUploadCompleted` callback |\n\n**See**: `references\u002Fknown-issues.md` for complete solutions with code examples.\n\n---\n\n## Common Patterns Summary\n\n| Pattern | Use Case | Key API |\n|---------|----------|---------|\n| **Avatar Upload** | User profile images | `put`, `del` |\n| **Protected Upload** | Private documents | `put` with `access: 'private'` |\n| **Image Gallery** | List & paginate | `list` with cursor |\n| **Client Upload** | Large files, progress | `upload`, `handleUpload` |\n| **Multipart Upload** | Files >500MB | `createMultipartUpload`, `uploadPart` |\n| **Batch Operations** | Multiple files | `Promise.all`, `del([...])` |\n| **Image Processing** | Optimize before upload | `sharp` + `put` |\n\n**See**: `references\u002Fcommon-patterns.md` for complete implementations.\n\n---\n\n## Client-Side Upload (Essential Pattern)\n\n**Server Action (Token Generation):**\n```typescript\n'use server';\n\nimport { handleUpload, type HandleUploadBody } from '@vercel\u002Fblob\u002Fclient';\n\nexport async function generateUploadToken(body: HandleUploadBody) {\n  return await handleUpload({\n    body,\n    request: new Request('https:\u002F\u002Fdummy'),\n    onBeforeGenerateToken: async (pathname) => ({\n      allowedContentTypes: ['image\u002Fjpeg', 'image\u002Fpng', 'image\u002Fwebp'],\n      maximumSizeInBytes: 5 * 1024 * 1024\n    }),\n    onUploadCompleted: async ({ blob }) => {\n      \u002F\u002F Save to database\n      await db.insert(uploads).values({ url: blob.url, pathname: blob.pathname });\n    }\n  });\n}\n```\n\n**Client Component:**\n```typescript\n'use client';\n\nimport { upload } from '@vercel\u002Fblob\u002Fclient';\n\nconst blob = await upload(file.name, file, {\n  access: 'public',\n  handleUploadUrl: '\u002Fapi\u002Fupload'\n});\n```\n\n---\n\n## Configuration\n\n### .env.local\n\n```bash\n# Created by: vercel env pull .env.local\nBLOB_READ_WRITE_TOKEN=\"vercel_blob_rw_xxxxx\"\n```\n\n### .gitignore\n\n```\n.env.local\n.env*.local\n```\n\n---\n\n## When to Load References\n\n| Reference | Load When... |\n|-----------|--------------|\n| `references\u002Fknown-issues.md` | Debugging upload errors, token issues, or CDN caching problems |\n| `references\u002Fcommon-patterns.md` | Implementing avatar uploads, galleries, client uploads, or multipart uploads |\n\n---\n\n## Dependencies\n\n```json\n{\n  \"dependencies\": {\n    \"@vercel\u002Fblob\": \"^2.0.0\"\n  }\n}\n```\n\n**Free Tier Limits**: 100GB bandwidth\u002Fmonth, 500MB max file size\n\n---\n\n## Official Documentation\n\n- **Vercel Blob**: https:\u002F\u002Fvercel.com\u002Fdocs\u002Fstorage\u002Fvercel-blob\n- **Client Upload**: https:\u002F\u002Fvercel.com\u002Fdocs\u002Fstorage\u002Fvercel-blob\u002Fclient-upload\n- **SDK Reference**: https:\u002F\u002Fvercel.com\u002Fdocs\u002Fstorage\u002Fvercel-blob\u002Fusing-blob-sdk\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fvercel\u002Fstorage\n\n---\n\n## Troubleshooting\n\n| Problem | Solution |\n|---------|----------|\n| `BLOB_READ_WRITE_TOKEN not defined` | Run `vercel env pull .env.local` |\n| File size exceeded (>500MB) | Use multipart upload API |\n| Client upload fails | Use `handleUpload()` server-side |\n| Files not deleting | Use exact URL from `put()` response |\n\n---\n\n**Token Savings**: ~60% (patterns extracted to references)\n**Error Prevention**: 100% (all 10 documented issues)\n**Ready for production!**\n",{"name":5,"license":15,"metadata":24,"description":7},{"keywords":25},[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"vercel blob","@vercel\u002Fblob","vercel storage","vercel file upload","vercel cdn","blob storage vercel","client upload vercel","presigned url vercel","file upload nextjs","image upload vercel","pdf upload","video upload","user uploads","multipart upload","streaming upload","blob cdn","vercel assets","file download","main","c475fc64e94e803b50d14a791dfee8853fbb2c5c","integrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fvercel-blob\u002Fskills\u002Fvercel-blob","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory","https:\u002F\u002Fgithub.com\u002FElogic360","2026-11-08 22:21:22",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add Elogic360\u002Fsoftware-factory --skill vercel-blob",{"tool":56,"command":57},"bunx","bunx skills add Elogic360\u002Fsoftware-factory --skill vercel-blob",{"tool":59,"command":60},"pnpm","pnpm dlx skills add Elogic360\u002Fsoftware-factory --skill vercel-blob","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fvercel-blob\u002Fskills\u002Fvercel-blob\u002FSKILL.md",true,[64,70,76,80,86,92,96,100],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"assets\u002Fexample-template.txt","ASSET","资产文件",416,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fvercel-blob\u002Fskills\u002Fvercel-blob\u002Fassets\u002Fexample-template.txt",{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fcommon-patterns.md","REFERENCE","参考文档",9542,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fvercel-blob\u002Fskills\u002Fvercel-blob\u002Freferences\u002Fcommon-patterns.md",{"path":77,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fknown-issues.md",6956,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fvercel-blob\u002Fskills\u002Fvercel-blob\u002Freferences\u002Fknown-issues.md",{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"scripts\u002Fexample-script.sh","SCRIPT","脚本",302,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fvercel-blob\u002Fskills\u002Fvercel-blob\u002Fscripts\u002Fexample-script.sh",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"templates\u002Favatar-upload-flow.tsx","OTHER","其他",10321,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fvercel-blob\u002Fskills\u002Fvercel-blob\u002Ftemplates\u002Favatar-upload-flow.tsx",{"path":93,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":94,"sourceHtmlUrl":95},"templates\u002Fdrag-drop-upload.tsx",10897,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fvercel-blob\u002Fskills\u002Fvercel-blob\u002Ftemplates\u002Fdrag-drop-upload.tsx",{"path":97,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":98,"sourceHtmlUrl":99},"templates\u002Ffile-list-manager.tsx",10760,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fvercel-blob\u002Fskills\u002Fvercel-blob\u002Ftemplates\u002Ffile-list-manager.tsx",{"path":101,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":102,"sourceHtmlUrl":103},"templates\u002Fpackage.json",499,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fvercel-blob\u002Fskills\u002Fvercel-blob\u002Ftemplates\u002Fpackage.json",[105,113,120,127,134,141],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":109,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"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":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":109,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"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":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":109,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"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":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":109,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"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":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":109,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"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":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":109,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"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",[],[]]