[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71KH3MXQCH43NFGCHY71XCY":3,"skill-same:01M71KH3MXQCH43NFGCHY71XCY":81},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":6,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M71KH3MXQCH43NFGCHY71XCY","claude-to-deerflow",null,"Interact with DeerFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to DeerFlow for research\u002Fanalysis, start a DeerFlow conversation thread, check DeerFlow status or health, list available models\u002Fskills\u002Fagents in DeerFlow, manage DeerFlow memory, upload files to DeerFlow threads, or delegate complex research tasks to DeerFlow. Also use when the user mentions deerflow, deer flow, or wants to run a deep research task that DeerFlow can handle.","q2805187159\u002FAnvil","q2805187159","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F105276843?v=4","01M71KF4TN999VNJX9FY9QT06A","铁甲勇士宋小宝","01M71KF4V97XXQ7AGES97R4Q9F",3,"MIT","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fclaude-to-deerflow\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"claude to deerflow","files","flow","status","run","threads","api","tasks","analysis","when","ai agent","send","messages","delegate","deer flow","memory","deep research","deep","conversation","http api","2026-11-10 10:12:30",false,"---\nname: claude-to-deerflow\ndescription: \"Interact with DeerFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to DeerFlow for research\u002Fanalysis, start a DeerFlow conversation thread, check DeerFlow status or health, list available models\u002Fskills\u002Fagents in DeerFlow, manage DeerFlow memory, upload files to DeerFlow threads, or delegate complex research tasks to DeerFlow. Also use when the user mentions deerflow, deer flow, or wants to run a deep research task that DeerFlow can handle.\"\n---\n\n# DeerFlow Skill\n\nCommunicate with a running DeerFlow instance via its HTTP API. DeerFlow is an AI agent platform\nbuilt on LangGraph that orchestrates sub-agents for research, code execution, web browsing, and more.\n\n## Architecture\n\nDeerFlow exposes two API surfaces behind an Nginx reverse proxy:\n\n| Service        | Direct Port | Via Proxy                        | Purpose                          |\n|----------------|-------------|----------------------------------|----------------------------------|\n| Gateway API    | 8001        | `$DEERFLOW_GATEWAY_URL`          | REST endpoints (models, skills, memory, uploads) |\n| LangGraph API  | 2024        | `$DEERFLOW_LANGGRAPH_URL`        | Agent threads, runs, streaming   |\n\n## Environment Variables\n\nAll URLs are configurable via environment variables. **Read these env vars before making any request.**\n\n| Variable                | Default                                  | Description                        |\n|-------------------------|------------------------------------------|------------------------------------|\n| `DEERFLOW_URL`          | `http:\u002F\u002Flocalhost:2026`                  | Unified proxy base URL             |\n| `DEERFLOW_GATEWAY_URL`  | `${DEERFLOW_URL}`                        | Gateway API base (models, skills, memory, uploads) |\n| `DEERFLOW_LANGGRAPH_URL`| `${DEERFLOW_URL}\u002Fapi\u002Flanggraph`          | LangGraph API base (threads, runs) |\n\nWhen making curl calls, always resolve the URL like this:\n\n```bash\n# Resolve base URLs from env (do this FIRST before any API call)\nDEERFLOW_URL=\"${DEERFLOW_URL:-http:\u002F\u002Flocalhost:2026}\"\nDEERFLOW_GATEWAY_URL=\"${DEERFLOW_GATEWAY_URL:-$DEERFLOW_URL}\"\nDEERFLOW_LANGGRAPH_URL=\"${DEERFLOW_LANGGRAPH_URL:-$DEERFLOW_URL\u002Fapi\u002Flanggraph}\"\n```\n\n## Available Operations\n\n### 1. Health Check\n\nVerify DeerFlow is running:\n\n```bash\ncurl -s \"$DEERFLOW_GATEWAY_URL\u002Fhealth\"\n```\n\n### 2. Send a Message (Streaming)\n\nThis is the primary operation. It creates a thread and streams the agent's response.\n\n**Step 1: Create a thread**\n\n```bash\ncurl -s -X POST \"$DEERFLOW_LANGGRAPH_URL\u002Fthreads\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{}'\n```\n\nResponse: `{\"thread_id\": \"\u003Cuuid>\", ...}`\n\n**Step 2: Stream a run**\n\n```bash\ncurl -s -N -X POST \"$DEERFLOW_LANGGRAPH_URL\u002Fthreads\u002F\u003Cthread_id>\u002Fruns\u002Fstream\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"assistant_id\": \"lead_agent\",\n    \"input\": {\n      \"messages\": [\n        {\n          \"type\": \"human\",\n          \"content\": [{\"type\": \"text\", \"text\": \"YOUR MESSAGE HERE\"}]\n        }\n      ]\n    },\n    \"stream_mode\": [\"values\", \"messages-tuple\"],\n    \"stream_subgraphs\": true,\n    \"config\": {\n      \"recursion_limit\": 1000\n    },\n    \"context\": {\n      \"thinking_enabled\": true,\n      \"is_plan_mode\": true,\n      \"subagent_enabled\": true,\n      \"thread_id\": \"\u003Cthread_id>\"\n    }\n  }'\n```\n\nThe response is an SSE stream. Each event has the format:\n```\nevent: \u003Cevent_type>\ndata: \u003Cjson_data>\n```\n\nKey event types:\n- `metadata` — run metadata including `run_id`\n- `values` — full state snapshot with `messages` array\n- `messages-tuple` — incremental message updates (AI text chunks, tool calls, tool results)\n- `end` — stream is complete\n\n**Context modes** (set via `context`):\n- Flash mode: `thinking_enabled: false, is_plan_mode: false, subagent_enabled: false`\n- Standard mode: `thinking_enabled: true, is_plan_mode: false, subagent_enabled: false`\n- Pro mode: `thinking_enabled: true, is_plan_mode: true, subagent_enabled: false`\n- Ultra mode: `thinking_enabled: true, is_plan_mode: true, subagent_enabled: true`\n\n### 3. Continue a Conversation\n\nTo send follow-up messages, reuse the same `thread_id` from step 2 and POST another run\nwith the new message.\n\n### 4. List Models\n\n```bash\ncurl -s \"$DEERFLOW_GATEWAY_URL\u002Fapi\u002Fmodels\"\n```\n\nReturns: `{\"models\": [{\"name\": \"...\", \"provider\": \"...\", ...}, ...]}`\n\n### 5. List Skills\n\n```bash\ncurl -s \"$DEERFLOW_GATEWAY_URL\u002Fapi\u002Fskills\"\n```\n\nReturns: `{\"skills\": [{\"name\": \"...\", \"enabled\": true, ...}, ...]}`\n\n### 6. Enable\u002FDisable a Skill\n\n```bash\ncurl -s -X PUT \"$DEERFLOW_GATEWAY_URL\u002Fapi\u002Fskills\u002F\u003Cskill_name>\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"enabled\": true}'\n```\n\n### 7. List Agents\n\n```bash\ncurl -s \"$DEERFLOW_GATEWAY_URL\u002Fapi\u002Fagents\"\n```\n\nReturns: `{\"agents\": [{\"name\": \"...\", ...}, ...]}`\n\n### 8. Get Memory\n\n```bash\ncurl -s \"$DEERFLOW_GATEWAY_URL\u002Fapi\u002Fmemory\"\n```\n\nReturns user context, facts, and conversation history summaries.\n\n### 9. Upload Files to a Thread\n\n```bash\ncurl -s -X POST \"$DEERFLOW_GATEWAY_URL\u002Fapi\u002Fthreads\u002F\u003Cthread_id>\u002Fuploads\" \\\n  -F \"files=@\u002Fpath\u002Fto\u002Ffile.pdf\"\n```\n\nSupports PDF, PPTX, XLSX, DOCX — automatically converts to Markdown.\n\n### 10. List Uploaded Files\n\n```bash\ncurl -s \"$DEERFLOW_GATEWAY_URL\u002Fapi\u002Fthreads\u002F\u003Cthread_id>\u002Fuploads\u002Flist\"\n```\n\n### 11. Get Thread History\n\n```bash\ncurl -s \"$DEERFLOW_LANGGRAPH_URL\u002Fthreads\u002F\u003Cthread_id>\u002Fhistory\"\n```\n\n### 12. List Threads\n\n```bash\ncurl -s -X POST \"$DEERFLOW_LANGGRAPH_URL\u002Fthreads\u002Fsearch\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"limit\": 20, \"sort_by\": \"updated_at\", \"sort_order\": \"desc\"}'\n```\n\n## Usage Script\n\nFor sending messages and collecting the full response, use the helper script:\n\n```bash\nbash \u002Fpath\u002Fto\u002Fskills\u002Fclaude-to-deerflow\u002Fscripts\u002Fchat.sh \"Your question here\"\n```\n\nSee `scripts\u002Fchat.sh` for the implementation. The script:\n1. Checks health\n2. Creates a thread\n3. Streams the run and collects the final AI response\n4. Prints the result\n\n## Parsing SSE Output\n\nThe stream returns SSE events. To extract the final AI response from a `values` event:\n- Look for the last `event: values` block\n- Parse its `data` JSON\n- The `messages` array contains all messages; the last one with `type: \"ai\"` is the response\n- The `content` field of that message is the AI's text reply\n\n## Error Handling\n\n- If health check fails, DeerFlow is not running. Inform the user they need to start it.\n- If the stream returns an error event, extract and display the error message.\n- Common issues: port not open, services still starting up, config errors.\n\n## Tips\n\n- For quick questions, use flash mode (fastest, no planning).\n- For research tasks, use pro or ultra mode (enables planning and sub-agents).\n- You can upload files first, then reference them in your message.\n- Thread IDs persist — you can return to a conversation later.\n","# DeerFlow Skill\n\nCommunicate with a running DeerFlow instance via its HTTP API. DeerFlow is an AI agent platform\nbuilt on LangGraph that orchestrates sub-agents for research, code execution, web browsing, and more.\n\n## Architecture\n\nDeerFlow exposes two API surfaces behind an Nginx reverse proxy:\n\n| Service        | Direct Port | Via Proxy                        | Purpose                          |\n|----------------|-------------|----------------------------------|----------------------------------|\n| Gateway API    | 8001        | `$DEERFLOW_GATEWAY_URL`          | REST endpoints (models, skills, memory, uploads) |\n| LangGraph API  | 2024        | `$DEERFLOW_LANGGRAPH_URL`        | Agent threads, runs, streaming   |\n\n## Environment Variables\n\nAll URLs are configurable via environment variables. **Read these env vars before making any request.**\n\n| Variable                | Default                                  | Description                        |\n|-------------------------|------------------------------------------|------------------------------------|\n| `DEERFLOW_URL`          | `http:\u002F\u002Flocalhost:2026`                  | Unified proxy base URL             |\n| `DEERFLOW_GATEWAY_URL`  | `${DEERFLOW_URL}`                        | Gateway API base (models, skills, memory, uploads) |\n| `DEERFLOW_LANGGRAPH_URL`| `${DEERFLOW_URL}\u002Fapi\u002Flanggraph`          | LangGraph API base (threads, runs) |\n\nWhen making curl calls, always resolve the URL like this:\n\n```bash\n# Resolve base URLs from env (do this FIRST before any API call)\nDEERFLOW_URL=\"${DEERFLOW_URL:-http:\u002F\u002Flocalhost:2026}\"\nDEERFLOW_GATEWAY_URL=\"${DEERFLOW_GATEWAY_URL:-$DEERFLOW_URL}\"\nDEERFLOW_LANGGRAPH_URL=\"${DEERFLOW_LANGGRAPH_URL:-$DEERFLOW_URL\u002Fapi\u002Flanggraph}\"\n```\n\n## Available Operations\n\n### 1. Health Check\n\nVerify DeerFlow is running:\n\n```bash\ncurl -s \"$DEERFLOW_GATEWAY_URL\u002Fhealth\"\n```\n\n### 2. Send a Message (Streaming)\n\nThis is the primary operation. It creates a thread and streams the agent's response.\n\n**Step 1: Create a thread**\n\n```bash\ncurl -s -X POST \"$DEERFLOW_LANGGRAPH_URL\u002Fthreads\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{}'\n```\n\nResponse: `{\"thread_id\": \"\u003Cuuid>\", ...}`\n\n**Step 2: Stream a run**\n\n```bash\ncurl -s -N -X POST \"$DEERFLOW_LANGGRAPH_URL\u002Fthreads\u002F\u003Cthread_id>\u002Fruns\u002Fstream\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"assistant_id\": \"lead_agent\",\n    \"input\": {\n      \"messages\": [\n        {\n          \"type\": \"human\",\n          \"content\": [{\"type\": \"text\", \"text\": \"YOUR MESSAGE HERE\"}]\n        }\n      ]\n    },\n    \"stream_mode\": [\"values\", \"messages-tuple\"],\n    \"stream_subgraphs\": true,\n    \"config\": {\n      \"recursion_limit\": 1000\n    },\n    \"context\": {\n      \"thinking_enabled\": true,\n      \"is_plan_mode\": true,\n      \"subagent_enabled\": true,\n      \"thread_id\": \"\u003Cthread_id>\"\n    }\n  }'\n```\n\nThe response is an SSE stream. Each event has the format:\n```\nevent: \u003Cevent_type>\ndata: \u003Cjson_data>\n```\n\nKey event types:\n- `metadata` — run metadata including `run_id`\n- `values` — full state snapshot with `messages` array\n- `messages-tuple` — incremental message updates (AI text chunks, tool calls, tool results)\n- `end` — stream is complete\n\n**Context modes** (set via `context`):\n- Flash mode: `thinking_enabled: false, is_plan_mode: false, subagent_enabled: false`\n- Standard mode: `thinking_enabled: true, is_plan_mode: false, subagent_enabled: false`\n- Pro mode: `thinking_enabled: true, is_plan_mode: true, subagent_enabled: false`\n- Ultra mode: `thinking_enabled: true, is_plan_mode: true, subagent_enabled: true`\n\n### 3. Continue a Conversation\n\nTo send follow-up messages, reuse the same `thread_id` from step 2 and POST another run\nwith the new message.\n\n### 4. List Models\n\n```bash\ncurl -s \"$DEERFLOW_GATEWAY_URL\u002Fapi\u002Fmodels\"\n```\n\nReturns: `{\"models\": [{\"name\": \"...\", \"provider\": \"...\", ...}, ...]}`\n\n### 5. List Skills\n\n```bash\ncurl -s \"$DEERFLOW_GATEWAY_URL\u002Fapi\u002Fskills\"\n```\n\nReturns: `{\"skills\": [{\"name\": \"...\", \"enabled\": true, ...}, ...]}`\n\n### 6. Enable\u002FDisable a Skill\n\n```bash\ncurl -s -X PUT \"$DEERFLOW_GATEWAY_URL\u002Fapi\u002Fskills\u002F\u003Cskill_name>\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"enabled\": true}'\n```\n\n### 7. List Agents\n\n```bash\ncurl -s \"$DEERFLOW_GATEWAY_URL\u002Fapi\u002Fagents\"\n```\n\nReturns: `{\"agents\": [{\"name\": \"...\", ...}, ...]}`\n\n### 8. Get Memory\n\n```bash\ncurl -s \"$DEERFLOW_GATEWAY_URL\u002Fapi\u002Fmemory\"\n```\n\nReturns user context, facts, and conversation history summaries.\n\n### 9. Upload Files to a Thread\n\n```bash\ncurl -s -X POST \"$DEERFLOW_GATEWAY_URL\u002Fapi\u002Fthreads\u002F\u003Cthread_id>\u002Fuploads\" \\\n  -F \"files=@\u002Fpath\u002Fto\u002Ffile.pdf\"\n```\n\nSupports PDF, PPTX, XLSX, DOCX — automatically converts to Markdown.\n\n### 10. List Uploaded Files\n\n```bash\ncurl -s \"$DEERFLOW_GATEWAY_URL\u002Fapi\u002Fthreads\u002F\u003Cthread_id>\u002Fuploads\u002Flist\"\n```\n\n### 11. Get Thread History\n\n```bash\ncurl -s \"$DEERFLOW_LANGGRAPH_URL\u002Fthreads\u002F\u003Cthread_id>\u002Fhistory\"\n```\n\n### 12. List Threads\n\n```bash\ncurl -s -X POST \"$DEERFLOW_LANGGRAPH_URL\u002Fthreads\u002Fsearch\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"limit\": 20, \"sort_by\": \"updated_at\", \"sort_order\": \"desc\"}'\n```\n\n## Usage Script\n\nFor sending messages and collecting the full response, use the helper script:\n\n```bash\nbash \u002Fpath\u002Fto\u002Fskills\u002Fclaude-to-deerflow\u002Fscripts\u002Fchat.sh \"Your question here\"\n```\n\nSee `scripts\u002Fchat.sh` for the implementation. The script:\n1. Checks health\n2. Creates a thread\n3. Streams the run and collects the final AI response\n4. Prints the result\n\n## Parsing SSE Output\n\nThe stream returns SSE events. To extract the final AI response from a `values` event:\n- Look for the last `event: values` block\n- Parse its `data` JSON\n- The `messages` array contains all messages; the last one with `type: \"ai\"` is the response\n- The `content` field of that message is the AI's text reply\n\n## Error Handling\n\n- If health check fails, DeerFlow is not running. Inform the user they need to start it.\n- If the stream returns an error event, extract and display the error message.\n- Common issues: port not open, services still starting up, config errors.\n\n## Tips\n\n- For quick questions, use flash mode (fastest, no planning).\n- For research tasks, use pro or ultra mode (enables planning and sub-agents).\n- You can upload files first, then reference them in your message.\n- Thread IDs persist — you can return to a conversation later.\n",{"name":5,"description":7},"main","6ffadc67c9777282fa1f9330ec12ac8778064409","skills\u002Fclaude-to-deerflow",0,"https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil","https:\u002F\u002Fgithub.com\u002Fq2805187159","Independent Researcher\r\n\r\nEmail: q2805187159@gmail.com\r\n\r\nGithub: q2805187159\r\n\r\nResearch Interests:\r\n- LLM Agents\r\n- Tool Routing\r\n- RAG","2026-06-24 18:31:41",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add q2805187159\u002FAnvil --skill claude-to-deerflow",{"tool":63,"command":64},"bunx","bunx skills add q2805187159\u002FAnvil --skill claude-to-deerflow",{"tool":66,"command":67},"pnpm","pnpm dlx skills add q2805187159\u002FAnvil --skill claude-to-deerflow","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fclaude-to-deerflow\u002FSKILL.md",true,[71,77],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"scripts\u002Fchat.sh","SCRIPT","脚本",8183,"https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fclaude-to-deerflow\u002Fscripts\u002Fchat.sh",{"path":78,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":79,"sourceHtmlUrl":80},"scripts\u002Fstatus.sh",3314,"https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fclaude-to-deerflow\u002Fscripts\u002Fstatus.sh",[82,115,147,154,178,201],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":96,"publishedAt":114},"01M71NPWVVMB1AZ8XGKNJFT0YP","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.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[90,93],{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":94,"categoryName":95,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113],"webapp","testing","webapp testing","for","applications","local","frontend","debugging","toolkit","logs","browser","with","playwright","web","behavior","ui","screenshots","2026-11-10 10:56:23",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":129,"publishedAt":114},"01M71NPTQ96H4XSZVZT422BNRB","web-design-guidelines","Review UI code for Web Interface Guidelines compliance. Use when asked to \"review my UI\", \"check accessibility\", \"audit design\", \"review UX\", or \"check my site against best practices\".","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fweb-design-guidelines\u002FSKILL.md",[121,124],{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":125,"categoryName":126,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[130,131,110,132,133,100,134,135,136,137,33,138,139,140,141,142,143,144,145,146],"guidelines","design","web design guidelines","web design","vercel","interface","web interface guidelines","use","best practices","file","code","review","check","compliance","audit","ux","accessibility",{"skillNo":148,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":153,"publishedAt":114},"01M71NPS2D31Y2BGFYA9DB7CE4","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fweb-design-guidelines copy\u002FSKILL.md",[151,152],{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":125,"categoryName":126,"taxonomyType":127,"taxonomyTypeDesc":128},[130,131,110,132,133,100,134,135,136,137,33,138,139,140,141,142,143,144,145,146],{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":164,"publishedAt":114},"01M71NPQ9DRT54QSQJ0BHBM3VG","video-generation","Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference image for guided generation.","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-generation\u002FSKILL.md",[160,163],{"categoryNo":161,"categoryName":162,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[165,166,167,100,137,33,168,169,170,171,172,173,174,175,176,177],"Video","video generation","generation","image","create","imagine","requests","generate","videos","reference","prompts","user","structured",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":185,"publishedAt":114},"01M71NPN57CT154SWXAS52475X","youtube-downloader","Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p, 720p, 480p, 360p), multiple formats (mp4, webm, mkv), and audio-only downloads as MP3.","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-downloader\u002FSKILL.md",[184],{"categoryNo":161,"categoryName":162,"taxonomyType":21,"taxonomyTypeDesc":22},[186,187,188,189,190,191,192,137,33,193,108,194,195,196,197,198,173,199,176,200],"youtube","youtube downloader","mp4","as","downloads","Audio","only","mp3","options","quality","format","settings","grab","formats","download",{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":205,"categories":206,"keywords":207,"publishedAt":114},"01M71NPKD95YB8N3J6J78QGFFW","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[208,209,210,211,212,213,214,137,215,33,216,217,218,219,220,221],"verification","verification before completion","running","evidence","complete","prs","claim","assertions","committing","output","claims","work","about","commands"]