[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HQWC2VGFABV660TZ56F46":3,"skill-same:01M71HQWC2VGFABV660TZ56F46":96},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":25,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M71HQWC2VGFABV660TZ56F46","alicloud-ai-video-wan-video",null,"Generate videos with Model Studio DashScope SDK using Wan i2v models (wan2.6-i2v-flash, wan2.6-i2v, wan2.6-i2v-us). Use when implementing or documenting video.generate requests\u002Fresponses, mapping prompt\u002Fnegative_prompt\u002Fduration\u002Ffps\u002Fsize\u002Fseed\u002Freference_image\u002Fmotion_strength, or integrating video generation into the video-agent pipeline.","JSGforever\u002Fskillguard","JSGforever","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F85541948?v=4","01M71FQD3E132VMR5F4TAYX3YS","01M71FQD4DYW0XJ4XQ4YQH75Y9",2,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__cinience--alicloud-ai-video-wan-video\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"alicloud ai video wan video","ai video","Video","generate","generation","requests","video generation","size","with model","with","studio","image","when","prompt","use","motion","implementing","agent pipeline","pipeline","model","2026-11-10 10:12:30",false,"---\nname: alicloud-ai-video-wan-video\ndescription: Generate videos with Model Studio DashScope SDK using Wan i2v models (wan2.6-i2v-flash, wan2.6-i2v, wan2.6-i2v-us). Use when implementing or documenting video.generate requests\u002Fresponses, mapping prompt\u002Fnegative_prompt\u002Fduration\u002Ffps\u002Fsize\u002Fseed\u002Freference_image\u002Fmotion_strength, or integrating video generation into the video-agent pipeline.\n---\n\nCategory: provider\n\n# Model Studio Wan Video\n\n## Validation\n\n```bash\nmkdir -p output\u002Falicloud-ai-video-wan-video\npython -m py_compile skills\u002Fai\u002Fvideo\u002Falicloud-ai-video-wan-video\u002Fscripts\u002Fgenerate_video.py && echo \"py_compile_ok\" > output\u002Falicloud-ai-video-wan-video\u002Fvalidate.txt\n```\n\nPass criteria: command exits 0 and `output\u002Falicloud-ai-video-wan-video\u002Fvalidate.txt` is generated.\n\n## Output And Evidence\n\n- Save task IDs, polling responses, and final video URLs to `output\u002Falicloud-ai-video-wan-video\u002F`.\n- Keep one end-to-end run log for troubleshooting.\n\nProvide consistent video generation behavior for the video-agent pipeline by standardizing `video.generate` inputs\u002Foutputs and using DashScope SDK (Python) with the exact model name.\n\n## Critical model names\n\nUse one of these exact model strings:\n- `wan2.6-i2v-flash`\n- `wan2.6-i2v`\n- `wan2.6-i2v-us`\n\n## Prerequisites\n\n- Install SDK (recommended in a venv to avoid PEP 668 limits):\n\n```bash\npython3 -m venv .venv\n. .venv\u002Fbin\u002Factivate\npython -m pip install dashscope\n```\n- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~\u002F.alibabacloud\u002Fcredentials` (env takes precedence).\n\n## Normalized interface (video.generate)\n\n### Request\n- `prompt` (string, required)\n- `negative_prompt` (string, optional)\n- `duration` (number, required) seconds\n- `fps` (number, required)\n- `size` (string, required) e.g. `1280*720`\n- `seed` (int, optional)\n- `reference_image` (string | bytes, required for i2v family models)\n- `motion_strength` (number, optional)\n\n### Response\n- `video_url` (string)\n- `duration` (number)\n- `fps` (number)\n- `seed` (int)\n\n## Quick start (Python + DashScope SDK)\n\nVideo generation is usually asynchronous. Expect a task ID and poll until completion.\nNote: Wan i2v models require an input image; map `reference_image` to `img_url`.\n\n```python\nimport os\nfrom dashscope import VideoSynthesis\n\n# Prefer env var for auth: export DASHSCOPE_API_KEY=...\n# Or use ~\u002F.alibabacloud\u002Fcredentials with dashscope_api_key under [default].\n\ndef generate_video(req: dict) -> dict:\n    payload = {\n        \"model\": req.get(\"model\", \"wan2.6-i2v-flash\"),\n        \"prompt\": req[\"prompt\"],\n        \"negative_prompt\": req.get(\"negative_prompt\"),\n        \"duration\": req.get(\"duration\", 4),\n        \"fps\": req.get(\"fps\", 24),\n        \"size\": req.get(\"size\", \"1280*720\"),\n        \"seed\": req.get(\"seed\"),\n        \"motion_strength\": req.get(\"motion_strength\"),\n        \"api_key\": os.getenv(\"DASHSCOPE_API_KEY\"),\n    }\n\n    if req.get(\"reference_image\"):\n        # DashScope expects img_url for i2v models; local files are auto-uploaded.\n        payload[\"img_url\"] = req[\"reference_image\"]\n\n    response = VideoSynthesis.call(**payload)\n\n    # Some SDK versions require polling for the final result.\n    # If a task_id is returned, poll until status is SUCCEEDED.\n    result = response.output.get(\"results\", [None])[0]\n\n    return {\n        \"video_url\": None if not result else result.get(\"url\"),\n        \"duration\": response.output.get(\"duration\"),\n        \"fps\": response.output.get(\"fps\"),\n        \"seed\": response.output.get(\"seed\"),\n    }\n```\n\n## Async handling (polling)\n\n```python\nimport os\nfrom dashscope import VideoSynthesis\n\ntask = VideoSynthesis.async_call(\n    model=req.get(\"model\", \"wan2.6-i2v-flash\"),\n    prompt=req[\"prompt\"],\n    img_url=req[\"reference_image\"],\n    duration=req.get(\"duration\", 4),\n    fps=req.get(\"fps\", 24),\n    size=req.get(\"size\", \"1280*720\"),\n    api_key=os.getenv(\"DASHSCOPE_API_KEY\"),\n)\n\nfinal = VideoSynthesis.wait(task)\nvideo_url = final.output.get(\"video_url\")\n```\n\n## Operational guidance\n\n- Video generation can take minutes; expose progress and allow cancel\u002Fretry.\n- Cache by `(prompt, negative_prompt, duration, fps, size, seed, reference_image hash, motion_strength)`.\n- Store video assets in object storage and persist only URLs in metadata.\n- `reference_image` can be a URL or local path; the SDK auto-uploads local files.\n- If you get `Field required: input.img_url`, the reference image is missing or not mapped.\n\n## Size notes\n\n- Use `WxH` format (e.g. `1280*720`).\n- Prefer common sizes; unsupported sizes can return 400.\n\n## Output location\n\n- Default output: `output\u002Falicloud-ai-video-wan-video\u002Fvideos\u002F`\n- Override base dir with `OUTPUT_DIR`.\n\n## Anti-patterns\n\n- Do not invent model names or aliases; use official Wan i2v model IDs only.\n- Do not block the UI without progress updates.\n- Do not retry blindly on 4xx; handle validation failures explicitly.\n\n## Workflow\n\n1) Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.\n2) Run one minimal read-only query first to verify connectivity and permissions.\n3) Execute the target operation with explicit parameters and bounded scope.\n4) Verify results and save output\u002Fevidence files.\n\n## References\n\n- See `references\u002Fapi_reference.md` for DashScope SDK mapping and async handling notes.\n\n- Source list: `references\u002Fsources.md`\n","Category: provider\n\n# Model Studio Wan Video\n\n## Validation\n\n```bash\nmkdir -p output\u002Falicloud-ai-video-wan-video\npython -m py_compile skills\u002Fai\u002Fvideo\u002Falicloud-ai-video-wan-video\u002Fscripts\u002Fgenerate_video.py && echo \"py_compile_ok\" > output\u002Falicloud-ai-video-wan-video\u002Fvalidate.txt\n```\n\nPass criteria: command exits 0 and `output\u002Falicloud-ai-video-wan-video\u002Fvalidate.txt` is generated.\n\n## Output And Evidence\n\n- Save task IDs, polling responses, and final video URLs to `output\u002Falicloud-ai-video-wan-video\u002F`.\n- Keep one end-to-end run log for troubleshooting.\n\nProvide consistent video generation behavior for the video-agent pipeline by standardizing `video.generate` inputs\u002Foutputs and using DashScope SDK (Python) with the exact model name.\n\n## Critical model names\n\nUse one of these exact model strings:\n- `wan2.6-i2v-flash`\n- `wan2.6-i2v`\n- `wan2.6-i2v-us`\n\n## Prerequisites\n\n- Install SDK (recommended in a venv to avoid PEP 668 limits):\n\n```bash\npython3 -m venv .venv\n. .venv\u002Fbin\u002Factivate\npython -m pip install dashscope\n```\n- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~\u002F.alibabacloud\u002Fcredentials` (env takes precedence).\n\n## Normalized interface (video.generate)\n\n### Request\n- `prompt` (string, required)\n- `negative_prompt` (string, optional)\n- `duration` (number, required) seconds\n- `fps` (number, required)\n- `size` (string, required) e.g. `1280*720`\n- `seed` (int, optional)\n- `reference_image` (string | bytes, required for i2v family models)\n- `motion_strength` (number, optional)\n\n### Response\n- `video_url` (string)\n- `duration` (number)\n- `fps` (number)\n- `seed` (int)\n\n## Quick start (Python + DashScope SDK)\n\nVideo generation is usually asynchronous. Expect a task ID and poll until completion.\nNote: Wan i2v models require an input image; map `reference_image` to `img_url`.\n\n```python\nimport os\nfrom dashscope import VideoSynthesis\n\n# Prefer env var for auth: export DASHSCOPE_API_KEY=...\n# Or use ~\u002F.alibabacloud\u002Fcredentials with dashscope_api_key under [default].\n\ndef generate_video(req: dict) -> dict:\n    payload = {\n        \"model\": req.get(\"model\", \"wan2.6-i2v-flash\"),\n        \"prompt\": req[\"prompt\"],\n        \"negative_prompt\": req.get(\"negative_prompt\"),\n        \"duration\": req.get(\"duration\", 4),\n        \"fps\": req.get(\"fps\", 24),\n        \"size\": req.get(\"size\", \"1280*720\"),\n        \"seed\": req.get(\"seed\"),\n        \"motion_strength\": req.get(\"motion_strength\"),\n        \"api_key\": os.getenv(\"DASHSCOPE_API_KEY\"),\n    }\n\n    if req.get(\"reference_image\"):\n        # DashScope expects img_url for i2v models; local files are auto-uploaded.\n        payload[\"img_url\"] = req[\"reference_image\"]\n\n    response = VideoSynthesis.call(**payload)\n\n    # Some SDK versions require polling for the final result.\n    # If a task_id is returned, poll until status is SUCCEEDED.\n    result = response.output.get(\"results\", [None])[0]\n\n    return {\n        \"video_url\": None if not result else result.get(\"url\"),\n        \"duration\": response.output.get(\"duration\"),\n        \"fps\": response.output.get(\"fps\"),\n        \"seed\": response.output.get(\"seed\"),\n    }\n```\n\n## Async handling (polling)\n\n```python\nimport os\nfrom dashscope import VideoSynthesis\n\ntask = VideoSynthesis.async_call(\n    model=req.get(\"model\", \"wan2.6-i2v-flash\"),\n    prompt=req[\"prompt\"],\n    img_url=req[\"reference_image\"],\n    duration=req.get(\"duration\", 4),\n    fps=req.get(\"fps\", 24),\n    size=req.get(\"size\", \"1280*720\"),\n    api_key=os.getenv(\"DASHSCOPE_API_KEY\"),\n)\n\nfinal = VideoSynthesis.wait(task)\nvideo_url = final.output.get(\"video_url\")\n```\n\n## Operational guidance\n\n- Video generation can take minutes; expose progress and allow cancel\u002Fretry.\n- Cache by `(prompt, negative_prompt, duration, fps, size, seed, reference_image hash, motion_strength)`.\n- Store video assets in object storage and persist only URLs in metadata.\n- `reference_image` can be a URL or local path; the SDK auto-uploads local files.\n- If you get `Field required: input.img_url`, the reference image is missing or not mapped.\n\n## Size notes\n\n- Use `WxH` format (e.g. `1280*720`).\n- Prefer common sizes; unsupported sizes can return 400.\n\n## Output location\n\n- Default output: `output\u002Falicloud-ai-video-wan-video\u002Fvideos\u002F`\n- Override base dir with `OUTPUT_DIR`.\n\n## Anti-patterns\n\n- Do not invent model names or aliases; use official Wan i2v model IDs only.\n- Do not block the UI without progress updates.\n- Do not retry blindly on 4xx; handle validation failures explicitly.\n\n## Workflow\n\n1) Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.\n2) Run one minimal read-only query first to verify connectivity and permissions.\n3) Execute the target operation with explicit parameters and bounded scope.\n4) Verify results and save output\u002Fevidence files.\n\n## References\n\n- See `references\u002Fapi_reference.md` for DashScope SDK mapping and async handling notes.\n\n- Source list: `references\u002Fsources.md`\n",{"name":5,"description":7},"main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__cinience--alicloud-ai-video-wan-video",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add JSGforever\u002Fskillguard --skill alicloud-ai-video-wan-video",{"tool":64,"command":65},"bunx","bunx skills add JSGforever\u002Fskillguard --skill alicloud-ai-video-wan-video",{"tool":67,"command":68},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill alicloud-ai-video-wan-video","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__cinience--alicloud-ai-video-wan-video\u002FSKILL.md",true,[72,78,82,86,92],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"agents\u002Fopenai.yaml","REFERENCE","参考文档",225,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__cinience--alicloud-ai-video-wan-video\u002Fagents\u002Fopenai.yaml",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fapi_reference.md",1610,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__cinience--alicloud-ai-video-wan-video\u002Freferences\u002Fapi_reference.md",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fsources.md",106,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__cinience--alicloud-ai-video-wan-video\u002Freferences\u002Fsources.md",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002Fgenerate_dancing_video.py","SCRIPT","脚本",8058,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__cinience--alicloud-ai-video-wan-video\u002Fscripts\u002Fgenerate_dancing_video.py",{"path":93,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":94,"sourceHtmlUrl":95},"scripts\u002Fgenerate_video.py",6347,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__cinience--alicloud-ai-video-wan-video\u002Fscripts\u002Fgenerate_video.py",[97,124,140,166,188,209],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":104,"publishedAt":46},"01M71HY2SNXBA9Q00WZDTZQ31Z","skillguard-codex-scanner","Hybrid deterministic+LLM agent-skill security scanner. Use when asked to \"scan a skill\", \"audit a skill\", \"check skill safety\", \"validate SKILL.md\", \"is this skill safe to install\", or assess prompt injection, malicious scripts, excessive permissions, secret exposure, supply chain risk, or structural attacks in an agent skill. Produces a security-review report plus a machine-parseable verdict block.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fsrc\u002Fskillguard\u002Fstatic_scanner\u002Fskillguard-codex-scanner\u002FSKILL.md",[103],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[105,106,107,108,109,110,111,112,113,114,115,116,38,117,118,119,120,121,122,123],"scanner","skillguard codex scanner","skillguard","codex","chain","skill security","security-review","review report","structural","secret","prompt injection","security scanner","review","malicious","permissions","exposure","audit","scripts","safe",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":128,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":136,"publishedAt":46},"01M71HY0SPKTT3S27BC2HPAC5M","data-exfiltrator","Analyzes data files","MIT","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Fsmoke-one-skill\u002Fasset1__cisco-ai-defense--data-exfiltrator\u002FSKILL.md",[131],{"categoryNo":132,"categoryName":133,"taxonomyType":134,"taxonomyTypeDesc":135},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[137,138,139],"data","data exfiltrator","files",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":46},"01M71HXVS9EMN44BGDW215FZ72","real-time-collaboration-engine","Build real-time collaborative editing with WebSockets, OT\u002FCRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative editors, whiteboards, video editing. Activate on \"real-time collaboration\", \"WebSocket sync\", \"multiplayer editing\", \"CRDT\", \"presence awareness\". NOT for simple chat, request-response APIs, or single-user apps.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--real-time-collaboration-engine\u002FSKILL.md",[],[147,148,149,150,151,152,28,153,154,155,156,157,158,159,160,161,162,163,164,165],"time","real time collaboration engine","real time collaboration","collaboration","engine","real time","reliability","video editing","performance","conflict resolution","presence","access","apps","updates","Bash","activate","optimizer","react","streaming",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":175,"publishedAt":46},"01M71HXP6CTY4KFN0QVMMN0V7J","react-performance-optimizer","Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on \"React performance\", \"slow render\", \"useMemo\", \"bundle size\", \"virtualization\". NOT for backend optimization, non-React frameworks, or premature optimization.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--react-performance-optimizer\u002FSKILL.md",[172],{"categoryNo":173,"categoryName":174,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[155,176,163,164,177,178,179,180,181,182,147,183,184,159,161,185,162,165,186,187],"react performance optimizer","react performance","performance optimizer","app","nextjs","expert","re","render","2025","code","router","strategies",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":195,"publishedAt":46},"01M71HXH7QXSQB4QTDZ7SP7YXQ","llm-streaming-response-handler","Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI\u002FAnthropic\u002FClaude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on \"LLM streaming\", \"SSE\", \"token stream\", \"chat UI\", \"real-time AI\". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--llm-streaming-response-handler\u002FSKILL.md",[194],{"categoryNo":173,"categoryName":174,"taxonomyType":20,"taxonomyTypeDesc":21},[196,165,197,198,199,200,155,147,201,202,203,161,162,163,204,164,205,206,207,208],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","batch","display","text","server","read",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":213,"categories":214,"keywords":222,"publishedAt":46},"01M71HXCB0E1YRKYW1Y8T0Y106","github-actions-pipeline-builder","Build production CI\u002FCD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on \"GitHub Actions\", \"CI\u002FCD\", \"workflow\", \"deployment pipeline\", \"automated testing\". NOT for Jenkins\u002FCircleCI, manual deployments, or non-GitHub repositories.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--github-actions-pipeline-builder\u002FSKILL.md",[215,218,221],{"categoryNo":216,"categoryName":217,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":219,"categoryName":220,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[223,224,225,226,227,228,44,153,181,229,230,231,162,187,232,208,233,234,235,236],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","testing","ci","workflows","run","release","write","edit","git"]