[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HQSSK2B24XBV84GNMEVB4":3,"skill-same:01M71HQSSK2B24XBV84GNMEVB4":93},{"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":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":54,"install":55,"resources":68},"01M71HQSSK2B24XBV84GNMEVB4","alicloud-ai-multimodal-qwen-vl",null,"Understand images with Alibaba Cloud Model Studio Qwen VL models (qwen3-vl-plus\u002Fqwen3-vl-flash and latest aliases). Use when building image Q&A, visual analysis, OCR-like extraction, chart\u002Ftable reading, or screenshot understanding workflows.","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-multimodal-qwen-vl\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"alicloud ai multimodal qwen vl","multimodal","Qwen","ai multimodal","use","when","alibaba","q&a","studio","reading","chart","images","image","flash","model","table","analysis","ocr","screenshot","workflows","2026-11-10 10:12:30",false,"---\nname: alicloud-ai-multimodal-qwen-vl\ndescription: Understand images with Alibaba Cloud Model Studio Qwen VL models (qwen3-vl-plus\u002Fqwen3-vl-flash and latest aliases). Use when building image Q&A, visual analysis, OCR-like extraction, chart\u002Ftable reading, or screenshot understanding workflows.\n---\n\nCategory: provider\n\n# Model Studio Qwen VL (Image Understanding)\n\n## Validation\n\n```bash\nmkdir -p output\u002Falicloud-ai-multimodal-qwen-vl\npython -m py_compile skills\u002Fai\u002Fmultimodal\u002Falicloud-ai-multimodal-qwen-vl\u002Fscripts\u002Fanalyze_image.py && echo \"py_compile_ok\" > output\u002Falicloud-ai-multimodal-qwen-vl\u002Fvalidate.txt\n```\n\nPass criteria: command exits 0 and `output\u002Falicloud-ai-multimodal-qwen-vl\u002Fvalidate.txt` is generated.\n\n## Output And Evidence\n\n- Save raw model responses and normalized extraction results to `output\u002Falicloud-ai-multimodal-qwen-vl\u002F`.\n- Include input image reference and prompt for traceability.\n\nUse Qwen VL models for image input + text output understanding tasks via DashScope compatible-mode API.\n\n## Prerequisites\n\n- Install dependencies (recommended in a venv):\n\n```bash\npython3 -m venv .venv\n. .venv\u002Fbin\u002Factivate\npython -m pip install requests\n```\n\n- Set `DASHSCOPE_API_KEY` in environment, or add `dashscope_api_key` to `~\u002F.alibabacloud\u002Fcredentials`.\n\n## Critical model names\n\nPrefer the Qwen3 VL family:\n- `qwen3-vl-plus`\n- `qwen3-vl-flash`\n\nWhen you need explicit \"latest\" routing or reproducible snapshots, use supported aliases\u002Fsnapshots from the official model list, such as:\n- `qwen3-vl-plus-latest`\n- `qwen3-vl-plus-2025-12-19`\n- `qwen3-vl-flash-latest`\n\nLegacy names still seen in some workloads:\n- `qwen-vl-max-latest`\n- `qwen-vl-plus-latest`\n\n## Normalized interface (multimodal.chat)\n\n### Request\n\n- `prompt` (string, required): user question\u002Finstruction about image.\n- `image` (string, required): HTTPS URL, local path, or `data:` URL.\n- `model` (string, optional): default `qwen3-vl-plus`.\n- `max_tokens` (int, optional): default `512`.\n- `temperature` (float, optional): default `0.2`.\n- `detail` (string, optional): `auto`\u002F`low`\u002F`high`, default `auto`.\n- `json_mode` (bool, optional): return JSON-only response when possible.\n- `schema` (object, optional): JSON Schema for structured extraction.\n- `max_retries` (int, optional): retry count for `429\u002F5xx`, default `2`.\n- `retry_backoff_s` (float, optional): exponential backoff base seconds, default `1.5`.\n\n### Response\n\n- `text` (string): primary model answer.\n- `model` (string): model actually used.\n- `usage` (object): token usage if returned by backend.\n\n## Quickstart\n\n```bash\npython skills\u002Fai\u002Fmultimodal\u002Falicloud-ai-multimodal-qwen-vl\u002Fscripts\u002Fanalyze_image.py \\\n  --request '{\"prompt\":\"Summarize the main content in this image\",\"image\":\"https:\u002F\u002Fexample.com\u002Fdemo.jpg\"}' \\\n  --print-response\n```\n\nUsing local image:\n\n```bash\npython skills\u002Fai\u002Fmultimodal\u002Falicloud-ai-multimodal-qwen-vl\u002Fscripts\u002Fanalyze_image.py \\\n  --request '{\"prompt\":\"Extract key information from the image\",\"image\":\".\u002Fsamples\u002Finvoice.png\",\"model\":\"qwen3-vl-plus\"}' \\\n  --print-response\n```\n\nStructured extraction (JSON mode):\n\n```bash\npython skills\u002Fai\u002Fmultimodal\u002Falicloud-ai-multimodal-qwen-vl\u002Fscripts\u002Fanalyze_image.py \\\n  --request '{\"prompt\":\"Extract fields: title, amount, date\",\"image\":\".\u002Fsamples\u002Finvoice.png\"}' \\\n  --json-mode \\\n  --print-response\n```\n\nStructured extraction (JSON Schema):\n\n```bash\npython skills\u002Fai\u002Fmultimodal\u002Falicloud-ai-multimodal-qwen-vl\u002Fscripts\u002Fanalyze_image.py \\\n  --request '{\"prompt\":\"Extract invoice fields\",\"image\":\".\u002Fsamples\u002Finvoice.png\"}' \\\n  --schema skills\u002Fai\u002Fmultimodal\u002Falicloud-ai-multimodal-qwen-vl\u002Freferences\u002Fexamples\u002Finvoice.schema.json \\\n  --print-response\n```\n\n## cURL (compatible mode)\n\n```bash\ncurl -sS https:\u002F\u002Fdashscope.aliyuncs.com\u002Fcompatible-mode\u002Fv1\u002Fchat\u002Fcompletions \\\n  -H \"Authorization: Bearer $DASHSCOPE_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"model\":\"qwen3-vl-plus\",\n    \"messages\":[\n      {\n        \"role\":\"user\",\n        \"content\":[\n          {\"type\":\"image_url\",\"image_url\":{\"url\":\"https:\u002F\u002Fexample.com\u002Fdemo.jpg\"}},\n          {\"type\":\"text\",\"text\":\"Describe this image and list executable actions\"}\n        ]\n      }\n    ],\n    \"max_tokens\":512,\n    \"temperature\":0.2\n  }'\n```\n\n## Output location\n\n- If `--output` is set, JSON response is saved to that file.\n- Default output dir convention: `output\u002Falicloud-ai-multimodal-qwen-vl\u002F`.\n\n## Smoke test\n\n```bash\npython tests\u002Fai\u002Fmultimodal\u002Falicloud-ai-multimodal-qwen-vl-test\u002Fscripts\u002Fsmoke_test_qwen_vl.py \\\n  --image .\u002Ftmp\u002Fvl_test_cat.png\n```\n\n## Error handling\n\n| Error | Likely cause | Action |\n| --- | --- | --- |\n| 401\u002F403 | Missing or invalid key | Check `DASHSCOPE_API_KEY` and account permissions. |\n| 400 | Invalid request schema or unsupported image source | Validate `messages` content and image URL\u002Fpath format. |\n| 429 | Rate limit | Retry with exponential backoff and lower concurrency. |\n| 5xx | Temporary backend issue | Retry with backoff and idempotent request design. |\n\n## Operational guidance\n\n- For stable production behavior, pin snapshot model IDs instead of pure `-latest`.\n- Compress very large images before upload to reduce latency and cost.\n- Add explicit extraction constraints in prompt (fields, JSON shape, language).\n- For OCR-like output, ask for confidence notes and unresolved text markers.\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- Source list: `references\u002Fsources.md`\n- API notes: `references\u002Fapi_reference.md`\n","Category: provider\n\n# Model Studio Qwen VL (Image Understanding)\n\n## Validation\n\n```bash\nmkdir -p output\u002Falicloud-ai-multimodal-qwen-vl\npython -m py_compile skills\u002Fai\u002Fmultimodal\u002Falicloud-ai-multimodal-qwen-vl\u002Fscripts\u002Fanalyze_image.py && echo \"py_compile_ok\" > output\u002Falicloud-ai-multimodal-qwen-vl\u002Fvalidate.txt\n```\n\nPass criteria: command exits 0 and `output\u002Falicloud-ai-multimodal-qwen-vl\u002Fvalidate.txt` is generated.\n\n## Output And Evidence\n\n- Save raw model responses and normalized extraction results to `output\u002Falicloud-ai-multimodal-qwen-vl\u002F`.\n- Include input image reference and prompt for traceability.\n\nUse Qwen VL models for image input + text output understanding tasks via DashScope compatible-mode API.\n\n## Prerequisites\n\n- Install dependencies (recommended in a venv):\n\n```bash\npython3 -m venv .venv\n. .venv\u002Fbin\u002Factivate\npython -m pip install requests\n```\n\n- Set `DASHSCOPE_API_KEY` in environment, or add `dashscope_api_key` to `~\u002F.alibabacloud\u002Fcredentials`.\n\n## Critical model names\n\nPrefer the Qwen3 VL family:\n- `qwen3-vl-plus`\n- `qwen3-vl-flash`\n\nWhen you need explicit \"latest\" routing or reproducible snapshots, use supported aliases\u002Fsnapshots from the official model list, such as:\n- `qwen3-vl-plus-latest`\n- `qwen3-vl-plus-2025-12-19`\n- `qwen3-vl-flash-latest`\n\nLegacy names still seen in some workloads:\n- `qwen-vl-max-latest`\n- `qwen-vl-plus-latest`\n\n## Normalized interface (multimodal.chat)\n\n### Request\n\n- `prompt` (string, required): user question\u002Finstruction about image.\n- `image` (string, required): HTTPS URL, local path, or `data:` URL.\n- `model` (string, optional): default `qwen3-vl-plus`.\n- `max_tokens` (int, optional): default `512`.\n- `temperature` (float, optional): default `0.2`.\n- `detail` (string, optional): `auto`\u002F`low`\u002F`high`, default `auto`.\n- `json_mode` (bool, optional): return JSON-only response when possible.\n- `schema` (object, optional): JSON Schema for structured extraction.\n- `max_retries` (int, optional): retry count for `429\u002F5xx`, default `2`.\n- `retry_backoff_s` (float, optional): exponential backoff base seconds, default `1.5`.\n\n### Response\n\n- `text` (string): primary model answer.\n- `model` (string): model actually used.\n- `usage` (object): token usage if returned by backend.\n\n## Quickstart\n\n```bash\npython skills\u002Fai\u002Fmultimodal\u002Falicloud-ai-multimodal-qwen-vl\u002Fscripts\u002Fanalyze_image.py \\\n  --request '{\"prompt\":\"Summarize the main content in this image\",\"image\":\"https:\u002F\u002Fexample.com\u002Fdemo.jpg\"}' \\\n  --print-response\n```\n\nUsing local image:\n\n```bash\npython skills\u002Fai\u002Fmultimodal\u002Falicloud-ai-multimodal-qwen-vl\u002Fscripts\u002Fanalyze_image.py \\\n  --request '{\"prompt\":\"Extract key information from the image\",\"image\":\".\u002Fsamples\u002Finvoice.png\",\"model\":\"qwen3-vl-plus\"}' \\\n  --print-response\n```\n\nStructured extraction (JSON mode):\n\n```bash\npython skills\u002Fai\u002Fmultimodal\u002Falicloud-ai-multimodal-qwen-vl\u002Fscripts\u002Fanalyze_image.py \\\n  --request '{\"prompt\":\"Extract fields: title, amount, date\",\"image\":\".\u002Fsamples\u002Finvoice.png\"}' \\\n  --json-mode \\\n  --print-response\n```\n\nStructured extraction (JSON Schema):\n\n```bash\npython skills\u002Fai\u002Fmultimodal\u002Falicloud-ai-multimodal-qwen-vl\u002Fscripts\u002Fanalyze_image.py \\\n  --request '{\"prompt\":\"Extract invoice fields\",\"image\":\".\u002Fsamples\u002Finvoice.png\"}' \\\n  --schema skills\u002Fai\u002Fmultimodal\u002Falicloud-ai-multimodal-qwen-vl\u002Freferences\u002Fexamples\u002Finvoice.schema.json \\\n  --print-response\n```\n\n## cURL (compatible mode)\n\n```bash\ncurl -sS https:\u002F\u002Fdashscope.aliyuncs.com\u002Fcompatible-mode\u002Fv1\u002Fchat\u002Fcompletions \\\n  -H \"Authorization: Bearer $DASHSCOPE_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"model\":\"qwen3-vl-plus\",\n    \"messages\":[\n      {\n        \"role\":\"user\",\n        \"content\":[\n          {\"type\":\"image_url\",\"image_url\":{\"url\":\"https:\u002F\u002Fexample.com\u002Fdemo.jpg\"}},\n          {\"type\":\"text\",\"text\":\"Describe this image and list executable actions\"}\n        ]\n      }\n    ],\n    \"max_tokens\":512,\n    \"temperature\":0.2\n  }'\n```\n\n## Output location\n\n- If `--output` is set, JSON response is saved to that file.\n- Default output dir convention: `output\u002Falicloud-ai-multimodal-qwen-vl\u002F`.\n\n## Smoke test\n\n```bash\npython tests\u002Fai\u002Fmultimodal\u002Falicloud-ai-multimodal-qwen-vl-test\u002Fscripts\u002Fsmoke_test_qwen_vl.py \\\n  --image .\u002Ftmp\u002Fvl_test_cat.png\n```\n\n## Error handling\n\n| Error | Likely cause | Action |\n| --- | --- | --- |\n| 401\u002F403 | Missing or invalid key | Check `DASHSCOPE_API_KEY` and account permissions. |\n| 400 | Invalid request schema or unsupported image source | Validate `messages` content and image URL\u002Fpath format. |\n| 429 | Rate limit | Retry with exponential backoff and lower concurrency. |\n| 5xx | Temporary backend issue | Retry with backoff and idempotent request design. |\n\n## Operational guidance\n\n- For stable production behavior, pin snapshot model IDs instead of pure `-latest`.\n- Compress very large images before upload to reduce latency and cost.\n- Add explicit extraction constraints in prompt (fields, JSON shape, language).\n- For OCR-like output, ask for confidence notes and unresolved text markers.\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- Source list: `references\u002Fsources.md`\n- API notes: `references\u002Fapi_reference.md`\n",{"name":5,"description":7},"main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__cinience--alicloud-ai-multimodal-qwen-vl",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add JSGforever\u002Fskillguard --skill alicloud-ai-multimodal-qwen-vl",{"tool":61,"command":62},"bunx","bunx skills add JSGforever\u002Fskillguard --skill alicloud-ai-multimodal-qwen-vl",{"tool":64,"command":65},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill alicloud-ai-multimodal-qwen-vl","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__cinience--alicloud-ai-multimodal-qwen-vl\u002FSKILL.md",true,[69,75,79,83,87],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"agents\u002Fopenai.yaml","REFERENCE","参考文档",245,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__cinience--alicloud-ai-multimodal-qwen-vl\u002Fagents\u002Fopenai.yaml",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fapi_reference.md",1540,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__cinience--alicloud-ai-multimodal-qwen-vl\u002Freferences\u002Fapi_reference.md",{"path":80,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fexamples\u002Finvoice.schema.json",265,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__cinience--alicloud-ai-multimodal-qwen-vl\u002Freferences\u002Fexamples\u002Finvoice.schema.json",{"path":84,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fsources.md",441,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__cinience--alicloud-ai-multimodal-qwen-vl\u002Freferences\u002Fsources.md",{"path":88,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":91,"sourceHtmlUrl":92},"scripts\u002Fanalyze_image.py","SCRIPT","脚本",11013,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__cinience--alicloud-ai-multimodal-qwen-vl\u002Fscripts\u002Fanalyze_image.py",[94,123,139,166,188,209],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":103,"publishedAt":43},"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",[100],{"categoryNo":101,"categoryName":102,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[104,105,106,107,108,109,110,111,112,113,114,115,28,116,117,118,119,120,121,122],"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":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":127,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":135,"publishedAt":43},"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",[130],{"categoryNo":131,"categoryName":132,"taxonomyType":133,"taxonomyTypeDesc":134},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[136,137,138],"data","data exfiltrator","files",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":43},"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",[],[146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165],"time","real time collaboration engine","real time collaboration","collaboration","engine","real time","Video","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":43},"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",[155,176,163,164,177,178,179,180,181,182,146,183,184,159,161,185,162,165,186,187],"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":43},"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},[196,165,197,198,199,200,155,146,201,202,203,161,162,163,204,164,205,206,207,208],"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":43},"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":101,"categoryName":102,"taxonomyType":20,"taxonomyTypeDesc":21},[223,224,225,226,227,228,229,153,181,230,231,42,162,187,232,208,233,234,235,236],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","testing","ci","run","release","write","edit","git"]