[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-minimax-comfyui-workflow":3,"mdc--leu6p0-key":37,"related-repo-minimax-comfyui-workflow":1158,"related-org-minimax-comfyui-workflow":1259},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":32,"sourceUrl":35,"mdContent":36},"comfyui-workflow","execute and monitor ComfyUI workflows","Submit a ComfyUI workflow JSON to a local 8188 server, monitor the queue, and download generated images. Use this Skill when the user wants to run a saved workflow, check whether ComfyUI is busy, fetch a generated image, list available checkpoints, or automate a reproducible generation pipeline.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"minimax","MiniMax","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fminimax.jpg","MiniMax-AI",[13,17,20,23],{"name":14,"slug":15,"type":16},"Automation","automation","tag",{"name":18,"slug":19,"type":16},"Creative","creative",{"name":21,"slug":22,"type":16},"Images","images",{"name":24,"slug":25,"type":16},"Generative Art","generative-art",5,"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-Code-Plugins","2026-08-27T13:32:24.894724",null,2,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":34},[],"Community registry and contribution toolkit for MiniMax Code plugins.","https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-Code-Plugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fantianqi\u002Fcomfyui-studio\u002Fskills\u002Fcomfyui-workflow","---\nname: comfyui-workflow\ndescription: Submit a ComfyUI workflow JSON to a local 8188 server, monitor the queue, and download generated images. Use this Skill when the user wants to run a saved workflow, check whether ComfyUI is busy, fetch a generated image, list available checkpoints, or automate a reproducible generation pipeline.\n---\n\n# ComfyUI Workflow\n\nSubmit workflows, monitor the queue, and retrieve outputs from a local ComfyUI server. This is\nthe workhorse Skill; `comfyui-character` builds on top of it for character-consistent generation.\n\n## Scope\n\nThis Skill covers the **transport** between an agent and a local ComfyUI server. It does not\nedit workflows, train models, or invent prompts — those concerns live in sibling Skills. It\nassumes the user already has a workflow JSON they want to run (either a file the user wrote or\none of the bundled `workflows\u002F*.json` examples).\n\n## Two equivalent entry points\n\nYou can drive ComfyUI from this Skill in either of two ways. Pick whichever the host environment\nsupports best.\n\n### A. Python script (CLI-friendly, no MCP required)\n\n```bash\n# Health probe\npython scripts\u002Fsubmit_workflow.py --probe\n\n# Submit a workflow\npython scripts\u002Fsubmit_workflow.py \\\n  --workflow .\u002Fworkflows\u002Ftext-to-image.json \\\n  --prompt \"a tabby cat sleeping on a windowsill, morning light, photorealistic\" \\\n  --output-dir .\u002Fout\n\n# Check the queue without submitting\npython scripts\u002Fsubmit_workflow.py --queue\n\n# Download a specific image\npython scripts\u002Fsubmit_workflow.py --download \\\n  --filename ComfyUI_00001_.png --output-dir .\u002Fout\n```\n\nThe script lives at `skills\u002Fcomfyui-workflow\u002Fscripts\u002Fsubmit_workflow.py` (relative to the Plugin\nroot) and accepts `COMFYUI_URL` from the environment, falling back to `http:\u002F\u002F127.0.0.1:8188`.\nFull flag list in `references\u002Fapi-reference.md`.\n\n### B. stdio MCP server (no Python required)\n\nWhen the host agent is MCP-aware, the Plugin's `server.mjs` exposes three tools that mirror the\nPython script:\n\n| Tool | Mirrors |\n|---|---|\n| `submit_prompt` | `--workflow` invocation |\n| `check_queue`   | `--queue` invocation |\n| `get_image`     | `--download` invocation |\n\nThe MCP server has zero npm dependencies. It is a 200-line stdio JSON-RPC server in plain Node.\nSee `mcp.json` for the registration snippet and `server.mjs` for the source.\n\n## Workflow contract\n\nComfyUI accepts a JSON object whose top-level keys are node IDs and whose values are\n`{class_type, inputs}` records. When the user provides a workflow, **do not edit the structure**\nunless they ask. Two patterns are common:\n\n- A workflow file saved from the ComfyUI web UI: keys are numeric strings, `class_type` matches\n  the node name in the editor, `inputs` reference other nodes by `[nodeId, outputIndex]`.\n- An \"API format\" workflow produced by ComfyUI's \"Save (API Format)\" menu: same shape, but with\n  widget values inlined into `inputs`.\n\nBoth work identically when POSTed to `\u002Fprompt`. The Plugin's `workflows\u002Ftext-to-image.json` and\n`workflows\u002Fimage-to-image.json` are in the API format.\n\n## Overriding prompt values at submit time\n\nThe bundled Python script understands a tiny templating convention so you do not have to rewrite\nthe workflow JSON for every run. In a workflow, a `CLIPTextEncode` node with `inputs.text`\nstarting with the literal string `__PROMPT__` will have that text replaced with the value of\n`--prompt` on the command line before submission. This is a no-op for nodes that do not opt in.\n\n```json\n{\n  \"30\": {\n    \"class_type\": \"CLIPTextEncode\",\n    \"inputs\": { \"text\": \"__PROMPT__\", \"clip\": [\"4\", 0] }\n  }\n}\n```\n\nFor workflows without that marker, the user must edit the workflow JSON directly.\n\n## Step-by-step recipe\n\n1. **Health probe.** Either call `check_queue` via MCP or run `submit_workflow.py --probe`. Stop\n   and report if ComfyUI is unreachable; do not invent a successful run.\n2. **Resolve the workflow.** If the user named a file, read it. If they named a workflow by\n   description (e.g. \"the one with the upscale at the end\"), ask for a path or a saved name.\n3. **Apply prompt override if used.** If `--prompt` is provided and the workflow contains\n   `__PROMPT__`, substitute. Otherwise pass the workflow through unchanged.\n4. **Submit.** POST to `\u002Fprompt` with `{\"prompt\": \u003Cworkflow>}`. Capture `prompt_id`.\n5. **Poll.** Loop `GET \u002Fhistory\u002F\u003Cprompt_id>` with a 2-second sleep. Stop on terminal status\n   (`success`, `error`, or `cancelled`). Use a 15-minute cap; long jobs should be split.\n6. **Resolve outputs.** The `outputs` object lists the `SaveImage` \u002F `VHS_VideoCombine` files\n   produced. For each, fetch `GET \u002Fview?filename=...&subfolder=...&type=output`.\n7. **Report.** Tell the user the prompt_id, the time taken, the saved file paths, and any\n   warnings (low VRAM, retries, partial outputs).\n\n## Long jobs and VRAM safety\n\n- ComfyUI 22B-class models can hold the GPU for hours. The Plugin does not implement a watchdog;\n  for jobs longer than 30 minutes, instruct the user to watch `nvidia-smi` themselves.\n- If a poll returns an error status, capture the full `outputs` block and the error message;\n  report both. Do not retry automatically — generation is expensive.\n\n## Requirements\n\n- ComfyUI running locally (or reachable at `COMFYUI_URL`).\n- Python 3.10+ if using the script. The MCP server requires Node 18+.\n- No additional accounts, paid services, or network destinations.\n\n## License\n\nApache-2.0. See [LICENSE](..\u002F..\u002FLICENSE).\n",{"data":38,"body":39},{"name":4,"description":6},{"type":40,"children":41},"root",[42,50,65,72,93,99,104,111,346,383,389,402,497,517,523,543,587,616,622,659,869,874,880,1068,1074,1102,1108,1133,1139,1152],{"type":43,"tag":44,"props":45,"children":46},"element","h1",{"id":4},[47],{"type":48,"value":49},"text","ComfyUI Workflow",{"type":43,"tag":51,"props":52,"children":53},"p",{},[54,56,63],{"type":48,"value":55},"Submit workflows, monitor the queue, and retrieve outputs from a local ComfyUI server. This is\nthe workhorse Skill; ",{"type":43,"tag":57,"props":58,"children":60},"code",{"className":59},[],[61],{"type":48,"value":62},"comfyui-character",{"type":48,"value":64}," builds on top of it for character-consistent generation.",{"type":43,"tag":66,"props":67,"children":69},"h2",{"id":68},"scope",[70],{"type":48,"value":71},"Scope",{"type":43,"tag":51,"props":73,"children":74},{},[75,77,83,85,91],{"type":48,"value":76},"This Skill covers the ",{"type":43,"tag":78,"props":79,"children":80},"strong",{},[81],{"type":48,"value":82},"transport",{"type":48,"value":84}," between an agent and a local ComfyUI server. It does not\nedit workflows, train models, or invent prompts — those concerns live in sibling Skills. It\nassumes the user already has a workflow JSON they want to run (either a file the user wrote or\none of the bundled ",{"type":43,"tag":57,"props":86,"children":88},{"className":87},[],[89],{"type":48,"value":90},"workflows\u002F*.json",{"type":48,"value":92}," examples).",{"type":43,"tag":66,"props":94,"children":96},{"id":95},"two-equivalent-entry-points",[97],{"type":48,"value":98},"Two equivalent entry points",{"type":43,"tag":51,"props":100,"children":101},{},[102],{"type":48,"value":103},"You can drive ComfyUI from this Skill in either of two ways. Pick whichever the host environment\nsupports best.",{"type":43,"tag":105,"props":106,"children":108},"h3",{"id":107},"a-python-script-cli-friendly-no-mcp-required",[109],{"type":48,"value":110},"A. Python script (CLI-friendly, no MCP required)",{"type":43,"tag":112,"props":113,"children":118},"pre",{"className":114,"code":115,"language":116,"meta":117,"style":117},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# Health probe\npython scripts\u002Fsubmit_workflow.py --probe\n\n# Submit a workflow\npython scripts\u002Fsubmit_workflow.py \\\n  --workflow .\u002Fworkflows\u002Ftext-to-image.json \\\n  --prompt \"a tabby cat sleeping on a windowsill, morning light, photorealistic\" \\\n  --output-dir .\u002Fout\n\n# Check the queue without submitting\npython scripts\u002Fsubmit_workflow.py --queue\n\n# Download a specific image\npython scripts\u002Fsubmit_workflow.py --download \\\n  --filename ComfyUI_00001_.png --output-dir .\u002Fout\n","bash","",[119],{"type":43,"tag":57,"props":120,"children":121},{"__ignoreMap":117},[122,134,154,164,173,190,208,237,251,259,268,285,293,302,323],{"type":43,"tag":123,"props":124,"children":127},"span",{"class":125,"line":126},"line",1,[128],{"type":43,"tag":123,"props":129,"children":131},{"style":130},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[132],{"type":48,"value":133},"# Health probe\n",{"type":43,"tag":123,"props":135,"children":136},{"class":125,"line":30},[137,143,149],{"type":43,"tag":123,"props":138,"children":140},{"style":139},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[141],{"type":48,"value":142},"python",{"type":43,"tag":123,"props":144,"children":146},{"style":145},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[147],{"type":48,"value":148}," scripts\u002Fsubmit_workflow.py",{"type":43,"tag":123,"props":150,"children":151},{"style":145},[152],{"type":48,"value":153}," --probe\n",{"type":43,"tag":123,"props":155,"children":157},{"class":125,"line":156},3,[158],{"type":43,"tag":123,"props":159,"children":161},{"emptyLinePlaceholder":160},true,[162],{"type":48,"value":163},"\n",{"type":43,"tag":123,"props":165,"children":167},{"class":125,"line":166},4,[168],{"type":43,"tag":123,"props":169,"children":170},{"style":130},[171],{"type":48,"value":172},"# Submit a workflow\n",{"type":43,"tag":123,"props":174,"children":175},{"class":125,"line":26},[176,180,184],{"type":43,"tag":123,"props":177,"children":178},{"style":139},[179],{"type":48,"value":142},{"type":43,"tag":123,"props":181,"children":182},{"style":145},[183],{"type":48,"value":148},{"type":43,"tag":123,"props":185,"children":187},{"style":186},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[188],{"type":48,"value":189}," \\\n",{"type":43,"tag":123,"props":191,"children":193},{"class":125,"line":192},6,[194,199,204],{"type":43,"tag":123,"props":195,"children":196},{"style":145},[197],{"type":48,"value":198},"  --workflow",{"type":43,"tag":123,"props":200,"children":201},{"style":145},[202],{"type":48,"value":203}," .\u002Fworkflows\u002Ftext-to-image.json",{"type":43,"tag":123,"props":205,"children":206},{"style":186},[207],{"type":48,"value":189},{"type":43,"tag":123,"props":209,"children":211},{"class":125,"line":210},7,[212,217,223,228,233],{"type":43,"tag":123,"props":213,"children":214},{"style":145},[215],{"type":48,"value":216},"  --prompt",{"type":43,"tag":123,"props":218,"children":220},{"style":219},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[221],{"type":48,"value":222}," \"",{"type":43,"tag":123,"props":224,"children":225},{"style":145},[226],{"type":48,"value":227},"a tabby cat sleeping on a windowsill, morning light, photorealistic",{"type":43,"tag":123,"props":229,"children":230},{"style":219},[231],{"type":48,"value":232},"\"",{"type":43,"tag":123,"props":234,"children":235},{"style":186},[236],{"type":48,"value":189},{"type":43,"tag":123,"props":238,"children":240},{"class":125,"line":239},8,[241,246],{"type":43,"tag":123,"props":242,"children":243},{"style":145},[244],{"type":48,"value":245},"  --output-dir",{"type":43,"tag":123,"props":247,"children":248},{"style":145},[249],{"type":48,"value":250}," .\u002Fout\n",{"type":43,"tag":123,"props":252,"children":254},{"class":125,"line":253},9,[255],{"type":43,"tag":123,"props":256,"children":257},{"emptyLinePlaceholder":160},[258],{"type":48,"value":163},{"type":43,"tag":123,"props":260,"children":262},{"class":125,"line":261},10,[263],{"type":43,"tag":123,"props":264,"children":265},{"style":130},[266],{"type":48,"value":267},"# Check the queue without submitting\n",{"type":43,"tag":123,"props":269,"children":271},{"class":125,"line":270},11,[272,276,280],{"type":43,"tag":123,"props":273,"children":274},{"style":139},[275],{"type":48,"value":142},{"type":43,"tag":123,"props":277,"children":278},{"style":145},[279],{"type":48,"value":148},{"type":43,"tag":123,"props":281,"children":282},{"style":145},[283],{"type":48,"value":284}," --queue\n",{"type":43,"tag":123,"props":286,"children":288},{"class":125,"line":287},12,[289],{"type":43,"tag":123,"props":290,"children":291},{"emptyLinePlaceholder":160},[292],{"type":48,"value":163},{"type":43,"tag":123,"props":294,"children":296},{"class":125,"line":295},13,[297],{"type":43,"tag":123,"props":298,"children":299},{"style":130},[300],{"type":48,"value":301},"# Download a specific image\n",{"type":43,"tag":123,"props":303,"children":305},{"class":125,"line":304},14,[306,310,314,319],{"type":43,"tag":123,"props":307,"children":308},{"style":139},[309],{"type":48,"value":142},{"type":43,"tag":123,"props":311,"children":312},{"style":145},[313],{"type":48,"value":148},{"type":43,"tag":123,"props":315,"children":316},{"style":145},[317],{"type":48,"value":318}," --download",{"type":43,"tag":123,"props":320,"children":321},{"style":186},[322],{"type":48,"value":189},{"type":43,"tag":123,"props":324,"children":326},{"class":125,"line":325},15,[327,332,337,342],{"type":43,"tag":123,"props":328,"children":329},{"style":145},[330],{"type":48,"value":331},"  --filename",{"type":43,"tag":123,"props":333,"children":334},{"style":145},[335],{"type":48,"value":336}," ComfyUI_00001_.png",{"type":43,"tag":123,"props":338,"children":339},{"style":145},[340],{"type":48,"value":341}," --output-dir",{"type":43,"tag":123,"props":343,"children":344},{"style":145},[345],{"type":48,"value":250},{"type":43,"tag":51,"props":347,"children":348},{},[349,351,357,359,365,367,373,375,381],{"type":48,"value":350},"The script lives at ",{"type":43,"tag":57,"props":352,"children":354},{"className":353},[],[355],{"type":48,"value":356},"skills\u002Fcomfyui-workflow\u002Fscripts\u002Fsubmit_workflow.py",{"type":48,"value":358}," (relative to the Plugin\nroot) and accepts ",{"type":43,"tag":57,"props":360,"children":362},{"className":361},[],[363],{"type":48,"value":364},"COMFYUI_URL",{"type":48,"value":366}," from the environment, falling back to ",{"type":43,"tag":57,"props":368,"children":370},{"className":369},[],[371],{"type":48,"value":372},"http:\u002F\u002F127.0.0.1:8188",{"type":48,"value":374},".\nFull flag list in ",{"type":43,"tag":57,"props":376,"children":378},{"className":377},[],[379],{"type":48,"value":380},"references\u002Fapi-reference.md",{"type":48,"value":382},".",{"type":43,"tag":105,"props":384,"children":386},{"id":385},"b-stdio-mcp-server-no-python-required",[387],{"type":48,"value":388},"B. stdio MCP server (no Python required)",{"type":43,"tag":51,"props":390,"children":391},{},[392,394,400],{"type":48,"value":393},"When the host agent is MCP-aware, the Plugin's ",{"type":43,"tag":57,"props":395,"children":397},{"className":396},[],[398],{"type":48,"value":399},"server.mjs",{"type":48,"value":401}," exposes three tools that mirror the\nPython script:",{"type":43,"tag":403,"props":404,"children":405},"table",{},[406,425],{"type":43,"tag":407,"props":408,"children":409},"thead",{},[410],{"type":43,"tag":411,"props":412,"children":413},"tr",{},[414,420],{"type":43,"tag":415,"props":416,"children":417},"th",{},[418],{"type":48,"value":419},"Tool",{"type":43,"tag":415,"props":421,"children":422},{},[423],{"type":48,"value":424},"Mirrors",{"type":43,"tag":426,"props":427,"children":428},"tbody",{},[429,453,475],{"type":43,"tag":411,"props":430,"children":431},{},[432,442],{"type":43,"tag":433,"props":434,"children":435},"td",{},[436],{"type":43,"tag":57,"props":437,"children":439},{"className":438},[],[440],{"type":48,"value":441},"submit_prompt",{"type":43,"tag":433,"props":443,"children":444},{},[445,451],{"type":43,"tag":57,"props":446,"children":448},{"className":447},[],[449],{"type":48,"value":450},"--workflow",{"type":48,"value":452}," invocation",{"type":43,"tag":411,"props":454,"children":455},{},[456,465],{"type":43,"tag":433,"props":457,"children":458},{},[459],{"type":43,"tag":57,"props":460,"children":462},{"className":461},[],[463],{"type":48,"value":464},"check_queue",{"type":43,"tag":433,"props":466,"children":467},{},[468,474],{"type":43,"tag":57,"props":469,"children":471},{"className":470},[],[472],{"type":48,"value":473},"--queue",{"type":48,"value":452},{"type":43,"tag":411,"props":476,"children":477},{},[478,487],{"type":43,"tag":433,"props":479,"children":480},{},[481],{"type":43,"tag":57,"props":482,"children":484},{"className":483},[],[485],{"type":48,"value":486},"get_image",{"type":43,"tag":433,"props":488,"children":489},{},[490,496],{"type":43,"tag":57,"props":491,"children":493},{"className":492},[],[494],{"type":48,"value":495},"--download",{"type":48,"value":452},{"type":43,"tag":51,"props":498,"children":499},{},[500,502,508,510,515],{"type":48,"value":501},"The MCP server has zero npm dependencies. It is a 200-line stdio JSON-RPC server in plain Node.\nSee ",{"type":43,"tag":57,"props":503,"children":505},{"className":504},[],[506],{"type":48,"value":507},"mcp.json",{"type":48,"value":509}," for the registration snippet and ",{"type":43,"tag":57,"props":511,"children":513},{"className":512},[],[514],{"type":48,"value":399},{"type":48,"value":516}," for the source.",{"type":43,"tag":66,"props":518,"children":520},{"id":519},"workflow-contract",[521],{"type":48,"value":522},"Workflow contract",{"type":43,"tag":51,"props":524,"children":525},{},[526,528,534,536,541],{"type":48,"value":527},"ComfyUI accepts a JSON object whose top-level keys are node IDs and whose values are\n",{"type":43,"tag":57,"props":529,"children":531},{"className":530},[],[532],{"type":48,"value":533},"{class_type, inputs}",{"type":48,"value":535}," records. When the user provides a workflow, ",{"type":43,"tag":78,"props":537,"children":538},{},[539],{"type":48,"value":540},"do not edit the structure",{"type":48,"value":542},"\nunless they ask. Two patterns are common:",{"type":43,"tag":544,"props":545,"children":546},"ul",{},[547,576],{"type":43,"tag":548,"props":549,"children":550},"li",{},[551,553,559,561,567,569,575],{"type":48,"value":552},"A workflow file saved from the ComfyUI web UI: keys are numeric strings, ",{"type":43,"tag":57,"props":554,"children":556},{"className":555},[],[557],{"type":48,"value":558},"class_type",{"type":48,"value":560}," matches\nthe node name in the editor, ",{"type":43,"tag":57,"props":562,"children":564},{"className":563},[],[565],{"type":48,"value":566},"inputs",{"type":48,"value":568}," reference other nodes by ",{"type":43,"tag":57,"props":570,"children":572},{"className":571},[],[573],{"type":48,"value":574},"[nodeId, outputIndex]",{"type":48,"value":382},{"type":43,"tag":548,"props":577,"children":578},{},[579,581,586],{"type":48,"value":580},"An \"API format\" workflow produced by ComfyUI's \"Save (API Format)\" menu: same shape, but with\nwidget values inlined into ",{"type":43,"tag":57,"props":582,"children":584},{"className":583},[],[585],{"type":48,"value":566},{"type":48,"value":382},{"type":43,"tag":51,"props":588,"children":589},{},[590,592,598,600,606,608,614],{"type":48,"value":591},"Both work identically when POSTed to ",{"type":43,"tag":57,"props":593,"children":595},{"className":594},[],[596],{"type":48,"value":597},"\u002Fprompt",{"type":48,"value":599},". The Plugin's ",{"type":43,"tag":57,"props":601,"children":603},{"className":602},[],[604],{"type":48,"value":605},"workflows\u002Ftext-to-image.json",{"type":48,"value":607}," and\n",{"type":43,"tag":57,"props":609,"children":611},{"className":610},[],[612],{"type":48,"value":613},"workflows\u002Fimage-to-image.json",{"type":48,"value":615}," are in the API format.",{"type":43,"tag":66,"props":617,"children":619},{"id":618},"overriding-prompt-values-at-submit-time",[620],{"type":48,"value":621},"Overriding prompt values at submit time",{"type":43,"tag":51,"props":623,"children":624},{},[625,627,633,635,641,643,649,651,657],{"type":48,"value":626},"The bundled Python script understands a tiny templating convention so you do not have to rewrite\nthe workflow JSON for every run. In a workflow, a ",{"type":43,"tag":57,"props":628,"children":630},{"className":629},[],[631],{"type":48,"value":632},"CLIPTextEncode",{"type":48,"value":634}," node with ",{"type":43,"tag":57,"props":636,"children":638},{"className":637},[],[639],{"type":48,"value":640},"inputs.text",{"type":48,"value":642},"\nstarting with the literal string ",{"type":43,"tag":57,"props":644,"children":646},{"className":645},[],[647],{"type":48,"value":648},"__PROMPT__",{"type":48,"value":650}," will have that text replaced with the value of\n",{"type":43,"tag":57,"props":652,"children":654},{"className":653},[],[655],{"type":48,"value":656},"--prompt",{"type":48,"value":658}," on the command line before submission. This is a no-op for nodes that do not opt in.",{"type":43,"tag":112,"props":660,"children":664},{"className":661,"code":662,"language":663,"meta":117,"style":117},"language-json shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","{\n  \"30\": {\n    \"class_type\": \"CLIPTextEncode\",\n    \"inputs\": { \"text\": \"__PROMPT__\", \"clip\": [\"4\", 0] }\n  }\n}\n","json",[665],{"type":43,"tag":57,"props":666,"children":667},{"__ignoreMap":117},[668,676,704,741,853,861],{"type":43,"tag":123,"props":669,"children":670},{"class":125,"line":126},[671],{"type":43,"tag":123,"props":672,"children":673},{"style":219},[674],{"type":48,"value":675},"{\n",{"type":43,"tag":123,"props":677,"children":678},{"class":125,"line":30},[679,684,690,694,699],{"type":43,"tag":123,"props":680,"children":681},{"style":219},[682],{"type":48,"value":683},"  \"",{"type":43,"tag":123,"props":685,"children":687},{"style":686},"--shiki-light:#9C3EDA;--shiki-default:#C792EA;--shiki-dark:#C792EA",[688],{"type":48,"value":689},"30",{"type":43,"tag":123,"props":691,"children":692},{"style":219},[693],{"type":48,"value":232},{"type":43,"tag":123,"props":695,"children":696},{"style":219},[697],{"type":48,"value":698},":",{"type":43,"tag":123,"props":700,"children":701},{"style":219},[702],{"type":48,"value":703}," {\n",{"type":43,"tag":123,"props":705,"children":706},{"class":125,"line":156},[707,712,716,720,724,728,732,736],{"type":43,"tag":123,"props":708,"children":709},{"style":219},[710],{"type":48,"value":711},"    \"",{"type":43,"tag":123,"props":713,"children":714},{"style":139},[715],{"type":48,"value":558},{"type":43,"tag":123,"props":717,"children":718},{"style":219},[719],{"type":48,"value":232},{"type":43,"tag":123,"props":721,"children":722},{"style":219},[723],{"type":48,"value":698},{"type":43,"tag":123,"props":725,"children":726},{"style":219},[727],{"type":48,"value":222},{"type":43,"tag":123,"props":729,"children":730},{"style":145},[731],{"type":48,"value":632},{"type":43,"tag":123,"props":733,"children":734},{"style":219},[735],{"type":48,"value":232},{"type":43,"tag":123,"props":737,"children":738},{"style":219},[739],{"type":48,"value":740},",\n",{"type":43,"tag":123,"props":742,"children":743},{"class":125,"line":166},[744,748,752,756,760,765,769,774,778,782,786,790,794,799,803,808,812,816,821,825,830,834,838,843,848],{"type":43,"tag":123,"props":745,"children":746},{"style":219},[747],{"type":48,"value":711},{"type":43,"tag":123,"props":749,"children":750},{"style":139},[751],{"type":48,"value":566},{"type":43,"tag":123,"props":753,"children":754},{"style":219},[755],{"type":48,"value":232},{"type":43,"tag":123,"props":757,"children":758},{"style":219},[759],{"type":48,"value":698},{"type":43,"tag":123,"props":761,"children":762},{"style":219},[763],{"type":48,"value":764}," {",{"type":43,"tag":123,"props":766,"children":767},{"style":219},[768],{"type":48,"value":222},{"type":43,"tag":123,"props":770,"children":772},{"style":771},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[773],{"type":48,"value":48},{"type":43,"tag":123,"props":775,"children":776},{"style":219},[777],{"type":48,"value":232},{"type":43,"tag":123,"props":779,"children":780},{"style":219},[781],{"type":48,"value":698},{"type":43,"tag":123,"props":783,"children":784},{"style":219},[785],{"type":48,"value":222},{"type":43,"tag":123,"props":787,"children":788},{"style":145},[789],{"type":48,"value":648},{"type":43,"tag":123,"props":791,"children":792},{"style":219},[793],{"type":48,"value":232},{"type":43,"tag":123,"props":795,"children":796},{"style":219},[797],{"type":48,"value":798},",",{"type":43,"tag":123,"props":800,"children":801},{"style":219},[802],{"type":48,"value":222},{"type":43,"tag":123,"props":804,"children":805},{"style":771},[806],{"type":48,"value":807},"clip",{"type":43,"tag":123,"props":809,"children":810},{"style":219},[811],{"type":48,"value":232},{"type":43,"tag":123,"props":813,"children":814},{"style":219},[815],{"type":48,"value":698},{"type":43,"tag":123,"props":817,"children":818},{"style":219},[819],{"type":48,"value":820}," [",{"type":43,"tag":123,"props":822,"children":823},{"style":219},[824],{"type":48,"value":232},{"type":43,"tag":123,"props":826,"children":827},{"style":145},[828],{"type":48,"value":829},"4",{"type":43,"tag":123,"props":831,"children":832},{"style":219},[833],{"type":48,"value":232},{"type":43,"tag":123,"props":835,"children":836},{"style":219},[837],{"type":48,"value":798},{"type":43,"tag":123,"props":839,"children":840},{"style":771},[841],{"type":48,"value":842}," 0",{"type":43,"tag":123,"props":844,"children":845},{"style":219},[846],{"type":48,"value":847},"]",{"type":43,"tag":123,"props":849,"children":850},{"style":219},[851],{"type":48,"value":852}," }\n",{"type":43,"tag":123,"props":854,"children":855},{"class":125,"line":26},[856],{"type":43,"tag":123,"props":857,"children":858},{"style":219},[859],{"type":48,"value":860},"  }\n",{"type":43,"tag":123,"props":862,"children":863},{"class":125,"line":192},[864],{"type":43,"tag":123,"props":865,"children":866},{"style":219},[867],{"type":48,"value":868},"}\n",{"type":43,"tag":51,"props":870,"children":871},{},[872],{"type":48,"value":873},"For workflows without that marker, the user must edit the workflow JSON directly.",{"type":43,"tag":66,"props":875,"children":877},{"id":876},"step-by-step-recipe",[878],{"type":48,"value":879},"Step-by-step recipe",{"type":43,"tag":881,"props":882,"children":883},"ol",{},[884,909,919,943,975,1017,1058],{"type":43,"tag":548,"props":885,"children":886},{},[887,892,894,899,901,907],{"type":43,"tag":78,"props":888,"children":889},{},[890],{"type":48,"value":891},"Health probe.",{"type":48,"value":893}," Either call ",{"type":43,"tag":57,"props":895,"children":897},{"className":896},[],[898],{"type":48,"value":464},{"type":48,"value":900}," via MCP or run ",{"type":43,"tag":57,"props":902,"children":904},{"className":903},[],[905],{"type":48,"value":906},"submit_workflow.py --probe",{"type":48,"value":908},". Stop\nand report if ComfyUI is unreachable; do not invent a successful run.",{"type":43,"tag":548,"props":910,"children":911},{},[912,917],{"type":43,"tag":78,"props":913,"children":914},{},[915],{"type":48,"value":916},"Resolve the workflow.",{"type":48,"value":918}," If the user named a file, read it. If they named a workflow by\ndescription (e.g. \"the one with the upscale at the end\"), ask for a path or a saved name.",{"type":43,"tag":548,"props":920,"children":921},{},[922,927,929,934,936,941],{"type":43,"tag":78,"props":923,"children":924},{},[925],{"type":48,"value":926},"Apply prompt override if used.",{"type":48,"value":928}," If ",{"type":43,"tag":57,"props":930,"children":932},{"className":931},[],[933],{"type":48,"value":656},{"type":48,"value":935}," is provided and the workflow contains\n",{"type":43,"tag":57,"props":937,"children":939},{"className":938},[],[940],{"type":48,"value":648},{"type":48,"value":942},", substitute. Otherwise pass the workflow through unchanged.",{"type":43,"tag":548,"props":944,"children":945},{},[946,951,953,958,960,966,968,974],{"type":43,"tag":78,"props":947,"children":948},{},[949],{"type":48,"value":950},"Submit.",{"type":48,"value":952}," POST to ",{"type":43,"tag":57,"props":954,"children":956},{"className":955},[],[957],{"type":48,"value":597},{"type":48,"value":959}," with ",{"type":43,"tag":57,"props":961,"children":963},{"className":962},[],[964],{"type":48,"value":965},"{\"prompt\": \u003Cworkflow>}",{"type":48,"value":967},". Capture ",{"type":43,"tag":57,"props":969,"children":971},{"className":970},[],[972],{"type":48,"value":973},"prompt_id",{"type":48,"value":382},{"type":43,"tag":548,"props":976,"children":977},{},[978,983,985,991,993,999,1001,1007,1009,1015],{"type":43,"tag":78,"props":979,"children":980},{},[981],{"type":48,"value":982},"Poll.",{"type":48,"value":984}," Loop ",{"type":43,"tag":57,"props":986,"children":988},{"className":987},[],[989],{"type":48,"value":990},"GET \u002Fhistory\u002F\u003Cprompt_id>",{"type":48,"value":992}," with a 2-second sleep. Stop on terminal status\n(",{"type":43,"tag":57,"props":994,"children":996},{"className":995},[],[997],{"type":48,"value":998},"success",{"type":48,"value":1000},", ",{"type":43,"tag":57,"props":1002,"children":1004},{"className":1003},[],[1005],{"type":48,"value":1006},"error",{"type":48,"value":1008},", or ",{"type":43,"tag":57,"props":1010,"children":1012},{"className":1011},[],[1013],{"type":48,"value":1014},"cancelled",{"type":48,"value":1016},"). Use a 15-minute cap; long jobs should be split.",{"type":43,"tag":548,"props":1018,"children":1019},{},[1020,1025,1027,1033,1035,1041,1043,1049,1051,1057],{"type":43,"tag":78,"props":1021,"children":1022},{},[1023],{"type":48,"value":1024},"Resolve outputs.",{"type":48,"value":1026}," The ",{"type":43,"tag":57,"props":1028,"children":1030},{"className":1029},[],[1031],{"type":48,"value":1032},"outputs",{"type":48,"value":1034}," object lists the ",{"type":43,"tag":57,"props":1036,"children":1038},{"className":1037},[],[1039],{"type":48,"value":1040},"SaveImage",{"type":48,"value":1042}," \u002F ",{"type":43,"tag":57,"props":1044,"children":1046},{"className":1045},[],[1047],{"type":48,"value":1048},"VHS_VideoCombine",{"type":48,"value":1050}," files\nproduced. For each, fetch ",{"type":43,"tag":57,"props":1052,"children":1054},{"className":1053},[],[1055],{"type":48,"value":1056},"GET \u002Fview?filename=...&subfolder=...&type=output",{"type":48,"value":382},{"type":43,"tag":548,"props":1059,"children":1060},{},[1061,1066],{"type":43,"tag":78,"props":1062,"children":1063},{},[1064],{"type":48,"value":1065},"Report.",{"type":48,"value":1067}," Tell the user the prompt_id, the time taken, the saved file paths, and any\nwarnings (low VRAM, retries, partial outputs).",{"type":43,"tag":66,"props":1069,"children":1071},{"id":1070},"long-jobs-and-vram-safety",[1072],{"type":48,"value":1073},"Long jobs and VRAM safety",{"type":43,"tag":544,"props":1075,"children":1076},{},[1077,1090],{"type":43,"tag":548,"props":1078,"children":1079},{},[1080,1082,1088],{"type":48,"value":1081},"ComfyUI 22B-class models can hold the GPU for hours. The Plugin does not implement a watchdog;\nfor jobs longer than 30 minutes, instruct the user to watch ",{"type":43,"tag":57,"props":1083,"children":1085},{"className":1084},[],[1086],{"type":48,"value":1087},"nvidia-smi",{"type":48,"value":1089}," themselves.",{"type":43,"tag":548,"props":1091,"children":1092},{},[1093,1095,1100],{"type":48,"value":1094},"If a poll returns an error status, capture the full ",{"type":43,"tag":57,"props":1096,"children":1098},{"className":1097},[],[1099],{"type":48,"value":1032},{"type":48,"value":1101}," block and the error message;\nreport both. Do not retry automatically — generation is expensive.",{"type":43,"tag":66,"props":1103,"children":1105},{"id":1104},"requirements",[1106],{"type":48,"value":1107},"Requirements",{"type":43,"tag":544,"props":1109,"children":1110},{},[1111,1123,1128],{"type":43,"tag":548,"props":1112,"children":1113},{},[1114,1116,1121],{"type":48,"value":1115},"ComfyUI running locally (or reachable at ",{"type":43,"tag":57,"props":1117,"children":1119},{"className":1118},[],[1120],{"type":48,"value":364},{"type":48,"value":1122},").",{"type":43,"tag":548,"props":1124,"children":1125},{},[1126],{"type":48,"value":1127},"Python 3.10+ if using the script. The MCP server requires Node 18+.",{"type":43,"tag":548,"props":1129,"children":1130},{},[1131],{"type":48,"value":1132},"No additional accounts, paid services, or network destinations.",{"type":43,"tag":66,"props":1134,"children":1136},{"id":1135},"license",[1137],{"type":48,"value":1138},"License",{"type":43,"tag":51,"props":1140,"children":1141},{},[1142,1144,1151],{"type":48,"value":1143},"Apache-2.0. See ",{"type":43,"tag":1145,"props":1146,"children":1148},"a",{"href":1147},"..\u002F..\u002FLICENSE",[1149],{"type":48,"value":1150},"LICENSE",{"type":48,"value":382},{"type":43,"tag":1153,"props":1154,"children":1155},"style",{},[1156],{"type":48,"value":1157},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":1159,"total":1258},[1160,1176,1195,1206,1217,1230,1239],{"slug":1161,"name":1161,"fn":1162,"description":1163,"org":1164,"tags":1165,"stars":26,"repoUrl":27,"updatedAt":1175},"article2tasks","convert articles into Dida365 tasks","将技术周报（批量）或单篇文章整理为滴答清单待办事项，自动分类到已有清单并打标签，全程通过 MCP 写入，跨平台无需任何本地脚本。当用户提供周报内容、文章链接，或提及「周报」「文章汇总」「添加到滴答」时，使用此技能。",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1166,1169,1172],{"name":1167,"slug":1168,"type":16},"Content Creation","content-creation",{"name":1170,"slug":1171,"type":16},"MCP","mcp",{"name":1173,"slug":1174,"type":16},"Task Management","task-management","2026-08-18T03:49:38.751656",{"slug":1177,"name":1177,"fn":1178,"description":1179,"org":1180,"tags":1181,"stars":26,"repoUrl":27,"updatedAt":1194},"binder-agent-eval","evaluate LLM agent decision quality","当需要在相同的阶段输入上评测 LLM agent 的结构化决策、或对比多个 provider 的决策质量时使用；对应 openbinder evaluate-agent（--provider\u002F--compare\u002F--case）与 openbinder provider doctor。典型触发语：\"用 mock provider 跑一遍 decision case 评测\"\"对比一下几个 provider 在同一批 case 上的表现\"\"先 doctor 一下 minimax 配置通不通\"。同义场景：agent 评测、decision evaluation、visible\u002Fhidden 分层、泄露检查、provider 对比、冻结决策。",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1182,1185,1188,1191],{"name":1183,"slug":1184,"type":16},"Agents","agents",{"name":1186,"slug":1187,"type":16},"Benchmarking","benchmarking",{"name":1189,"slug":1190,"type":16},"Evals","evals",{"name":1192,"slug":1193,"type":16},"LLM","llm","2026-08-27T13:32:30.156635",{"slug":1196,"name":1196,"fn":1197,"description":1198,"org":1199,"tags":1200,"stars":26,"repoUrl":27,"updatedAt":1205},"binder-handoff","export and validate binder task packages","当需要把 binder 设计算力任务打包交给外部平台（Claude Science 或自有服务器）、或校验\u002F导入外部返回的结果包时使用；对应 openbinder handoff export\u002Fvalidate\u002Fimport。典型触发语：\"把这个 target 打包成 handoff 任务包\"\"校验一下对方返回的 result package\"\"把外部算回来的结果导入进来\"。同义场景：external handoff、任务包导出、结果包校验、回传包导入、RUNBOOK。",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1201,1202],{"name":14,"slug":15,"type":16},{"name":1203,"slug":1204,"type":16},"Data Engineering","data-engineering","2026-08-27T13:32:32.957864",{"slug":1207,"name":1207,"fn":1208,"description":1209,"org":1210,"tags":1211,"stars":26,"repoUrl":27,"updatedAt":1216},"binder-protocol","compile and validate binder design protocols","当需要把 binder 设计协议草稿编译成结构化 protocol.yaml、校验协议、或按阶段切出 stage slice 时使用；对应 openbinder protocol validate\u002Fcompile\u002Fshow 三个子命令。典型触发语：\"把这份 protocol 草稿编译一下\"\"校验这个 protocol.yaml\"\"把 cofold_scoring 阶段的切片拿出来\"。同义场景：协议编译、protocol compiler、十阶段、stage slice、阶段上下文、protocol validate。",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1212,1213],{"name":14,"slug":15,"type":16},{"name":1214,"slug":1215,"type":16},"YAML","yaml","2026-08-27T13:32:33.760978",{"slug":1218,"name":1218,"fn":1219,"description":1220,"org":1221,"tags":1222,"stars":26,"repoUrl":27,"updatedAt":1229},"binder-ranking-audit","audit binder campaign ranking results","当需要重算并审计 binder campaign 的候选排序、核对 recorded 与 recomputed 是否一致时使用；对应 openbinder audit-ranking（--fixture\u002F--source）。典型触发语：\"审计一下这个 campaign 的排序\"\"recorded 和 recomputed 对得上吗\"\"重算 top-N 命中率和 Spearman\"。同义场景：ranking audit、排序审计、ensemble 重算、hit rate、缺失数据处理、missing data 报告。",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1223,1226],{"name":1224,"slug":1225,"type":16},"Data Analysis","data-analysis",{"name":1227,"slug":1228,"type":16},"QA","qa","2026-08-27T13:32:34.155444",{"slug":1231,"name":1231,"fn":1232,"description":1233,"org":1234,"tags":1235,"stars":26,"repoUrl":27,"updatedAt":1238},"binder-replay","replay binder design campaigns","当需要回放已记录的 binder 设计 campaign、重现每一步\"当时知道什么、决定了什么\"时使用；对应 openbinder replay（--fixture\u002F--events\u002F--source）。典型触发语：\"帮我回放一下 IL-7Ra 的 binder campaign\"\"回放那个失败的 campaign\"\"看看当时每一步都知道了什么\"。同义场景：campaign replay、事件流回放、replay report、gap 分析、时间线重建。",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1236,1237],{"name":14,"slug":15,"type":16},{"name":1224,"slug":1225,"type":16},"2026-08-27T13:32:33.346398",{"slug":1240,"name":1240,"fn":1241,"description":1242,"org":1243,"tags":1244,"stars":26,"repoUrl":27,"updatedAt":1257},"binder-report","generate final reports from agent artifacts","当需要把 output\u002F 下已产生的 replay、agent 评测、ranking 审计产物汇总成最终报告束时使用；收集既有 artifact、按六类证据分级标注、生成 limitations 并提交 stage-gate 审批。典型触发语：\"把这些产物汇总成最终报告\"\"出一份 binder 最终报告和 limitations\"\"把 replay\u002F评测\u002F审计结果打包成报告束\"。同义场景：最终报告、报告束、evidence grading、limitations、claim check、收尾报告。",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1245,1248,1251,1254],{"name":1246,"slug":1247,"type":16},"Documentation","documentation",{"name":1249,"slug":1250,"type":16},"Operations","operations",{"name":1252,"slug":1253,"type":16},"Reporting","reporting",{"name":1255,"slug":1256,"type":16},"Summarization","summarization","2026-08-27T13:32:26.101404",93,{"items":1260,"total":1455},[1261,1285,1297,1316,1331,1351,1369,1387,1400,1416,1435,1445],{"slug":1262,"name":1262,"fn":1263,"description":1264,"org":1265,"tags":1266,"stars":1282,"repoUrl":1283,"updatedAt":1284},"android-native-dev","develop Android native applications","Android native application development and UI design guide. Covers Material Design 3, Kotlin\u002FCompose development, project configuration, accessibility, and build troubleshooting. Read this before Android native application development.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1267,1270,1273,1276,1279],{"name":1268,"slug":1269,"type":16},"Accessibility","accessibility",{"name":1271,"slug":1272,"type":16},"Android","android",{"name":1274,"slug":1275,"type":16},"Kotlin","kotlin",{"name":1277,"slug":1278,"type":16},"Mobile","mobile",{"name":1280,"slug":1281,"type":16},"UI Components","ui-components",13030,"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002Fskills","2026-07-13T06:16:54.247834",{"slug":1286,"name":1286,"fn":1287,"description":1288,"org":1289,"tags":1290,"stars":1282,"repoUrl":1283,"updatedAt":1296},"buddy-sings","generate singing performances for AI companions","Use when user wants their Claude Code pet (\u002Fbuddy) to sing a song. Triggers on any request that combines the concept of their Claude Code buddy, pet, or companion with singing or music. Supports multilingual triggers — match equivalent phrases in any language.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1291,1292,1295],{"name":1183,"slug":1184,"type":16},{"name":1293,"slug":1294,"type":16},"Audio","audio",{"name":18,"slug":19,"type":16},"2026-07-13T06:16:35.130644",{"slug":1298,"name":1298,"fn":1299,"description":1300,"org":1301,"tags":1302,"stars":1282,"repoUrl":1283,"updatedAt":1315},"color-font-skill","select color palettes and font pairings","Choose presentation-ready color palettes and font pairings for PPT\u002Fdesign tasks. Use when users ask for visual theme choices, brand-safe palettes, or font recommendations. Triggers include: 配色, 色板, 字体, color palette, font, PPT配色, 字体搭配.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1303,1306,1309,1312],{"name":1304,"slug":1305,"type":16},"Design","design",{"name":1307,"slug":1308,"type":16},"Presentations","presentations",{"name":1310,"slug":1311,"type":16},"Themes","themes",{"name":1313,"slug":1314,"type":16},"Typography","typography","2026-07-13T06:17:02.785587",{"slug":1317,"name":1317,"fn":1318,"description":1319,"org":1320,"tags":1321,"stars":1282,"repoUrl":1283,"updatedAt":1330},"design-style-skill","select visual design systems for presentations","Select a consistent visual design system for PPT slides using radius\u002Fspacing style recipes. Use when users ask for overall style direction or component styling consistency. Includes Sharp\u002FSoft\u002FRounded\u002FPill recipes, component mappings, typography\u002Fspacing rules, and mixing guidance. Triggers: 风格, style, radius, spacing, 圆角, 间距, PPT风格, 视觉风格, design style, component style.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1322,1323,1326,1329],{"name":1304,"slug":1305,"type":16},{"name":1324,"slug":1325,"type":16},"Design System","design-system",{"name":1327,"slug":1328,"type":16},"PowerPoint","powerpoint",{"name":1307,"slug":1308,"type":16},"2026-07-13T06:17:10.398389",{"slug":1332,"name":1332,"fn":1333,"description":1334,"org":1335,"tags":1336,"stars":1282,"repoUrl":1283,"updatedAt":1350},"flutter-dev","build cross-platform apps with Flutter","Flutter cross-platform development guide covering widget patterns, Riverpod\u002FBloc state management, GoRouter navigation, performance optimization, and platform-specific implementations. Includes const optimization, responsive layouts, testing strategies, and DevTools profiling.\nUse when: building Flutter apps, implementing state management (Riverpod\u002FBloc), setting up GoRouter navigation, creating custom widgets, optimizing performance, writing widget tests, cross-platform development.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1337,1340,1343,1344,1347],{"name":1338,"slug":1339,"type":16},"Dart","dart",{"name":1341,"slug":1342,"type":16},"Flutter","flutter",{"name":1277,"slug":1278,"type":16},{"name":1345,"slug":1346,"type":16},"Performance","performance",{"name":1348,"slug":1349,"type":16},"State Management","state-management","2026-07-13T06:16:36.626679",{"slug":1352,"name":1352,"fn":1353,"description":1354,"org":1355,"tags":1356,"stars":1282,"repoUrl":1283,"updatedAt":1368},"frontend-dev","build visually striking frontend web pages","Full-stack frontend development combining premium UI design, cinematic animations,\nAI-generated media assets, persuasive copywriting, and visual art. Builds complete,\nvisually striking web pages with real media, advanced motion, and compelling copy.\nUse when: building landing pages, marketing sites, product pages, dashboards,\ngenerating media assets (image\u002Fvideo\u002Faudio\u002Fmusic), writing conversion copy,\ncreating generative art, or implementing cinematic scroll animations.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1357,1360,1361,1362,1365],{"name":1358,"slug":1359,"type":16},"Animation","animation",{"name":18,"slug":19,"type":16},{"name":1304,"slug":1305,"type":16},{"name":1363,"slug":1364,"type":16},"Frontend","frontend",{"name":1366,"slug":1367,"type":16},"Web Development","web-development","2026-07-13T06:16:39.108827",{"slug":1370,"name":1370,"fn":1371,"description":1372,"org":1373,"tags":1374,"stars":1282,"repoUrl":1283,"updatedAt":1386},"fullstack-dev","build full-stack web applications","Full-stack backend architecture and frontend-backend integration guide.\nTRIGGER when: building a full-stack app, creating REST API with frontend, scaffolding backend service,\nbuilding todo app, building CRUD app, building real-time app, building chat app,\nExpress + React, Next.js API, Node.js backend, Python backend, Go backend,\ndesigning service layers, implementing error handling, managing config\u002Fauth,\nsetting up API clients, implementing auth flows, handling file uploads,\nadding real-time features (SSE\u002FWebSocket), hardening for production.\nDO NOT TRIGGER when: pure frontend UI work, pure CSS\u002Fstyling, database schema only.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1375,1378,1379,1382,1385],{"name":1376,"slug":1377,"type":16},"Backend","backend",{"name":1363,"slug":1364,"type":16},{"name":1380,"slug":1381,"type":16},"Full-stack","full-stack",{"name":1383,"slug":1384,"type":16},"REST API","rest-api",{"name":1366,"slug":1367,"type":16},"2026-07-13T06:16:43.219005",{"slug":1388,"name":1388,"fn":1389,"description":1390,"org":1391,"tags":1392,"stars":1282,"repoUrl":1283,"updatedAt":1399},"gif-sticker-maker","create animated GIF stickers from photos","Convert photos (people, pets, objects, logos) into 4 animated GIF stickers with captions.\nUse when: user wants to create cartoon stickers, GIF expressions, emoji packs, animated avatars,\nor convert photos to Funko Pop \u002F Pop Mart blind box style animations.\nTriggers: sticker, GIF, cartoon, emoji, expression pack, avatar animation.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1393,1394,1395,1396],{"name":1358,"slug":1359,"type":16},{"name":18,"slug":19,"type":16},{"name":21,"slug":22,"type":16},{"name":1397,"slug":1398,"type":16},"Media","media","2026-07-13T06:16:51.74461",{"slug":1401,"name":1401,"fn":1402,"description":1403,"org":1404,"tags":1405,"stars":1282,"repoUrl":1283,"updatedAt":1415},"ios-application-dev","develop iOS applications with SwiftUI and UIKit","iOS application development guide covering UIKit, SnapKit, and SwiftUI. Includes touch targets, safe areas, navigation patterns, Dynamic Type, Dark Mode, accessibility, collection views, common UI components, and SwiftUI design guidelines. For detailed references on specific topics, see the reference files.\nUse when: developing iOS apps, implementing UI, reviewing iOS code, working with UIKit\u002FSnapKit\u002FSwiftUI layouts, building iPhone interfaces, Swift mobile development, Apple HIG compliance, iOS accessibility implementation.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1406,1407,1410,1411,1414],{"name":1268,"slug":1269,"type":16},{"name":1408,"slug":1409,"type":16},"iOS","ios",{"name":1277,"slug":1278,"type":16},{"name":1412,"slug":1413,"type":16},"SwiftUI","swiftui",{"name":1280,"slug":1281,"type":16},"2026-07-13T06:16:55.686092",{"slug":1417,"name":1417,"fn":1418,"description":1419,"org":1420,"tags":1421,"stars":1282,"repoUrl":1283,"updatedAt":1434},"minimax-docx","create and edit DOCX documents","Professional DOCX document creation, editing, and formatting using OpenXML SDK (.NET). Three pipelines: (A) create new documents from scratch, (B) fill\u002Fedit content in existing documents, (C) apply template formatting with XSD validation gate-check. MUST use this skill whenever the user wants to produce, modify, or format a Word document — including when they say \"write a report\", \"draft a proposal\", \"make a contract\", \"fill in this form\", \"reformat to match this template\", or any task whose final output is a .docx file. Even if the user doesn't mention \"docx\" explicitly, if the task implies a printable\u002Fformal document, use this skill.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1422,1425,1428,1431],{"name":1423,"slug":1424,"type":16},"Documents","documents",{"name":1426,"slug":1427,"type":16},"DOCX","docx",{"name":1429,"slug":1430,"type":16},"Office","office",{"name":1432,"slug":1433,"type":16},"Templates","templates","2026-07-13T06:16:40.461868",{"slug":1436,"name":1436,"fn":1437,"description":1438,"org":1439,"tags":1440,"stars":1282,"repoUrl":1283,"updatedAt":1444},"minimax-music-gen","generate music and audio tracks","Use when user wants to generate music, songs, or audio tracks. Triggers on any request involving music creation, song writing, lyrics generation, audio production, or covers. Also triggers when user provides lyrics and wants them turned into a song, or describes a mood\u002Fscene and wants background music. Supports multilingual triggers — match equivalent phrases in any language. Do NOT use for music playback of existing files, music theory questions, or music recommendation without generation.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1441,1442,1443],{"name":1293,"slug":1294,"type":16},{"name":18,"slug":19,"type":16},{"name":1397,"slug":1398,"type":16},"2026-07-13T06:16:50.381758",{"slug":1446,"name":1446,"fn":1447,"description":1448,"org":1449,"tags":1450,"stars":1282,"repoUrl":1283,"updatedAt":1454},"minimax-music-playlist","generate personalized music playlists","Generate personalized music playlists by analyzing the user's music taste and generation feedback history. Triggers on any request involving playlist generation, music taste profiling, or personalized music recommendations. Supports multilingual triggers — match equivalent phrases in any language.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1451,1452,1453],{"name":1293,"slug":1294,"type":16},{"name":18,"slug":19,"type":16},{"name":1397,"slug":1398,"type":16},"2026-07-13T06:16:57.002997",141]