{ "schemaVersion": "1.0", "item": { "slug": "comfyui-workflow", "name": "Comfyui Workflow", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/yiqiliu2/comfyui-workflow", "canonicalUrl": "https://clawhub.ai/yiqiliu2/comfyui-workflow", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/comfyui-workflow", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=comfyui-workflow", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "GENERATION_RULES.md", "MODELS_INVENTORY.md", "PRACTICAL_GUIDE.md", "README.md", "SKILL.md", "WORKFLOWS_SUMMARY.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/comfyui-workflow" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/comfyui-workflow", "agentPageUrl": "https://openagent3.xyz/skills/comfyui-workflow/agent", "manifestUrl": "https://openagent3.xyz/skills/comfyui-workflow/agent.json", "briefUrl": "https://openagent3.xyz/skills/comfyui-workflow/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "ComfyUI Workflows — Agent Usage Guide", "body": "⚠️ READ-ONLY WARNING: The scripts in this skill (comfy_run.py, comfy_api.py) are\nproduction-validated and must not be modified. They handle 33+ workflow JSONs with complex LiteGraph→API\nconversion, subgraph expansion, bypass resolution, and multi-format output downloading. Any modification risks\nbreaking all workflows. Only read and use the scripts — never edit them." }, { "title": "Requirements", "body": "Before using this skill, ensure your environment meets these requirements:\n\nRequirementDetailsPython3.10 or higherpip packageswebsocket-client, requestsComfyUI serverMust be running before executing workflowsTokenRequired if ComfyUI has authentication enabled\n\nInstall Python dependencies:\n\npip install websocket-client requests" }, { "title": "Configuration Options", "body": "VariableDescriptionDefaultCOMFY_HOSTComfyUI server address127.0.0.1:8188COMFY_WORKFLOW_DIRSAdditional workflow directories(none)" }, { "title": "Credentials", "body": "CredentialRequiredSourceComfyUI TokenOnly if auth enabledComfyUI settings page" }, { "title": "Personal Configuration Required", "body": "Before using this skill, ensure these items are configured for your environment:\n\nItemDescriptionWhere to Configurecomfy_hostYour ComfyUI server addressscripts/config.json or COMFY_HOST envComfyUI serverMust be running before executing workflowsStart manuallyModel pathsYour local model directoriesMODELS_INVENTORY.md (for reference)TokenComfyUI authentication tokenGet from ComfyUI settingsWorkflow filesYour own workflow JSON filesworkflows/ directory (see note below)" }, { "title": "1. Start ComfyUI", "body": "Start your ComfyUI server manually before executing any workflows. The skill expects ComfyUI to be running at the configured host." }, { "title": "2. Configure Connection", "body": "Create scripts/config.json:\n\n{\n \"comfy_host\": \"127.0.0.1:8188\",\n \"workflow_dirs\": []\n}\n\nOr set environment variables:\n\nexport COMFY_HOST=\"127.0.0.1:8188\"" }, { "title": "3. Install Dependencies", "body": "pip install websocket-client requests" }, { "title": "4. Add Your Workflows", "body": "Place workflow JSON files in workflows/ directory, organized by category:\n\nworkflows/\n├── Image-Text/\n│ ├── workflow1.json\n│ └── workflow2.json\n├── Image-Edit/\n│ └── ...\n└── Video/\n └── ..." }, { "title": "Shell Variables (use in all commands)", "body": "VENV=python3 # or path to your venv\nSCRIPT=/path/to/comfyui-workflow-skill/scripts/comfy_run.py" }, { "title": "Step 0 — Ensure ComfyUI Is Running", "body": "Start ComfyUI manually. Verify it's accessible at http://127.0.0.1:8188." }, { "title": "Step 1 — List Available Workflows", "body": "$VENV $SCRIPT --list" }, { "title": "Step 2 — Inspect the Workflow", "body": "$VENV $SCRIPT -w \"workflow_name\" --inspect" }, { "title": "Step 3 — Prepare Inputs", "body": "--prompt \"your prompt\" # Text prompts\n--image /path/to/image.jpg # Image inputs\n--audio /path/to/audio.wav # Audio inputs\n--video /path/to/video.mp4 # Video inputs\n--width 1024 --height 1024 # Resolution\n--steps 50 --cfg 4.0 --seed 42 # Sampler settings\n--override '{\"node_id\": {\"key\": value}}' # Advanced overrides" }, { "title": "Step 4 — Execute", "body": "$VENV $SCRIPT -w \"workflow_name\" --prompt \"...\" -o /tmp" }, { "title": "Step 5 — Collect Outputs", "body": "Outputs are saved to the -o directory with auto-generated prefixes." }, { "title": "CLI Reference", "body": "Usage: comfy_run.py [-w WORKFLOW] [options]\n\nModes:\n --list List all available workflows\n --inspect Human-readable input/output inspection\n --inspect-json Machine-readable JSON inspection\n --dry-run Print API JSON without executing\n --queue Submit to queue and return immediately\n --status [IDs...] Check queue state\n\nInput customization:\n --prompt, -p TEXT Positive prompt\n --negative, -n TEXT Negative prompt\n --image, -i PATH [...] Input image(s)\n --audio, -a PATH [...] Input audio file(s)\n --video, -v PATH [...] Input video file(s)\n\nGeneration settings:\n --width, -W INT Output width\n --height, -H INT Output height\n --steps INT Sampling steps\n --cfg FLOAT CFG scale\n --seed INT Random seed\n\nAdvanced:\n --override JSON Node input overrides\n --config PATH YAML/JSON config file\n --server HOST:PORT ComfyUI server\n --output-dir, -o PATH Output directory\n --output-prefix TEXT Output filename prefix\n --no-ensure Skip auto-starting ComfyUI\n --no-validate Skip input validation" }, { "title": "Troubleshooting", "body": "ProblemFixWorkflow not foundUse --list to see available workflowsNO OUTPUTS generatedRun --inspect to check required inputsCannot reach ComfyUIEnsure ComfyUI is running at configured hostImage file not foundUse absolute paths, verify with ls -laGPU out of memoryReduce resolution or steps" }, { "title": "Knowledge Cache Pattern", "body": "MODELS_INVENTORY.md and WORKFLOWS_SUMMARY.md serve as the agent's persistent knowledge base for the user's actual ComfyUI setup. Use them to cache learned information across sessions:\n\n⚠️ DO NOT REFERENCE THE EXAMPLE CONTENT: The default content in these files describes sanitized example workflows that will NOT work. Agents MUST update them with the user's actual data before relying on them. Using outdated example data will cause workflow failures." }, { "title": "Initial Setup (First Time)", "body": "When the user first provides their own workflow files:\n\nClean the example content — Remove the sanitized example entries from both files\nPopulate with user's data — Run --inspect on each workflow, document findings in WORKFLOWS_SUMMARY.md\nInventory models — Scan user's model directories, update MODELS_INVENTORY.md with their actual models" }, { "title": "Ongoing Maintenance", "body": "After using a new workflow → Add its documentation to WORKFLOWS_SUMMARY.md\nAfter downloading models → Update MODELS_INVENTORY.md status\nWhen learning model-specific quirks → Document tips/tricks in the relevant section" }, { "title": "Session Workflow", "body": "1. Read MODELS_INVENTORY.md → know available models\n2. Read WORKFLOWS_SUMMARY.md → know workflow capabilities\n3. Select appropriate workflow without re-inspecting\n4. If new workflow discovered → document it for future sessions\n\nThis pattern lets the agent skip repeated discovery and work efficiently with cached knowledge." }, { "title": "Reference Documents", "body": "DocumentPurposeMODELS_INVENTORY.mdKnowledge cache — user's installed models, status, pathsWORKFLOWS_SUMMARY.mdKnowledge cache — workflow capabilities, settings, tipsreferences/prompting-guide.mdPrompt anatomy, model-specific strategiesreferences/maintenance.mdCode structure, debuggingreferences/architecture.mdDesign principles" } ], "body": "ComfyUI Workflows — Agent Usage Guide\n\n⚠️ READ-ONLY WARNING: The scripts in this skill (comfy_run.py, comfy_api.py) are production-validated and must not be modified. They handle 33+ workflow JSONs with complex LiteGraph→API conversion, subgraph expansion, bypass resolution, and multi-format output downloading. Any modification risks breaking all workflows. Only read and use the scripts — never edit them.\n\nRequirements\n\nBefore using this skill, ensure your environment meets these requirements:\n\nRequirement\tDetails\nPython\t3.10 or higher\npip packages\twebsocket-client, requests\nComfyUI server\tMust be running before executing workflows\nToken\tRequired if ComfyUI has authentication enabled\n\nInstall Python dependencies:\n\npip install websocket-client requests\n\nConfiguration Options\nVariable\tDescription\tDefault\nCOMFY_HOST\tComfyUI server address\t127.0.0.1:8188\nCOMFY_WORKFLOW_DIRS\tAdditional workflow directories\t(none)\nCredentials\nCredential\tRequired\tSource\nComfyUI Token\tOnly if auth enabled\tComfyUI settings page\nPersonal Configuration Required\n\nBefore using this skill, ensure these items are configured for your environment:\n\nItem\tDescription\tWhere to Configure\ncomfy_host\tYour ComfyUI server address\tscripts/config.json or COMFY_HOST env\nComfyUI server\tMust be running before executing workflows\tStart manually\nModel paths\tYour local model directories\tMODELS_INVENTORY.md (for reference)\nToken\tComfyUI authentication token\tGet from ComfyUI settings\nWorkflow files\tYour own workflow JSON files\tworkflows/ directory (see note below)\nQuick Setup\n1. Start ComfyUI\n\nStart your ComfyUI server manually before executing any workflows. The skill expects ComfyUI to be running at the configured host.\n\n2. Configure Connection\n\nCreate scripts/config.json:\n\n{\n \"comfy_host\": \"127.0.0.1:8188\",\n \"workflow_dirs\": []\n}\n\n\nOr set environment variables:\n\nexport COMFY_HOST=\"127.0.0.1:8188\"\n\n3. Install Dependencies\npip install websocket-client requests\n\n4. Add Your Workflows\n\nPlace workflow JSON files in workflows/ directory, organized by category:\n\nworkflows/\n├── Image-Text/\n│ ├── workflow1.json\n│ └── workflow2.json\n├── Image-Edit/\n│ └── ...\n└── Video/\n └── ...\n\nShell Variables (use in all commands)\nVENV=python3 # or path to your venv\nSCRIPT=/path/to/comfyui-workflow-skill/scripts/comfy_run.py\n\nEnd-to-End Workflow (Steps 0–5)\nStep 0 — Ensure ComfyUI Is Running\n\nStart ComfyUI manually. Verify it's accessible at http://127.0.0.1:8188.\n\nStep 1 — List Available Workflows\n$VENV $SCRIPT --list\n\nStep 2 — Inspect the Workflow\n$VENV $SCRIPT -w \"workflow_name\" --inspect\n\nStep 3 — Prepare Inputs\n--prompt \"your prompt\" # Text prompts\n--image /path/to/image.jpg # Image inputs\n--audio /path/to/audio.wav # Audio inputs\n--video /path/to/video.mp4 # Video inputs\n--width 1024 --height 1024 # Resolution\n--steps 50 --cfg 4.0 --seed 42 # Sampler settings\n--override '{\"node_id\": {\"key\": value}}' # Advanced overrides\n\nStep 4 — Execute\n$VENV $SCRIPT -w \"workflow_name\" --prompt \"...\" -o /tmp\n\nStep 5 — Collect Outputs\n\nOutputs are saved to the -o directory with auto-generated prefixes.\n\nCLI Reference\nUsage: comfy_run.py [-w WORKFLOW] [options]\n\nModes:\n --list List all available workflows\n --inspect Human-readable input/output inspection\n --inspect-json Machine-readable JSON inspection\n --dry-run Print API JSON without executing\n --queue Submit to queue and return immediately\n --status [IDs...] Check queue state\n\nInput customization:\n --prompt, -p TEXT Positive prompt\n --negative, -n TEXT Negative prompt\n --image, -i PATH [...] Input image(s)\n --audio, -a PATH [...] Input audio file(s)\n --video, -v PATH [...] Input video file(s)\n\nGeneration settings:\n --width, -W INT Output width\n --height, -H INT Output height\n --steps INT Sampling steps\n --cfg FLOAT CFG scale\n --seed INT Random seed\n\nAdvanced:\n --override JSON Node input overrides\n --config PATH YAML/JSON config file\n --server HOST:PORT ComfyUI server\n --output-dir, -o PATH Output directory\n --output-prefix TEXT Output filename prefix\n --no-ensure Skip auto-starting ComfyUI\n --no-validate Skip input validation\n\nTroubleshooting\nProblem\tFix\nWorkflow not found\tUse --list to see available workflows\nNO OUTPUTS generated\tRun --inspect to check required inputs\nCannot reach ComfyUI\tEnsure ComfyUI is running at configured host\nImage file not found\tUse absolute paths, verify with ls -la\nGPU out of memory\tReduce resolution or steps\nKnowledge Cache Pattern\n\nMODELS_INVENTORY.md and WORKFLOWS_SUMMARY.md serve as the agent's persistent knowledge base for the user's actual ComfyUI setup. Use them to cache learned information across sessions:\n\n⚠️ DO NOT REFERENCE THE EXAMPLE CONTENT: The default content in these files describes sanitized example workflows that will NOT work. Agents MUST update them with the user's actual data before relying on them. Using outdated example data will cause workflow failures.\n\nInitial Setup (First Time)\n\nWhen the user first provides their own workflow files:\n\nClean the example content — Remove the sanitized example entries from both files\nPopulate with user's data — Run --inspect on each workflow, document findings in WORKFLOWS_SUMMARY.md\nInventory models — Scan user's model directories, update MODELS_INVENTORY.md with their actual models\nOngoing Maintenance\nAfter using a new workflow → Add its documentation to WORKFLOWS_SUMMARY.md\nAfter downloading models → Update MODELS_INVENTORY.md status\nWhen learning model-specific quirks → Document tips/tricks in the relevant section\nSession Workflow\n1. Read MODELS_INVENTORY.md → know available models\n2. Read WORKFLOWS_SUMMARY.md → know workflow capabilities\n3. Select appropriate workflow without re-inspecting\n4. If new workflow discovered → document it for future sessions\n\n\nThis pattern lets the agent skip repeated discovery and work efficiently with cached knowledge.\n\nReference Documents\nDocument\tPurpose\nMODELS_INVENTORY.md\tKnowledge cache — user's installed models, status, paths\nWORKFLOWS_SUMMARY.md\tKnowledge cache — workflow capabilities, settings, tips\nreferences/prompting-guide.md\tPrompt anatomy, model-specific strategies\nreferences/maintenance.md\tCode structure, debugging\nreferences/architecture.md\tDesign principles" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/yiqiliu2/comfyui-workflow", "publisherUrl": "https://clawhub.ai/yiqiliu2/comfyui-workflow", "owner": "yiqiliu2", "version": "1.1.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/comfyui-workflow", "downloadUrl": "https://openagent3.xyz/downloads/comfyui-workflow", "agentUrl": "https://openagent3.xyz/skills/comfyui-workflow/agent", "manifestUrl": "https://openagent3.xyz/skills/comfyui-workflow/agent.json", "briefUrl": "https://openagent3.xyz/skills/comfyui-workflow/agent.md" } }