Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub · Developer Tools
Comfyui Workflow
Universal ComfyUI workflow executor with 33+ workflow templates. Self-describing — use --inspect on ANY workflow to discover inputs and outputs automatically...
skill openclawclawhub Free
Universal ComfyUI workflow executor with 33+ workflow templates. Self-describing — use --inspect on ANY workflow to discover inputs and outputs automatically...
⬇ 0 downloads ★ 0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- GENERATION_RULES.md, MODELS_INVENTORY.md, PRACTICAL_GUIDE.md, README.md, SKILL.md, WORKFLOWS_SUMMARY.md
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- 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.
New install
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.
Upgrade existing
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.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.1.0
Provenance
- Publisher
- yiqiliu2
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
ComfyUI Workflows — Agent Usage Guide
⚠️ 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.
Requirements
Before using this skill, ensure your environment meets these requirements: RequirementDetailsPython3.10 or higherpip packageswebsocket-client, requestsComfyUI serverMust be running before executing workflowsTokenRequired if ComfyUI has authentication enabled Install Python dependencies: pip install websocket-client requests
Configuration Options
VariableDescriptionDefaultCOMFY_HOSTComfyUI server address127.0.0.1:8188COMFY_WORKFLOW_DIRSAdditional workflow directories(none)
Credentials
CredentialRequiredSourceComfyUI TokenOnly if auth enabledComfyUI settings page
Personal Configuration Required
Before using this skill, ensure these items are configured for your environment: ItemDescriptionWhere 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)
1. Start ComfyUI
Start your ComfyUI server manually before executing any workflows. The skill expects ComfyUI to be running at the configured host.
2. Configure Connection
Create scripts/config.json: { "comfy_host": "127.0.0.1:8188", "workflow_dirs": [] } Or set environment variables: export COMFY_HOST="127.0.0.1:8188"
3. Install Dependencies
pip install websocket-client requests
4. Add Your Workflows
Place workflow JSON files in workflows/ directory, organized by category: workflows/ ├── Image-Text/ │ ├── workflow1.json │ └── workflow2.json ├── Image-Edit/ │ └── ... └── Video/ └── ...
Shell Variables (use in all commands)
VENV=python3 # or path to your venv SCRIPT=/path/to/comfyui-workflow-skill/scripts/comfy_run.py
Step 0 — Ensure ComfyUI Is Running
Start ComfyUI manually. Verify it's accessible at http://127.0.0.1:8188.
Step 1 — List Available Workflows
$VENV $SCRIPT --list
Step 2 — Inspect the Workflow
$VENV $SCRIPT -w "workflow_name" --inspect
Step 3 — Prepare Inputs
--prompt "your prompt" # Text prompts --image /path/to/image.jpg # Image inputs --audio /path/to/audio.wav # Audio inputs --video /path/to/video.mp4 # Video inputs --width 1024 --height 1024 # Resolution --steps 50 --cfg 4.0 --seed 42 # Sampler settings --override '{"node_id": {"key": value}}' # Advanced overrides
Step 4 — Execute
$VENV $SCRIPT -w "workflow_name" --prompt "..." -o /tmp
Step 5 — Collect Outputs
Outputs are saved to the -o directory with auto-generated prefixes.
CLI Reference
Usage: comfy_run.py [-w WORKFLOW] [options] Modes: --list List all available workflows --inspect Human-readable input/output inspection --inspect-json Machine-readable JSON inspection --dry-run Print API JSON without executing --queue Submit to queue and return immediately --status [IDs...] Check queue state Input customization: --prompt, -p TEXT Positive prompt --negative, -n TEXT Negative prompt --image, -i PATH [...] Input image(s) --audio, -a PATH [...] Input audio file(s) --video, -v PATH [...] Input video file(s) Generation settings: --width, -W INT Output width --height, -H INT Output height --steps INT Sampling steps --cfg FLOAT CFG scale --seed INT Random seed Advanced: --override JSON Node input overrides --config PATH YAML/JSON config file --server HOST:PORT ComfyUI server --output-dir, -o PATH Output directory --output-prefix TEXT Output filename prefix --no-ensure Skip auto-starting ComfyUI --no-validate Skip input validation
Troubleshooting
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
Knowledge Cache Pattern
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: ⚠️ 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.
Initial Setup (First Time)
When the user first provides their own workflow files: Clean the example content — Remove the sanitized example entries from both files Populate with user's data — Run --inspect on each workflow, document findings in WORKFLOWS_SUMMARY.md Inventory models — Scan user's model directories, update MODELS_INVENTORY.md with their actual models
Ongoing Maintenance
After using a new workflow → Add its documentation to WORKFLOWS_SUMMARY.md After downloading models → Update MODELS_INVENTORY.md status When learning model-specific quirks → Document tips/tricks in the relevant section
Session Workflow
1. Read MODELS_INVENTORY.md → know available models 2. Read WORKFLOWS_SUMMARY.md → know workflow capabilities 3. Select appropriate workflow without re-inspecting 4. If new workflow discovered → document it for future sessions This pattern lets the agent skip repeated discovery and work efficiently with cached knowledge.
Reference Documents
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
Category context
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
6 Docs
- SKILL.md
- GENERATION_RULES.md
- MODELS_INVENTORY.md
- PRACTICAL_GUIDE.md
- README.md
- WORKFLOWS_SUMMARY.md