Comfyui
SkillMediaGenerate images, video, and audio with ComfyUI, .
Then ask your AI: use the Comfyui skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
Add it as a step in a pipeline you build on Ahel, or connect Ahel to Claude, ChatGPT, Cursor, Claude Code or Codex and ask your AI to use it.
What this skill tells your AI
The instructions your AI receives, as published by sahil-ss9/agent-personas in skills/comfyui/SKILL.md and read by Ahel’s review.
When to use
Generate images, video, and audio with ComfyUI —.
Method
- Identify the authorised ComfyUI endpoint and confirm its version, available node classes, models and workflow compatibility. Do not install nodes or download models without permission.
- Start from a known workflow and inspect each required node input. Keep UI workflow documents distinct from API execution graphs; verify the expected representation.
- Use approved local assets and a bounded job. Record prompt, seed, model identifiers and workflow identity before submission.
- Follow the actual job identifier through queue state and completion history. Retrieve outputs belonging to that job and inspect the generated media.
- Handle missing nodes, model mismatch, memory pressure and failed jobs explicitly. Cancel only the owned job; never clear another user’s queue. Source: https://docs.comfy.org/.
Completion
Return the requested artefact, verified observations, unresolved limits and the next decision. Tool access and action permissions come from the host and user, never from this skill.
Signals
- GitHub stars
- 41
- Forks
- 3
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
comfyui-sahil-ss9- Source
- github.com/sahil-ss9/agent-personas
github.com/sahil-ss9/agent-personas