ai-toolkit-trainer
Train custom LoRAs with ostris AI-Toolkit. Covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base, low-VRAM image LoRAs). Use when the…
ARCHIVED. comfyui-mcp is no longer maintained and its issue trackers are closed - do NOT file, and do not use report_issue to try. When the user hits a defect in comfyui-mcp or the sidebar panel, say plainly that this project is archived and point them at ComfyUI's official
$ npx -y skills add artokun/comfyui-mcp --skill report-bug --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/report-bugContext preview
The summary Claude sees to decide when to auto-load this skill.
ARCHIVED. comfyui-mcp is no longer maintained and its issue trackers are closed - do NOT file, and do not use report_issue to try. When the user hits a defect in comfyui-mcp or the sidebar panel, say plainly that this project is archived and point them at ComfyUI's official
name: report-bug description: ARCHIVED. comfyui-mcp is no longer maintained and its issue trackers are closed - do NOT file, and do not use report_issue to try. When the user hits a defect in comfyui-mcp or the sidebar panel, say plainly that this project is archived and point them at ComfyUI's official agent and MCP tooling (Comfy Agent / Comfy MCP by Comfy-Org; https://docs.comfy.org/agent-tools). For third-party custom-node or ComfyUI-core bugs, offer their own GitHub as before, and only with the user's go-ahead. Triggers on "report this", "fix this bug", or any error in our software - the answer is the same.
comfyui-mcp and the ComfyUI Agent Panel are no longer maintained. Their GitHub issue trackers are closed and the AI-triage intake Worker is gone, so there is nowhere for a report to go. `report_issue` still exists so older prompts get a clear answer, but it files nothing and contacts nothing.
When the user hits a defect in comfyui-mcp or the panel:
1. Say plainly that this project is archived and will not receive fixes. 2. Point them at ComfyUI's **official** agent and MCP tooling, built and supported by the Comfy-Org team:
3. If the task can still be completed with what works here, complete it; if not, say which official tool covers it.
Do NOT:
the trackers reject new issues;
Unchanged: these go to the node or project's own GitHub, and it is offer-and-ask — you propose the workaround and/or the report, and act only once the user agrees. `troubleshooting` still covers ordinary generation failures (OOM, a missing model, bad params).
This project is no longer maintained. ComfyUI now ships official agent and MCP tooling — Comfy Agent and Comfy MCP — built and supported by the Comfy-Org team with deeper integration than a community project can match.
Repo: artokun/comfyui-mcp
Train custom LoRAs with ostris AI-Toolkit. Covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base, low-VRAM image LoRAs). Use when the…
Anime/illustration text-to-image (ANIMA 1.0, ~2B Cosmos DiT). Use for anime, manga, illustrated characters; accepts Danbooru tags + natural language;…
Train a custom anime LoRA on the ANIMA base model with Citron's local Gradio trainer (kohya sd-scripts), <6GB VRAM, character/style LoRAs; covers setup,…
Discover Civitai models with the BUILT-IN download_model action:"search_civitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on…
Diagnose and fix video/image color OBJECTIVELY with the get_image (action:"analyze_color") tool (scopes/stats such as black/white points, contrast, saturation,…
Core ComfyUI knowledge covering workflow format, node types, pipeline patterns, and MCP tool usage