panel-operations
FeaturedOn-demand procedures for the ComfyUI sidebar panel agent that are too long to sit in the system prompt. Read it when a task lands in one of these areas. subgraph boundary rails and blueprint reuse, merging or composing workflows across tabs, pinning your edits to one workflow, opening staged or downloaded workflow files, untangling Get/Set-bus and rgthree toggle-heavy graphs, authoring rgthree Fast Groups nodes, the LoRA Manager autocomplete-node limitation, the CivitAI browser flow, downloading model weights, reading hardware and runtime stats, Prompt Director audits, custom-node crash recovery, run-to-node render debugging, and multi-stage pipeline chaining. Each section is a lookup, not background reading. Reach for the one you need instead of guessing, and follow the tool's own description for parameter detail.
Install
Quality Score: 88/100
Skill Content
Details
- Author
- artokun
- Repository
- artokun/comfyui-mcp
- Created
- 6 months ago
- Last Updated
- yesterday
- Language
- TypeScript
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
workflow-layout
Lay out and organize a ComfyUI workflow cleanly on the live panel canvas. Dependency-layered node placement with no overlaps, subgraphs, colored group boxes, and subgraph rail alignment. Use when asked to tidy / clean up / organize / arrange a workflow, add groups or subgraphs, fix overlapping nodes, or build a workflow that should look good from the start.
agentprism-workflow-authoring
Write and run AgentPrism workflow scripts — the `export const meta` + agent()/parallel()/pipeline() JavaScript DSL executed by @automatalabs/workflows and by the @automatalabs/mcp-server `workflow` tool. Use when writing or editing a workflow script, or when running one through the MCP `workflow` tool. Covers the script API, per-call routing to ACP backends (Claude Code, Codex, OpenCode, pi, custom agents), structured outputs via JSON Schema, human checkpoints, token budgets, worktree isolation, the resume rules, and run operations (run, await, inspect, stop, execution logs).
panel
Run an external multi-model panel review and reconcile the results. Triggers on "panel", "panel this", "second opinion", "ask the outside models", "cross-check this", or /panel — and on 「会诊」「外部会诊」「问问外面的模型」「交叉验证」「让它们评评」. The panel is five non-Claude models, each on its own configurable endpoint; for Claude's own models (opus/sonnet/fable) use the consult skill instead.