- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add artokun/comfyui-mcp --skill debug-render -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add artokun/comfyui-mcp --skill debug-render -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add artokun/comfyui-mcp --skill debug-render -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add artokun/comfyui-mcp --skill debug-render -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/artokun/comfyui-mcp/tree/HEAD/plugin/skills/debug-render來自發布者
When a final asset looks wrong (not when it errors), don't re-roll the whole graph and hope. Localize the fault. Render only as far as one stage and look at what that stage actually produces. The wrong-looking output is downstream of a first bad step. Find that step, fix it there, and everything after it follows.
The tool for this is panel_run with to_node_id ("run to node"), which uses
ComfyUI's native partial execution. Only the target output node plus
everything upstream of it renders; every other branch is skipped. That makes each
probe fast and cheap, and the output is delivered to you automatically, same
as any run. Don't poll.
If instead the run fails (red error, OOM, missing node, black image from a crash), use the troubleshooting skill. This skill is for outputs that complete but look wrong.
to_node_id must be an OUTPUT nodeComfyUI can only run to an output node: SaveImage, PreviewImage, SaveVideo,
SaveAudio, etc. (these show is_output: true in panel_query_graph detail rows). A bare
KSampler / VAEDecode / preprocessor is not an output node, so you can't target
it directly. To inspect a point that isn't already an output, add a preview
tap there:
Build a tap with panel_add_node + panel_connect, run to it, inspect, then
panel_remove_node the tap when you're done (unless the user wants to keep it).
panel_graph_outline (then panel_query_graph for specifics). Note node ids, the output nodes
(is_output: true), and every node's mode. A node in bypass/mute on
the path is OFF and is a top cause of wrong renders. Fix modes first with
panel_set_node_mode before you blame anything else.panel_run(to_node_id = that output node). Only that branch renders.panel_set_widget, panel_set_node_mode,
a rewire, or a different model. Then run-to-node there again to confirm the fix
before running the full graph.panel_remove_node) and do a final full
panel_run to produce the real saved asset.MaskToImage-preview the mask actually reaching
the sampler (mask misalignment is the usual culprit).executed event and the
image is delivered to you inline, including PreviewImage taps, which arrive
labeled as a preview (temporary, not a saved file). Don't poll; just end the
turn and read the delivered image. A preview tap with no SaveImage means "no
saved output ran", which is expected for a probe.panel_run to_node_id product behavior (this repo).Debug a WRONG or imperfect render (not a hard error) by inspecting inputs and intermediate steps with run-to-node. Render one branch up to an output, preview-tap latents/masks/preprocessor maps, local
---name: debug-renderdescription: Debug a WRONG or imperfect render (not a hard error) by inspecting inputs and intermediate steps with…---# plugin/skills/debug-render/SKILL.md總覽
Debug a WRONG or imperfect render (not a hard error) by inspecting inputs and intermediate steps with run-to-node. Render one branch up to an output, preview-tap latents/masks/preprocessor maps, localize the first bad stage, then fix. Use when a final image/video completes but looks wrong, such as artifacts, wrong subject/pose/composition/color, blur, a ControlNet/IPAdapter/mask/LoRA not taking, or a two-stage refiner or upscale degrading the result. For errors/OOM/missing nodes use the troubleshooting skill.
常見問題
從發布者下載 plugin/skills/debug-render/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/artokun/comfyui-mcp。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。