Help us improve
Share bugs, ideas, or general feedback.
How this command is triggered — by the user, by Claude, or both
Slash command
/comfy:debug prompt_id or "last" to debug the most recent executionThe summary Claude sees in its command listing — used to decide when to auto-load this command
# /comfy-debug — Diagnose a Failed Workflow The user wants to find out why a ComfyUI workflow execution failed and get a suggested fix. ## Instructions 1. **Get the execution history.** The argument is: $ARGUMENTS - If a prompt_id is provided, call `get_history` with that prompt_id - If "last" is provided or no argument given, call `get_history` with no prompt_id to get the most recent execution 2. **Extract the error.** From the history response, identify: - `node_id`: the node where execution failed - `node_type` / `class_type`: what kind of node it was - `exception_mes...
/forensicsPerforms post-mortem investigation for failed or stuck workflows, producing a read-only diagnostic report based on problem description.
/dogfoodReviews failed tool calls in the session, diagnoses root causes using traces and playbooks, triages into code bug, docs issue, or user error, and produces a report.
/debug_workflowDebugs Output SDK workflow issues in local dev environment: verifies Docker services, API/Temporal health, lists recent runs, analyzes failures, and applies fixes via decision trees.
/workflow-debugInteractively debugs Cloudflare Workflow instances: identifies failures via wrangler CLI, fetches details, diagnoses errors like timeouts or serialization issues, and suggests fixes.
/fal-debugDiagnoses and fixes fal.ai integration issues including authentication, rate limits, timeouts, validation, uploads, and websockets. Provides diagnostic steps and code examples in JS/TS/Python.
/runParses and executes legacy inline orchestration workflow syntax supporting raw operators, YAML frontmatter templates, and temporary AI agents with model overrides.
Share bugs, ideas, or general feedback.
The user wants to find out why a ComfyUI workflow execution failed and get a suggested fix.
Get the execution history. The argument is: $ARGUMENTS
get_history with that prompt_idget_history with no prompt_id to get the most recent executionExtract the error. From the history response, identify:
node_id: the node where execution failednode_type / class_type: what kind of node it wasexception_message: the error messagetraceback: the full Python tracebackIf the execution succeeded (no error), tell the user it completed normally and show the output summary.
Get relevant logs. Call get_logs with a keyword filter matching the error — use the exception class name (e.g., "RuntimeError", "ValueError") or a distinctive phrase from the error message. Request up to 200 lines.
Inspect the failing node. Call get_node_info with the node_type of the failing node. Check:
Check for missing models. If the error mentions a missing file, model, or checkpoint:
list_local_models to see what's installeddownload_model or provide a search query for search_modelsCheck for missing nodes. If the error is a KeyError or mentions an unknown node type:
search_custom_nodes with the node class name to find which pack provides itPresent the diagnosis. Provide a clear summary:
clear_vram before retryingUser: /comfy-debug last
Steps:
get_history with no prompt_idget_logs with keyword "RuntimeError"get_node_info for "KSampler"clear_vram before retrying