home/coding/cursor-skill-workflow-debugger

Cursor Skill: workflow-debugger

GPTClaudeDeepSeek··1,156 copies·updated 2026-07-14
cursor-skill-workflow-debugger.prompt
# Cursor Skill: workflow-debugger

## Intent

Debug CI, local workflow, and automation failures by reproducing the issue, finding root cause, and making targeted fixes.

## Validation Checklist

- [ ] The output matches the skill's intended task and platform.
- [ ] Required inputs, assumptions, and uncertainty are explicit.
- [ ] Safety, scope, and source limits are respected.
- [ ] The response follows the requested format or the skill's default output format.
- [ ] The result is practical enough to use without another cleanup pass.

Use this skill when a CI workflow, automation pipeline, script run, or local repro path is failing and the goal is to isolate the real blocker quickly. Focus on evidence, local reproduction, and the smallest fix that resolves the failure.

## Use When

- A CI workflow is failing
- A GitHub Actions job broke after a code or config change
- A local script or command fails and needs a focused debug loop
- You need a structured path from logs to repro to fix

## Do Not Use When

- The user wants a broad architecture redesign
- There is no failure output, command, or workflow context
- The main task is code review rather than debugging

## Workflow

1. Read the failing output first.
2. Identify the exact failing step, command, or assertion.
3. Separate signal from noise.
4. Build the shortest possible local repro path.
5. Check recent changed files that could affect:
   - workflow config
   - environment variables
   - paths
   - dependency installation
   - test setup
   - build outputs
6. State the most likely root cause.
7. Suggest the smallest fix and the validation step.

## Output Format

when to use it

Community prompt sourced from the open-source GitHub repo mickpletcher/AI-Skills (NOASSERTION). A "Cursor Skill: workflow-debugger" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.

tags

codingcommunitydeveloper

source

mickpletcher/AI-Skills · NOASSERTION