Investigate bugs by clarifying expected behavior, reproducing the problem, and testing possible causes. The skill helps prepare a fix plan with risks and validation steps before code changes begin.
AI DevKit · Guide structured debugging before code changes by clarifying expected behavior, reproducing issues, identifying likely root causes, and agreeing on a fix plan with validation steps. Use when users ask to debug bugs, investigate regressions, triage incidents, diagnose failing behavior, handle failing tests, analyze production incidents, investigate error spikes, or run root cause analysis (RCA).
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Debug with an evidence-first workflow before changing code.
npx ai-devkit@latest memory search --query "<observed behavior>" --tags "debug,root-cause"dev-smoke check that fails before the fix and passes after.verify skill — including regression verification for bug fixes.dev-retro to prevent recurrence; run only if the user agrees.npx ai-devkit@latest memory store --title "<root cause>" --content "<diagnosis and fix>" --tags "debug,root-cause"If task tracing is usable, choose a short kebab-case debug task name when no
task name exists, then use task optionally: record repro/final results as
evidence, the current hypothesis as next, and blockers only when they
materially affect progress. Never block debugging because task tracing is
unavailable.
| Rationalization | Why It's Wrong | Do Instead |
|---|---|---|
| "I already know the cause" | Assumptions skip evidence | Reproduce and prove it first |
| "This is urgent, just fix it" | A wrong fix wastes more time | 10 minutes of diagnosis saves hours |
| "The fix is obvious from the stack trace" | Stack traces show symptoms, not causes | Trace backward to the root cause |
Use this response structure:
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Find active Codex, Claude Code, and other AI agents, inspect their recent context, and exchange messages with them. Use it to locate an agent, share information, or send a request and wait for a reply through ai-devkit commands.
Manage running AI agents with ai-devkit commands: identify sessions, list and inspect agents, start workers, assign or group tasks, resume sessions, and stop agents. The skill helps track assignments and verify completed work before reporting it.
Coordinate ongoing work across multiple agents by checking progress, resolving dependencies, unblocking agents, relaying relevant results, and verifying completion. Use it to supervise a shared workflow across repeated check-ins.
Check whether AI DevKit is ready on the local machine, identify setup gaps it can address, and run the narrowest relevant setup for supported agent harnesses. Recheck status afterward and report remaining manual actions.
Explore ideas for products, content, names, strategies, technical approaches, or decisions. It frames the goal and constraints, generates distinct options, challenges assumptions and tradeoffs, then narrows the result to three strong choices with reasons and a next step.
Update the top Unreleased section of CHANGELOG.md using commits since the latest release. Add one concise linked line per commit, using a pull request link when evidence is clear and a commit link otherwise, while preserving the file’s existing style.