Debug

SkillDev tools

Trace a bug, error, or regression to its root cause. Use when investigating a failure, a stack trace, unexpected behavior, or "why does X happen".

Then ask your AI: use the Debug skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.

No other account needed.

Add it as a step in a pipeline you build on Ahel, or connect Ahel to Claude, ChatGPT, Cursor, Claude Code or Codex and ask your AI to use it.

What this skill tells your AI

The instructions your AI receives, as published by thewinci/mimirs in skills/debug/SKILL.md and read by Ahel’s review.

Goal: find the cause, not just the symptom.

Locate the symptom — search "<error text / behavior>"; if you have a name, search_symbols <name> (exact lookup). read_relevant the suspect code.
Follow the path — trace from:<entrypoint> to:<suspect> to see how execution reaches the failure (shortest path is highlighted; a dynamic-dispatch hop ends a chain and is reported as such). usages <symbol> for who calls the suspect.
Known issues — get_annotations (search across notes) — the bug may already be flagged as a caveat.
When introduced — file_history <file> and search_commits "<symptom/area>" to find the change that likely caused it; git_context for recent uncommitted edits.
Past attempts — search_conversation "<symptom>" — was this hit or discussed before?
Fix & record — once fixed, annotate the root cause on the file and create_checkpoint what was wrong and how it was resolved.

Finish: state the root cause (file:line), the path from trigger to failure, and the fix.

Advanced