Read The Trace
Testing & Qualityread-the-traceRead The Trace is an Agent Skill for testing & quality published in the Archive228/loopkit repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Extract the actual cause from a stack trace instead of pattern-matching the error type. Use on any crash or exception.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/Archive228/loopkit/blob/HEAD/skills/read-the-trace/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/read-the-trace, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Read the Trace
LLMs love to see "TypeError" and generate a generic fix without reading the trace. Don't.
- Find the deepest frame in YOUR code — not the library frame at the top. That's where the bad value entered.
- Read the actual values: what was null/undefined/wrong-type, and where it came from.
- Trace it one level up: why was that value bad? The root is usually 1-2 frames above the throw.
- Reproduce with that exact input before fixing. A TypeError can mean a hundred things. The trace tells you which one — read all of it, including the "caused by".