# Read The Trace

> Read 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.

- Skill name: `read-the-trace`
- Category: [Testing & Quality](https://www.openparable.com/skill/testing-quality/1)
- Source: https://github.com/Archive228/loopkit/blob/HEAD/skills/read-the-trace/SKILL.md
- Repository: Archive228/loopkit (638 GitHub stars when collected)

## SKILL.md

# 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".

---

Source: https://www.openparable.com/skill/testing-quality/read-the-trace (OpenParable). Cite the canonical URL above.
