About start
A routing skill for choosing a focused evaluation workflow based on a user's task, then loading and following that skill. It covers trace analysis, evaluation audits, judge prompts, evaluator validation, synthetic data, review interfaces, and RAG evaluation.
Key features
- 01Routes requests to targeted evaluation skills
- 02Covers trace-based error discovery
- 03Includes evaluation pipeline auditing
- 04Supports judge and evaluator workflows
- 05Routes RAG and annotation tasks
Use cases
- 01Analyze traces to identify failure modes
- 02Audit an existing evaluation pipeline
- 03Create or validate an LLM judge
- 04Evaluate a RAG pipeline
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/startin Claude Code to confirm it loaded.
Details
From the project READMEStart
This plugin splits eval work into targeted skills. Your job here is small: find the row below that matches the user's situation, tell the user which skill you are loading and why, then load that skill and follow its workflow from start to finish instead of improvising your own version of it.
| Situation | Skill to load |
|---|---|
| Has traces, wants to find failure modes, no established taxonomy yet | error-discovery |
| Has an existing eval pipeline and wants to know if it can be trusted | eval-audit |
| Has a known failure mode and wants an LLM judge for it | write-judge-prompt |
| Has an LLM judge or evaluator and wants to check its quality | validate-evaluator |
| Has no traces to review yet | generate-synthetic-data, then error-discovery |
| Wants a custom annotation interface for some other labeling task | build-review-interface |
| Wants to evaluate a RAG pipeline | evaluate-rag |
Most requests that mention error analysis with traces in hand mean error-discovery. New users with an existing pipeline usually need eval-audit first. This file holds only routing. When in doubt about which row fits, ask the user instead of guessing. The workflow lives in the targeted skill.