About evals-start
A routing plugin that directs evaluation requests to a specialized skill based on the available traces, evaluation pipeline, and goal. It identifies which skill to load; the selected skill supplies the actual workflow.
Key features
- 01Routes by evaluation scenario
- 02Covers error analysis and eval audits
- 03Includes code evals and LLM judges
- 04Includes synthetic data and RAG evaluation
- 05Recommends asking when the situation is unclear
Use cases
- 01Choose error analysis for available traces
- 02Check the trustworthiness of an existing eval pipeline
- 03Select code or LLM evaluation for a known failure mode
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/evals-startin Claude Code to confirm it loaded.
Bundled filesagents/openai.yaml
Details
From the project READMEEvals Start
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 that code can check (e.g., format, schema, regex, execution) | write-code-eval |
| 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.