bare-eval
Run isolated eval and grading calls using CC 2.1.81 --bare mode. Constructs claude -p --bare invocations for skill evaluation, trigger testing, and LLM grading without plugin/hook interference. Use when running eval pipelines, grading skill outputs, benchmarking prompt quality, or testing trigger accuracy in isolation.
- Compatibility
- Claude Code 2.1.220+
Pinned to revision 1ff988bd66da, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/bare-eval/SKILL.md
- skills/bare-eval/references/grading-schemas.md
- skills/bare-eval/references/invocation-patterns.md
- skills/bare-eval/references/troubleshooting.md
- skills/bare-eval/rules/_sections.md
- skills/bare-eval/rules/bare-grading-only.md
- skills/bare-eval/rules/bare-plugin-conflict.md
- skills/bare-eval/rules/bare-requires-api-key.md
- skills/bare-eval/test-cases.json
- skills/bare-eval/workflows/skill-fitness.js
Every link opens the file at its source, pinned to the revision this page describes.