Validate brain-os skill eval definitions against SKILL.md content.
npx skills add https://github.com/sonthanh/brain-os-plugin --skill eval-sonthanh
Please help me install this Agent Skill. Skill: eval Source: https://github.com/sonthanh/brain-os-plugin/tree/main/skills/eval Command: npx skills add https://github.com/sonthanh/brain-os-plugin --skill eval-sonthanh
This evaluation tool ensures that skill edits do not introduce regressions by automatically validating eval definitions across all skills.
Run /eval to list skills with evals and to execute their checks.
High-intent search queries and answers about installing and using this skill.
Regression testing for brain-os skills is automated by validating eval definitions against SKILL.md content. Run /eval to list skills with evals and execute their checks, producing a test-style report suitable for CI workflows.
Skill correctness validation checks that edits to brain-os skills do not introduce regressions. You need it after edits or before releases to verify that each expectation in evals/evals.json matches the content in SKILL.md.
Yes, the eval tool outputs results in a clear test-style report suitable for CI workflows. It validates eval definitions across all skills in the repository after edits, preventing regressions before releases.
Validating eval definitions across all skills is done by reading evals/evals.json for each skill and validating each entry against its SKILL.md. Running /eval lists available skills with evals and executes their checks automatically.
The best way to prevent regressions when editing SKILL.md files is automated validation of eval definitions. The eval tool reads evals/evals.json for each skill and validates each expectation against the updated SKILL.md content.
Skill edits cause regressions because manual review misses expectations defined in evals/evals.json. Automating validation by checking each expectation against SKILL.md content catches regressions that manual review overlooks.
cr330326Convert SKILL.md and references into evals.json, grade.py, and running guides.
kanade0404Diagnose failing GitHub PR checks and apply root-cause fixes.
murphytruemanGenerate CI/CD pipeline configurations for design system quality checks.
verselesScan codebases across 28 languages for technical debt metrics.
