Auree Aubert 2c072d267d Let the routing evals grade any skill set, not just this repo (#81) ...

The standalone skills in getcargohq/gtm-skills compete for prompts using the
same four-part descriptions, and twelve of them are deliberately adjacent —
find-work-email against enrich-linkedin-profile against find-linkedin-url.
That is exactly the set most likely to drift into each other, and it had no
regression test because the ranker was hardwired to this repo's layout.

`--skills-root` points it at any directory of `<name>/SKILL.md`; cases default
to `<root>/evals/routing.jsonl` and `--cases` overrides. Default behaviour is
unchanged: 17 skills, 81/81 core.

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-08-12 14:44:56 -07:00

19 KiB

Raw Permalink Blame History

View Raw