CtrlK
BlogDocsLog inGet started
Tessl Logo

ce-retune

Retune a skill corpus for a new model, measurement-first: mine the run archive for a baseline, establish a noise floor, audit the corpus adversarially, then cut in measured passes until a pre-registered bar clears. Requires a benchmark harness that can A/B two builds of the corpus; refuses without one.

SKILL.md
Quality
Evals
Security

No security review available

No security review has been published for this skill

Repository
EveryInc/compound-engineering-plugin

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.