Ce Retune

everyinc/compound-engineering-plugin/skills/ce-retune

by everyinc67035e931c5cNo license25K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated today

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.

Instructions onlyAI & Agents

Only the file list is public. File contents are available once the skill is installed in a workspace.

PathSizeType
agents/openai.yaml43 Bapplication/yaml
references/baseline-mining.md10.4 KBtext/markdown
references/corpus-audit.md12.5 KBtext/markdown
references/cut-passes.md10.7 KBtext/markdown
references/halt-taxonomy.md11 KBtext/markdown
references/noise-floor.md12.9 KBtext/markdown
references/workflow-shapes.md11.5 KBtext/markdown
SKILL.md4.6 KBtext/markdown

Source and attribution

Source:everyinc/compound-engineering-plugininskills/ce-retuneat commit67035e9

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal