Ce Retune

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

作者 everyinc67035e931c5c無授權條款25K 個星標收錄於 2026年10月8日更新於 2026年10月8日儲存庫今天更新

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.

僅含說明AI & Agents

僅公開檔案列表。將技能安裝到工作區後即可檢視檔案內容。

路徑大小類型
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

來源與署名

來源:everyinc/compound-engineering-plugin位於skills/ce-retune提交67035e9

授權條款: 無授權條款

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架