Individual skill

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.

skills/ce-retune/SKILL.md

Read pinned source

Source commit 3449230705a508229a5a298671e9031e489f0278

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: No
Observed behavior: Network or broad shell
Last checked: Nov 2, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 25,972
Repository last updated: Nov 7, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

compound Repository topic
engineering Repository topic
security Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 4,684 bytes
SKILL.mdcore · 4,684 bytes
agents/openai.yamlasset · 43 bytes
references/baseline-mining.mddoc · 10,666 bytes
references/corpus-audit.mddoc · 12,768 bytes
references/cut-passes.mddoc · 10,984 bytes
references/halt-taxonomy.mddoc · 11,227 bytes
references/noise-floor.mddoc · 13,243 bytes
references/workflow-shapes.mddoc · 11,725 bytes

Read excerpt


# Retune a Corpus for a New Model

A corpus that degrades on a new model is a measurement problem before it is a writing problem: rewriting what looks wrong produces a plausible fix list and no way to know whether any item mattered.

**Outcome:** a corpus whose measured behavior on the target model clears a bar registered before any change, with the regression classes removed and each removal attributable.

**Done:** the bar is cleared, or the run reports the specific claim it could not support. A green test suite is not done: it proves nothing broke, not that behavior improved.

**Non-goal:** word reduction. Leanness and performance are separate programs that share a corpus; only one of them is the result here. Report completion, not word count.


## Phase 0: the measurement gate — check this first

This skill cannot run without a way to observe behavior. Check for all three, and name whichever is missing: