AdYour product here, seen by people installing AI tools every day
AI Plugin Index

ce-retune

Skill by EveryInc · updated · ★ 26k

Score 91

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. ce-retune is published by EveryInc on GitHub.

InstallGitHub
Yours? Claim it
Works withClaude CodeClaude apps Antigravity CLI

Install ce-retune

Built from the published package, never by AI
git clone --depth 1 https://github.com/EveryInc/compound-engineering-plugin /tmp/compound-engineering-plugin && mkdir -p ~/.claude/skills && cp -r /tmp/compound-engineering-plugin/skills/ce-retune ~/.claude/skills/ce-retune

Run in your terminal. Claude Code loads skills from ~/.claude/skills automatically.

Step-by-step: install ce-retune in Claude Code

Skills can run scripts on your machine. Some need an API key: check the README.

Maintenance

Last commit in the past day

Licence

MIT: permissive, fine for commercial use

Quality

Clear description, installs from GitHub, 25,684 stars, original repository

Security

No risky patterns in the files we checked

Weekly newsletter

Like ce-retune? Get the best new skills every week

The best new tools, security warnings before you install something risky, and one practical tip. Free, three minute read.

No spam. Unsubscribe in one click. Privacy

Security check

A

No download-and-run commands, hidden instructions or signs of sending keys out were found.

Checked automatically: skills/ce-retune/SKILL.md. This looks for known risky patterns and is not a full audit. How grades work

Inside the skill

  • SKILL.md5 KB
  • agents/openai.yaml43 B
  • references/baseline-mining.md10 KB
  • references/corpus-audit.md12 KB
  • references/cut-passes.md11 KB
  • references/halt-taxonomy.md11 KB
  • references/noise-floor.md13 KB
  • references/workflow-shapes.md11 KB

Alternatives to ce-retune

All alternatives →
app-buildersickn33
92

Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.

AAA Skill 48k
skill-creatorGentleman-Programming
92

Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter.

AAA Skill 8k
spec_generatorgoogle-gemini
91

Generates a structured Workable Spec JSON to guide a Developer Worker.

AAA Skill 108k
moatmrisickn33
91

Analyze AI disruption pressure across a business, map competitive exposure, and produce a 90-day defensive action plan.

AAA Skill 48k
optim-agentsickn33
91

Guide agent-driven parameter optimization for configurable systems with measurable objectives. Use for HPO, inference tuning, simulations, or RL/control experiments.

AAA Skill 48k
pi-custom-modelsickn33
91

Register custom Pi Agent model slugs so saved OpenRouter variants resolve correctly.

AAA Skill 48k
ce-retune vs app-builder ce-retune vs skill-creator ce-retune vs spec_generator

ce-retune: common questions

How do I install ce-retune?

Run the command above to copy the skill into ~/.claude/skills/. Claude Code picks it up automatically.

Is ce-retune free?

The code is published under the MIT licence. The service it connects to may have its own pricing.

Is ce-retune safe to use?

It scores 91 of 100. Grades: maintenance A, licence A, quality A. Security check: grade A, no risky patterns found in the files checked. Review the code before you install. How grades work.

What are alternatives to ce-retune?

Similar skills: app-builder, skill-creator, spec_generator, moatmri.

Add to stack

Loading.