Cr Tune — Development skill for Claude Code
Mine the CR ledger for disproved classes per critic and draft citation-backed tuning proposals (.coderabbit.yaml / critics.json) — proposals only, never auto-applied.
How to install Cr Tune
Installs to ~/.claude/commands/yotamleo-himmel-cr-tune.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/yotamleo/Himmel/HEAD/.claude/commands/cr-tune.md -o ~/.claude/commands/yotamleo-himmel-cr-tune.md Restart Claude Code, or start a new session, for it to be picked up.
What Cr Tune does
description: Mine the CR ledger for disproved classes per critic and draft citation-backed tuning proposals (.coderabbit.yaml / critics.json) — proposals only, never auto-applied
- Run the mechanical miner and the scorecard:
bash scripts/cr/cr-tune.sh bash scripts/cr/cr-scores.sh - Judgment layer (the session): map each disproved cluster / calibration flag / re-litigation signal to a named concept class (e.g. "test-fixture over-verification", "CR-round re-litig
Alternatives in Development
- Notebooklm Skill — Use this skill to enable Claude Code to communicate directly with your Google NotebookLM notebooks 5.9k ★
- Tutti — Where people and agents build in tune 3.5k ★
- Clawgod — This is NOT a third-party Claude Code client 837 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Claude Code Game Builder
Claude Code skill: multi-agent build → capture → blind critic → fix loops that push a game toward a reference-
Tune For Opus5
You are a senior engineer tuning this project's Claude Code instruction files so that Claude Opus 5 follows th
Sup Mem
Memory for Claude Code that measures whether its memories helped — outcome ledger, self-tuning retrieval, bite
Mine
Mine recent transcripts for repeated workflows and corrections, then draft up to 10 skill/memory proposals for
Dev Edit
Familiar: Editorial report on the draft; nothing applied
Ultragoal
Execute or resume an approved OMJ plan to evidence-backed completion, using native goal continuation when avai
Related Agents
PR Review Validator
Harvest one PR's bot reviews (Copilot, CodeRabbit, Greptile, code scanning), report where each auto-running bo
Critic Security
Review code for OWASP-style security issues (injection, authn/authz, secrets, supply chain, LLM-specific) in p
ChatGPT Plan Review
ChatGPT implementation-plan review targeting tasks/builds/{slug}/plan.md; manual / automated / parallel modes,