claude-md-optimizerlisted

# Claude MD Optimizer **Behavioral Classification: Guided Decision (ASK, THEN EXECUTE)** This skill analyzes CLAUDE.md files and proposes optimizations using progressive disclosure patterns. It NEVER makes destructive changes without explicit user approval. Always present the plan, get confirmation, then execute. ## Quick Start ### Phase 1: Analyze 1. Read CLAUDE.md and count total lines 2. Parse into sections and categorize each: - **Essential** - Required for every session (build commands, test patterns, security rules) - **Reference** - Needed occasionally (architecture docs, API references, troubleshooting) - **Redundant** - Duplicates existing docs or overly verbose ### Phase 2: Detect Constraints 1. Check `.gitattributes` for `filter=git-crypt diff=git-crypt` patterns 2. Identify encrypted paths (docs/, .claude/, etc.) 3. Find safe unencrypted directory for sub-documents (prefer project root or subdirs) 4. **Scan for CI machine-readable dependencies** (see [constraints.md](./constraints.md)) ### Phase 3: Plan Present categorization table to user: ``` | Section | Lines | Category | Target | Rationale | |---------|-------|----------|--------|-----------| | Docker Commands | 45 | Reference | docker-guide.md | Used <10% of sessions | | CI Health | 120 | Reference | ci-reference.md | Detailed reference rarely needed | | Git-Crypt Setup | 30 | Essential | Keep inline | Unlock instructions (chicken-and-egg) | ``` Wait for user approval before proceeding. ### P