
Review
Audit Claude Code auto-memory for stale notes, duplicate concepts, and entries that should graduate into permanent memory rules.
Overview
review is an agent skill most often used in Operate (also Build agent-tooling) that audits Claude Code auto-memory and recommends promotions, merges, and stale deletions.
Install
npx skills add https://github.com/alirezarezvani/claude-skills --skill reviewWhat is this skill?
- Full `/si:review` pass plus `--quick`, `--stale`, and `--candidates` focus modes
- Locates project memory under `~/.claude/projects/.../memory` and reads MEMORY.md
- Flags recurrence, staleness (missing files, outdated tools), and consolidation opportunities
- Checks MEMORY.md size against the 200-line startup limit
- Suggests `/memory` when auto-memory appears disabled
- 200-line MEMORY.md startup limit referenced in audit steps
Adoption & trust: 1.6k installs on skills.sh; 17.5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your agent memory folder is full of one-off notes and outdated paths, and you cannot tell what should stay in MEMORY.md.
Who is it for?
Solo builders running Claude Code daily on one repo who notice repeated mistakes or bloated MEMORY.md.
Skip if: Teams not using Claude auto-memory, or code review of application PRs (use a dedicated code-review skill instead).
When should I use this skill?
User runs `/si:review` or asks to analyze Claude auto-memory for promotion, staleness, consolidation, or health metrics.
What do I get? / Deliverables
You get actionable promotion, consolidation, and stale-entry recommendations grounded in your on-disk memory files.
- Memory health report
- Promotion and stale-entry recommendations
- Optional quick summary with top candidates
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Operate/iterate is the canonical shelf because the skill is ongoing hygiene on project memory after you have been shipping with agents. Iterate subphase matches tuning how the agent remembers context—not greenfield coding or launch distribution.
Where it fits
Run a full review after deleting deprecated API routes so memory stops referencing removed files.
Use `--candidates` mode when promoting recurring coding conventions from topic files into MEMORY.md.
Run `--stale` after changing billing stack so support macros in memory match current tooling.
How it compares
Memory-health checker for Claude projects—not a substitute for human PR or security review skills.
Common Questions / FAQ
Who is review for?
Indie developers and solo founders using Claude Code who maintain auto-memory and want periodic audits with CLI-backed checks.
When should I use review?
In Operate/iterate after refactors; in Build/agent-tooling when onboarding a long-lived repo; in Grow/support when support playbooks in memory drift from reality.
Is review safe to install?
It reads local memory paths via shell; confirm paths before running and review the Security Audits panel on this Prism page.
SKILL.md
READMESKILL.md - Review
# /si:review — Analyze Auto-Memory Performs a comprehensive audit of Claude Code's auto-memory and produces actionable recommendations. ## Usage ``` /si:review # Full review /si:review --quick # Summary only (counts + top 3 candidates) /si:review --stale # Focus on stale/outdated entries /si:review --candidates # Show only promotion candidates ``` ## What It Does ### Step 1: Locate memory directory ```bash # Find the project's auto-memory directory MEMORY_DIR="$HOME/.claude/projects/$(pwd | sed 's|/|%2F|g; s|%2F|/|; s|^/||')/memory" # Fallback: check common path patterns # ~/.claude/projects/<user>/<project>/memory/ # ~/.claude/projects/<absolute-path>/memory/ # List all memory files ls -la "$MEMORY_DIR"/ ``` If memory directory doesn't exist, report that auto-memory may be disabled. Suggest checking with `/memory`. ### Step 2: Read and analyze MEMORY.md Read the full `MEMORY.md` file. Count lines and check against the 200-line startup limit. Analyze each entry for: 1. **Recurrence indicators** - Same concept appears multiple times (different wording) - References to "again" or "still" or "keeps happening" - Similar entries across topic files 2. **Staleness indicators** - References files that no longer exist (`find` to verify) - Mentions outdated tools, versions, or commands - Contradicts current CLAUDE.md rules 3. **Consolidation opportunities** - Multiple entries about the same topic (e.g., three lines about testing) - Entries that could merge into one concise rule 4. **Promotion candidates** — entries that meet ALL criteria: - Appeared in 2+ sessions (check wording patterns) - Not project-specific trivia (broadly useful) - Actionable (can be written as a concrete rule) - Not already in CLAUDE.md or `.claude/rules/` ### Step 3: Read topic files If `MEMORY.md` references or the directory contains additional files (`debugging.md`, `patterns.md`, etc.): - Read each one - Cross-reference with MEMORY.md for duplicates - Check for entries that belong in the main file (high value) vs. topic files (details) ### Step 4: Cross-reference with CLAUDE.md Read the project's `CLAUDE.md` (if it exists) and compare: - Are there MEMORY.md entries that duplicate CLAUDE.md rules? (→ remove from memory) - Are there MEMORY.md entries that contradict CLAUDE.md? (→ flag conflict) - Are there MEMORY.md patterns not yet in CLAUDE.md that should be? (→ promotion candidate) Also check `.claude/rules/` directory for existing scoped rules. ### Step 5: Generate report Output format: ``` 📊 Auto-Memory Review Memory Health: MEMORY.md: {{lines}}/200 lines ({{percent}}%) Topic files: {{count}} ({{names}}) CLAUDE.md: {{lines}} lines Rules: {{count}} files in .claude/rules/ 🎯 Promotion Candidates ({{count}}): 1. "{{pattern}}" — seen {{n}}x, applies broadly → Suggest: {{target}} (CLAUDE.md / .claude/rules/{{name}}.md) 2. ... 🗑️ Stale Entries ({{count}}): 1. Line {{n}}: "{{entry}}" — {{reason}} 2. ... 🔄 Consolidation ({{count}} groups): 1. Lines {{a}}, {{b}}, {{c}} all about {{topic}} → merge into 1 entry 2. ... ⚠️ Conflicts ({{count}}): 1. MEMORY.md line {{n}} contradicts CLAUDE.md: {{detail}} 💡 Recommendations: - {{actionable suggestion}} - {{actionable suggestion}} ``` ## When to Use - After completing a major feature or debugging session - When `/si:status` shows MEMORY.md is over 150 lines - Weekly during active development - Before starting a new project phase - After onboarding a new team member (review what Claude learned) ## Tips - Run `/si:review --quick` frequently (low overhead) - Full review is most valuable when MEMORY.md is getting crowded - Act on promotion candidates promptly — they're proven patterns - Don't hesitate t