memory-review

$npx mdskill add alirezarezvani/claude-skills/memory-review

Analyzes auto-memory for optimization

  • Identifies stale knowledge entries
  • Depends on MEMORY.md files
  • Uses recurrence indicators for analysis
  • Delivers recommendations via text output

SKILL.md

.github/skills/memory-reviewView on GitHub ↗
---
name: "memory-review"
description: "Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics. Use when the user runs /si:memory-review or asks what has been learned and what should be promoted or pruned."
---

# /si:memory-review — Analyze Auto-Memory

Performs a comprehensive audit of Claude Code's auto-memory and produces actionable recommendations.

## Usage

```
/si:memory-review                    # Full review
/si:memory-review --quick            # Summary only (counts + top 3 candidates)
/si:memory-review --stale            # Focus on stale/outdated entries
/si:memory-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   - Mentions outdated tools, versions, or commands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:memory-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:memory-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 to delete stale entries — auto-memory will re-learn if needed

More from alirezarezvani/claude-skills

SkillDescription
a11y-auditAccessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines.
ab-test-setupWhen the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.
ad-creativeWhen the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creative testing.' This is pure creative production — distinct from paid-ads (campaign strategy). Use ad-creative when you need the copy, not the campaign plan.
adversarial-reviewerAdversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.
aeoAnswer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences, auditing existing content for E-E-A-T signals, tracking which pages get cited by which LLMs, or building a citation-friendly content strategy. Triggers — 'AEO audit', 'optimize for ChatGPT', 'get cited by Perplexity', 'LLM citation strategy', 'answer engine optimization', 'content for AI search', 'E-E-A-T audit'. Output is a markdown audit report (default) or JSON for pipeline integration. Stdlib-only Python tools.
agent-decision-receiptsMint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access, model decision) so it can be verified later from the certificate alone. Use when an autonomous agent takes a side-effecting action that may need to be proven later, or when satisfying EU AI Act Article 12 record-keeping. Three decisions: whether an action needs a receipt, minting it, verifying it. Signing is delegated to the open-source OpenAgentOntology package. Not after-the-fact log analysis; not a hosted notary; not a legal opinion.
agent-designerUse when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).
agent-harnessTurn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).
agent-launcher-orchestratorUse when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed agent", "run this on a schedule", "grade my agent against a rubric", "set up a nightly worker". Reads the per-session goal (./my-agent/goal.json), routes deterministically to one of five phase sub-skills (interview → stage-launch → grade-iterate → run-without-you → wrap-up) via goal_router.py, and compiles the goal+phase into an execution shape (single-pass workflow / bounded grade→iterate loop / recurring cron deployment loop) via loop_compiler.py. Forks context so heavy intake (build sheets, payloads, eval cases) stays out of the parent thread. All launches are emitted as BYOK curl the user runs with their own key; no tool makes API calls. Inspired by anthropics/launch-your-agent (Apache-2.0). Distinct from engineering/agent-harness (generic domain loop) and engineering/write-a-skill (authors Claude Code skills, not CMAs).
agent-memoryUse when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps re-learning the same correction, why a remembered rule is wrong, or where a memory line came from. Implements a four-tier store (L0 transcripts / L1 candidates / L2 project context / L3 stable persona) where promotion is earned by recurrence across sessions and days, never by one confident statement, and nothing reaches a committed file without a human adopting it.