New: Earn 20% as an AgentAlley affiliate. Share your link and earn on every sale you refer. Join now New: Earn 20% as an affiliate. Join now

Analyze auto-memory for promotion candidates, stale entries

/si:memory-review — Analyze Auto-Memory

by alirezarezvani · MIT license · ★ 26,349 on GitHub · updated Aug 30

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

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.

---
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/si:memory-review --stale            # Focus on stale/outdated entries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
```

Overview

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

Manual install (npx, ZIP)
Claude Codenpx skills add alirezarezvani/claude-skills --skill memory-review -g -a claude-code
Claude Code (manual)mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/alirezarezvani/claude-skills/tar.gz/19392f7a0826 \ | tar -xz -C ~/.claude/skills --strip-components=4 claude-skills-19392f7a0826/engineering-team/self-improving-agent/skills/memory-review
Windows (PowerShell)New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/260f9e316d327b0119a9/memory-review.zip" -OutFile "$env:TEMP\memory-review.zip"; Expand-Archive "$env:TEMP\memory-review.zip" -DestinationPath "$HOME\.claude\skills" -Force
Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md4.2 KB
Read the files here
alirezarezvani/19392f71 file
Shared references2SKILL.md reads these from elsewhere in the repo. Not in the ZIP.Get them on GitHub ↗
SKILL.md
Show the full text127 lines

/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
# 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
1---
2name: "memory-review"
3description: "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."
4---
5 
6# /si:memory-review — Analyze Auto-Memory
7 
8Performs a comprehensive audit of Claude Code's auto-memory and produces actionable recommendations.
9 
10## Usage
11 
12```
13/si:memory-review # Full review
14/si:memory-review --quick # Summary only (counts + top 3 candidates)
15/si:memory-review --stale # Focus on stale/outdated entries
16/si:memory-review --candidates # Show only promotion candidates
17```
18 
19## What It Does
20 
21### Step 1: Locate memory directory
22 
23```bash
24# Find the project's auto-memory directory
25MEMORY_DIR="$HOME/.claude/projects/$(pwd | sed 's|/|%2F|g; s|%2F|/|; s|^/||')/memory"
26 
27# Fallback: check common path patterns
28# ~/.claude/projects/<user>/<project>/memory/
29# ~/.claude/projects/<absolute-path>/memory/
30 
31# List all memory files
32ls -la "$MEMORY_DIR"/
33```
34 
35If memory directory doesn't exist, report that auto-memory may be disabled. Suggest checking with `/memory`.
36 
37### Step 2: Read and analyze MEMORY.md
38 
39Read the full `MEMORY.md` file. Count lines and check against the 200-line startup limit.
40 
41Analyze each entry for:
42 
431. **Recurrence indicators**
44 - Same concept appears multiple times (different wording)
45 - References to "again" or "still" or "keeps happening"
46 - Similar entries across topic files
47 
482. **Staleness indicators**
49 - References files that no longer exist (`find` to verify)
50 - Mentions outdated tools, versions, or commands
51 - Contradicts current CLAUDE.md rules
52 
533. **Consolidation opportunities**
54 - Multiple entries about the same topic (e.g., three lines about testing)
55 - Entries that could merge into one concise rule
56 
574. **Promotion candidates** — entries that meet ALL criteria:
58 - Appeared in 2+ sessions (check wording patterns)
59 - Not project-specific trivia (broadly useful)
60 - Actionable (can be written as a concrete rule)
61 - Not already in CLAUDE.md or `.claude/rules/`
62 
63### Step 3: Read topic files
64 
65If `MEMORY.md` references or the directory contains additional files (`debugging.md`, `patterns.md`, etc.):
66- Read each one
67- Cross-reference with MEMORY.md for duplicates
68- Check for entries that belong in the main file (high value) vs. topic files (details)
69 
70### Step 4: Cross-reference with CLAUDE.md
71 
72Read the project's `CLAUDE.md` (if it exists) and compare:
73- Are there MEMORY.md entries that duplicate CLAUDE.md rules? (→ remove from memory)
74- Are there MEMORY.md entries that contradict CLAUDE.md? (→ flag conflict)
75- Are there MEMORY.md patterns not yet in CLAUDE.md that should be? (→ promotion candidate)
76 
77Also check `.claude/rules/` directory for existing scoped rules.
78 
79### Step 5: Generate report
80 
81Output format:
82 
83```
84📊 Auto-Memory Review
85 
86Memory Health:
87 MEMORY.md: {{lines}}/200 lines ({{percent}}%)
88 Topic files: {{count}} ({{names}})
89 CLAUDE.md: {{lines}} lines
90 Rules: {{count}} files in .claude/rules/
91 
92🎯 Promotion Candidates ({{count}}):
93 1. "{{pattern}}" — seen {{n}}x, applies broadly
94 → Suggest: {{target}} (CLAUDE.md / .claude/rules/{{name}}.md)
95 2. ...
96 
97🗑️ Stale Entries ({{count}}):
98 1. Line {{n}}: "{{entry}}" — {{reason}}
99 2. ...
100 
101🔄 Consolidation ({{count}} groups):
102 1. Lines {{a}}, {{b}}, {{c}} all about {{topic}} → merge into 1 entry
103 2. ...
104 
105⚠️ Conflicts ({{count}}):
106 1. MEMORY.md line {{n}} contradicts CLAUDE.md: {{detail}}
107 
108💡 Recommendations:
109 - {{actionable suggestion}}
110 - {{actionable suggestion}}
111```
112 
113## When to Use
114 
115- After completing a major feature or debugging session
116- When `/si:memory-status` shows MEMORY.md is over 150 lines
117- Weekly during active development
118- Before starting a new project phase
119- After onboarding a new team member (review what Claude learned)
120 
121## Tips
122 
123- Run `/si:memory-review --quick` frequently (low overhead)
124- Full review is most valuable when MEMORY.md is getting crowded
125- Act on promotion candidates promptly — they're proven patterns
126- Don't hesitate to delete stale entries — auto-memory will re-learn if needed
127 
View all files on GitHub →

Details

Updated
Aug 30, 2026
License
MIT
Stars on the repo
★ 26,349
Checked
Source
alirezarezvani/claude-skills ↗
Creator
alirezarezvani · 363 listings
View creator

Similar skills

See all →
SkillExport the Obsidian wiki's knowledge graph to structuredWiki Export — Knowledge Graph ExportAr9av/obsidian-wiki · by Ar9avExport the Obsidian wiki's knowledge graph to structured formats for use in external tools. Use this skill when the user says "export wiki", "export graph", "export to JSON", "export to Gephi", export to Neo4j", "export to Postgres", "export to SQL", "graphml", "visualize wiki", knowledge graph export", "export to OKF", "OKF bundle", "open knowledge format", export as markdown bundle", or wants to use their wiki data in another tool. Outputs graph.json, graph.graphml, cypher.txt (Neo4j), postgres.sql (Postgres), and graph.html (interactive browser visualization) into a wiki-export/ directory at the vault root, plus an optional OKF (Open Knowledge Format) markdown bundle under wiki-export/okf/.★ 3.5k GitHub starsSkillImport a wiki knowledge graph into the current vaultWiki Import — Reconstruct Pages from an ExportAr9av/obsidian-wiki · by Ar9avImport a wiki knowledge graph into the current vault — either from a graph.json export file (stubs) or from an OKF (Open Knowledge Format) markdown bundle (full page bodies). Use this skill when the user says "import wiki", "import from export", "load graph.json", import vault", "import OKF bundle", "import OKF", "load OKF", "import markdown bundle", /wiki-import", or wants to transfer pages from one vault to another using the output of wiki-export.★ 3.5k GitHub starsSkillYour team's shared, AI-ready knowledge base/company-brain — Team-shared AI-ready knowledge basecoreyhaines31/makerskills · by coreyhaines31Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so an agent can answer on your team's behalf. Team-scope sibling to second-brain. Modes — capture, compile (wiki pages + INDEX.md), query (trust-weighted, saved to outputs/), review (verify / deprecate / supersede stale captures), lint, connect, search. Structured raw dirs (people/, companies/, meetings/, sops/, decisions/, customer-language/, sales-objections/). Every capture stamps author, timestamp, and trust status. Optional sync from call transcripts, Slack/email exports, CRM. Vault at ${COMPANY_BRAIN_VAULT:-$HOME/Documents/CompanyBrain}/. Triggers on "/company-brain," "/cb," "capture this into the team brain," "log this meeting," "save this SOP," "compile the company wiki," "query the team brain," "what does the team know about X," "review the company brain," "lint the company brain," "who's the internal expert on X.★ 855 GitHub starsSkillGive Claude a permanent, searchable long-term memoryAI Brain — persistent memory for Claude via ObsidianOotto-AI/claude-content-skills · by Ootto-AIGive Claude a permanent, searchable long-term memory using an Obsidian vault as the store. At the end of a session, summarize what mattered and save it as a Markdown note in your "AI Brain" vault; at the start of a session (or on demand), read back only the relevant past notes. Local markdown you own — connected via the Filesystem MCP. Trigger with "wrap up", "save this session", or "remember this".★ 139 GitHub starsSkillFind prior Claude Code and Codex sessions with an indexed/recall: session memory engineParcha-ai/parcha-skills · by Parcha-aiFind prior Claude Code and Codex sessions with an indexed local search engine, then continue the work, repeat it with fresh inputs, or distill it into a skill. Runs from Claude Code, Codex, or pi; the current index covers Claude Code and Codex transcripts. Use when the user names Recall, says "find that conversation where…", "what did we do last time about…", "continue what we did yesterday on X", "what did codex do on this branch", "turn what we did about Y into a skill", or "remember when you…". Not for searching code (use grep on the repo) or for facts already in MEMORY.md.★ 62 GitHub starsMCPA basic implementation of persistent memory using a localKnowledge Graph Memory Servermodelcontextprotocol/servers · by modelcontextprotocolA basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across…★ 90.5k GitHub stars

More from alirezarezvani

SkillResume a paused experiment/ar:ar-resume — Resume Experimentalirezarezvani/claude-skills · by alirezarezvaniResume a paused experiment. Checkout the experiment branch, read results history, continue iterating. Use when the user runs /ar:ar-resume or asks to pick up a previously started autoresearch experiment.★ 26.3k GitHub starsSkillShow experiment dashboard with results, active loops/ar:ar-status — Experiment Dashboardalirezarezvani/claude-skills · by alirezarezvaniShow experiment dashboard with results, active loops, and progress. Use when the user runs /ar:ar-status or asks how an autoresearch experiment is going.★ 26.3k GitHub starsSkillStart an autonomous experiment loop with user-selected/ar:loop — Autonomous Experiment Loopalirezarezvani/claude-skills · by alirezarezvaniStart an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly). Uses CronCreate for scheduling. Use when the user runs /ar:loop or asks to run an autoresearch experiment continuously on a schedule.★ 26.3k GitHub starsSkillRun a single experiment iteration/ar:run — Single Experiment Iterationalirezarezvani/claude-skills · by alirezarezvaniRun a single experiment iteration. Edit the target file, evaluate, keep or discard. Use when the user runs /ar:run or asks for one manual autoresearch iteration.★ 26.3k GitHub starsSkillSet up a new autoresearch experiment interactively/ar:setup — Create New Experimentalirezarezvani/claude-skills · by alirezarezvaniSet up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator. Use when the user runs /ar:setup or asks to start optimizing a file with the autoresearch loop.★ 26.3k GitHub starsSkill/cs:boardroom <brief/cs:boardroom — Multi-Role Boardroom Deliberationalirezarezvani/claude-skills · by alirezarezvani/cs:boardroom <brief> — 6-phase multi-role deliberation across the C-suite with Phase 2 isolation, critic pre-screen, and synthesis. Outputs a board memo. Use when a decision spans multiple executive domains — e.g. a pricing change touching finance, positioning, and product, or a raise-vs-cut runway call.★ 26.3k GitHub stars