remember · sneg55 — Claude Code skill: memory review and install
The skill reviews auto-memory alongside project memory files, then suggests what to promote, update, or keep where it is.
npx skills add sneg55/agent-starter --skill remember -a claude-codeWhat remember does
remember reads CLAUDE.md and CLAUDE.local.md, and reviews auto-memory entries available in the agent context. It sorts each entry toward project instructions, personal guidance, team memory, or a note that should remain in auto-memory.
It also checks the memory layers for repeated entries, contradictions, and outdated guidance. The skill returns a report with proposed promotions and cleanup, while raising unclear cases for the user to decide. It does not edit files before the user explicitly approves the proposals.
What it helps with
- Sort auto-memory notes into project or personal instructions
- Spot duplicate entries across memory files
- Find outdated guidance and conflicts between layers
- Prepare memory changes for user review
Example prompts for the agent
- Review this project's auto-memory and suggest entries for
CLAUDE.mdorCLAUDE.local.md. - Compare the memory layers, report duplicates and conflicts, and wait for my approval before editing anything.
How to install remember
1Skills CLI (Vercel)
npx skills add sneg55/agent-starter --skill remember -a claude-code2Manually: put the files in place
~/.claude/skills/remember/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/remember/
1Skills CLI (Vercel)
npx skills add sneg55/agent-starter --skill remember -a codex2Manually: put the files in place
.agents/skills/remember/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add sneg55/agent-starter --skill remember -a cursor2Manually: put the files in place
.cursor/skills/remember/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install sneg55/agent-starter remember2Manually: put the files in place
.github/skills/remember/SKILL.md1Skills CLI (Vercel)
npx skills add sneg55/agent-starter --skill remember -a gemini-cli2Platform CLI
gemini skills install https://github.com/sneg55/agent-starter --path skills/rememberManually: put the files in place
.devin/skills/remember/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add sneg55/agent-starter --skill remember -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about remember
How do I install remember in Claude Code?
Run npx skills add sneg55/agent-starter --skill remember -a claude-code. The skill file is at ~/.claude/skills/remember/SKILL.md.
What does remember do?
It compares auto-memory with CLAUDE.md and CLAUDE.local.md, flags duplicate or outdated notes and conflicts, then presents suggested changes in a report.
Does remember edit memory files automatically?
No. It presents its proposals first and waits for explicit user approval before making changes.
Source text
SKILL.md · MIT
--- name: remember description: Review auto-memory entries and propose promotions to CLAUDE.md, CLAUDE.local.md, or shared memory. Also detects outdated, conflicting, and duplicate entries across memory layers. user_invocable: true when_to_use: Use when you want to review, organize, or promote auto-memory entries. Also useful for cleaning up outdated or conflicting entries across CLAUDE.md, CLAUDE.local.md, and auto-memory. allowed-tools: - Read - Write - Edit - Glob - Grep - Bash --- # Memory Review ## Goal Review the user's memory landscape and produce a clear report of proposed changes, grouped by action type. Do NOT apply changes - present proposals for user approval. ## Steps ### 1. Gather all memory layers Read CLAUDE.md and CLAUDE.local.md from the project root (if they exist). Your auto-memory content is already in your system prompt - review it there. Note which team memory sections exist, if any. **Success criteria**: You have the contents of all memory layers and can compare them. ### 2. Classify each auto-memory entry For each substantive entry in auto-memory, determine the best destination: | Destination | What belongs there | Examples | |---|---|---| | **CLAUDE.md** | Project conventions and instructions for Claude that all contributors should follow | "use bun not npm", "API routes use kebab-case", "test command is bun test", "prefer functional style" | | **CLAUDE.local.md** | Personal instructions for Claude specific to this user, not applicable to other contributors | "I prefer concise responses", "always explain trade-offs", "don't auto-commit", "run tests before committing" | | **Team memory** | Org-wide knowledge that applies across repositories (only if team memory is configured) | "deploy PRs go through #deploy-queue", "staging is at staging.internal", "platform team owns infra" | | **Stay in auto-memory** | Working notes, temporary context, or entries that don't clearly fit elsewhere | Session-specific observations, uncertain patterns | **Important distinctions:** - CLAUDE.md and CLAUDE.local.md contain instructions for Claude, not user preferences for external tools (editor theme, IDE keybindings, etc. don't belong in either) - Workflow practices (PR conventions, merge strategies, branch naming) are ambiguous - ask the user whether they're personal or team-wide - When unsure, ask rather than guess **Success criteria**: Each entry has a proposed destination or is flagged as ambiguous. ### 3. Identify cleanup opportunities Scan across all layers for: - **Duplicates**: Auto-memory entries already captured in CLAUDE.md or CLAUDE.local.md → propose removing from auto-memory - **Outdated**: CLAUDE.md or CLAUDE.local.md entries contradicted by newer auto-memory entries → propose updating the older layer - **Conflicts**: Contradictions between any two layers → propose resolution, noting which is more recent **Success criteria**: All cross-layer issues identified. ### 4. Present the report Output a structured report grouped by action type: 1. **Promotions** - entries to move, with destination and rationale 2. **Cleanup** - duplicates, outdated entries, conflicts to resolve 3. **Ambiguous** - entries where you need the user's input on destination 4. **No action needed** - brief note on entries that should stay put If auto-memory is empty, say so and offer to review CLAUDE.md for cleanup. **Success criteria**: User can review and approve/reject each proposal individually. ## Rules - Present ALL proposals before making any changes - Do NOT modify files without explicit user approval - Do NOT create new files unless the target doesn't exist yet - Ask about ambiguous entries - don't guess
© sneg55 · MIT · sneg55/agent-starter
Similar skills
All skills for Agent setup: memory, context, orchestration →remember by other authors comes first.