| name | setup-memory |
| description | Automatically install, configure, or upgrade ClaudeMemory |
ClaudeMemory Setup & Upgrade
This skill automatically sets up or upgrades ClaudeMemory based on your current state.
What This Skill Does
When invoked, it will:
-
Check current installation status
- Detect installed gem version
- Check database existence and health
- Verify configuration files
-
Determine required action
- Fresh install (no databases)
- Upgrade (version mismatch)
- Verification (already up to date)
-
Execute setup/upgrade automatically
- Run
claude-memory doctor for health check
- Add version markers to
.claude/CLAUDE.md
- Run smoke tests
- Report results
-
Provide next steps
- Restart recommendations if needed
- Usage guidance
Instructions
IMPORTANT: This skill should take action, not just provide instructions.
Step 1: Check Installation Status
gem list claude_memory
claude-memory --version
claude-memory doctor
Analyze the output to determine current state.
- If
gem list shows no claude_memory entry, the gem is not installed.
Guide the user: gem install claude_memory
- If running in plugin mode (
CLAUDE_PLUGIN_ROOT is set), hooks and MCP
are managed by the plugin — only databases and memory instructions need setup.
Step 2: Determine Action Required
- Not installed: Databases don't exist
- Action: Run
claude-memory init (ask user for --global flag preference)
- Installed but outdated: Version marker missing or old
- Action: Run upgrade steps (doctor, add version marker, verify)
- Up to date: All healthy
- Action: Report status only
Step 3: Execute Required Actions
For Fresh Install:
- Ask user: "Install globally only or with project memory? [project/global]"
- Run
claude-memory init (with --global if selected)
- Run
claude-memory doctor to verify
- Add version marker to
.claude/CLAUDE.md
- Report success
For Upgrade:
- Run
claude-memory doctor (auto-runs migrations)
- Add/update version marker in
.claude/CLAUDE.md
- Run
claude-memory stats for smoke test
- Report upgrade complete
For Verification:
- Run
claude-memory doctor
- Confirm version in
.claude/CLAUDE.md
- Report all healthy
Step 4: Report Results
Provide a clear summary:
- ✅ What was done
- 📊 Current status (facts, schema version, etc.)
- 🔄 Next steps (if any)
After Setup/Upgrade
Always remind the user:
- Restart Claude Code if configuration files were modified
- Test memory tools: Try
memory.status or memory.recall "<topic>"
- Use memory-first workflow: Check memory before reading files
What Gets Created
Databases
~/.claude/memory.sqlite3 - Global knowledge (preferences, conventions)
.claude/memory.sqlite3 - Project-specific facts and decisions
Configuration Files
.claude/CLAUDE.md - Workflow instructions for memory-first usage
.claude/settings.json - Hooks for automatic ingestion
.claude.json - MCP server configuration
.claude/rules/claude_memory.generated.md - Published snapshot
Hooks
ClaudeMemory automatically ingests transcripts on these events:
- SessionStart - Catch up on previous session
- Stop - After each response
- SessionEnd - Final ingestion before closing
- PreCompact - Before context summarization
Common Scenarios
Fresh Install
User has never installed ClaudeMemory:
- Ask installation preference (project vs global)
- Run
claude-memory init with appropriate flags
- Verify with
doctor
- Add version marker
- Report success and next steps
Upgrade After Gem Update
User updated gem but not configuration:
- Run
claude-memory doctor (auto-migrates schema)
- Update version marker in
.claude/CLAUDE.md
- Verify with smoke tests
- Report upgrade complete
Verification
User wants to check current status:
- Run
claude-memory doctor
- Run
claude-memory stats
- Check version marker in
.claude/CLAUDE.md
- Report all findings
Troubleshooting Guide
If automatic setup fails, provide these solutions:
Permission Denied
chmod +x $(which claude-memory)
Database Locked
- Close other Claude sessions
- Run
claude-memory recover
Missing Ruby
ClaudeMemory requires Ruby 3.2.0+. Check with:
ruby --version
Hooks Not Working
Re-run setup:
claude-memory init
Memory-First Workflow
After successful setup, always remind users:
- Query memory first:
memory.recall "<topic>"
- Use semantic shortcuts:
memory.decisions, memory.conventions, memory.architecture
- Check before exploring: Memory saves time vs reading files
- Combine knowledge: Merge recalled facts with code exploration
This workflow leverages distilled knowledge from previous sessions.