claude-reflect
Execute self-learning system that captures corrections during sessions and syncs them to CLAUDE.md.Use when discussing learnings, corrections, or when the user mentions remembering something.Trigger with phrases like "remember this", "don't forget", "use X not Y", or "actually...".
When & Why to Use This Skill
Claude Reflect is a sophisticated self-learning system designed to capture real-time corrections and insights during AI interactions. By automatically queuing user feedback and syncing it to CLAUDE.md files, it ensures persistent memory of project conventions, preferred tools, and specific instructions, significantly reducing repetitive prompting and improving session-to-session consistency.
Use Cases
- Project Convention Persistence: Automatically update project-specific CLAUDE.md files with newly discovered coding standards or architectural preferences mentioned during a chat session.
- Tool Preference Management: Capture and remember specific tool versions or command-line flags (e.g., 'use gpt-4o for reasoning') to ensure the AI uses the correct environment settings in future tasks.
- Error Correction Loop: Streamline the 'reflect and learn' workflow by scanning session history for missed corrections and applying them to global or local configuration files via the /reflect command.
- Context Optimization: Reduce manual documentation overhead by letting the AI identify and propose its own 'learnings' based on natural language triggers like 'actually', 'don't forget', or 'use X not Y'.
| name | claude-reflect |
|---|---|
| description | | |
| allowed-tools | Read, Write, Edit, Bash(jq:*), Bash(cat:*) |
| version | 1.4.1 |
| license | MIT |
| author | Bayram Annakov <bayram.annakov@gmail.com> |
Claude Reflect - Self-Learning System
A two-stage system that helps Claude Code learn from user corrections.
How It Works
Stage 1: Capture (Automatic)
Hooks detect correction patterns ("no, use X", "actually...", "use X not Y") and queue them to ~/.claude/learnings-queue.json.
Stage 2: Process (Manual)
User runs /reflect to review and apply queued learnings to CLAUDE.md files.
Available Commands
| Command | Purpose |
|---|---|
/reflect |
Process queued learnings with human review |
/reflect --scan-history |
Scan past sessions for missed learnings |
/reflect --dry-run |
Preview changes without applying |
/skip-reflect |
Discard all queued learnings |
/view-queue |
View pending learnings without processing |
When to Remind Users
Remind users about /reflect when:
- They complete a feature or meaningful work unit
- They make corrections you should remember for future sessions
- They explicitly say "remember this" or similar
- Context is about to compact and queue has items
Correction Detection Patterns
High-confidence corrections:
- Tool rejections (user stops an action with guidance)
- "no, use X" / "don't use Y"
- "actually..." / "I meant..."
- "use X not Y" / "X instead of Y"
- "remember:" (explicit marker)
CLAUDE.md Destinations
~/.claude/CLAUDE.md- Global learnings (model names, general patterns)./CLAUDE.md- Project-specific learnings (conventions, tools, structure)
Example Interaction
User: no, use gpt-5.1 not gpt-5 for reasoning tasks
Claude: Got it, I'll use gpt-5.1 for reasoning tasks.
[Hook captures this correction to queue]
User: /reflect
Claude: Found 1 learning queued. "Use gpt-5.1 for reasoning tasks"
Scope: global
Apply to ~/.claude/CLAUDE.md? [y/n]