reflect
Analyzes conversation transcripts to extract user corrections, patterns, and preferences, then proposes skill improvements. Use this skill when users provide corrections, express preferences about code style, or when patterns emerge from successful approaches. Can be triggered manually with /reflect or automatically at session end when enabled.
When & Why to Use This Skill
The Reflect skill is an advanced self-improvement mechanism for Claude agents designed to optimize performance through continuous learning. It meticulously analyzes conversation transcripts to extract user corrections, stylistic preferences, and successful behavioral patterns. By implementing a 'correct once, never again' logic, it automatically proposes updates to existing skills, ensuring the agent's output aligns perfectly with specific user requirements and project standards over time.
Use Cases
- Automated Skill Refinement: Extracting specific corrections from a debugging session to update the agent's internal logic, preventing the recurrence of the same mistakes.
- Personalized Coding Standards: Learning and applying a user's unique code style and architectural preferences across different projects without manual configuration.
- Knowledge Base Evolution: Identifying successful problem-solving patterns in complex tasks and formalizing them into 'Best Practices' for the agent's future reference.
- Session-End Optimization: Using the automatic reflection mode to summarize key takeaways from a long development session and update the agent's context for the next interaction.
| name | reflect |
|---|---|
| description | > |
Reflect - Self-Improving Skills
Overview
This skill enables Claude Code to learn from conversations by analyzing corrections, approvals, and patterns, then proposing updates to relevant skills. It implements a "correct once, never again" learning system.
Usage Modes
1. Manual Reflection (/reflect)
Trigger analysis of the current conversation:
/reflect [skill-name]
- Without skill-name: Analyzes all skills used in conversation
- With skill-name: Focuses on specific skill
2. Automatic Reflection
When enabled via /reflect-on, runs automatically at session end via Stop hook.
3. Toggle Commands
/reflect-on- Enable automatic reflection/reflect-off- Disable automatic reflection/reflect-status- Show current configuration
Confidence Levels
HIGH - Explicit corrections:
- User contradicts Claude's approach with specific alternative
- Pattern: "Don't do X, do Y instead"
- Action: Direct updates with deprecation warnings
MEDIUM - Approvals and patterns:
- User approves specific approach
- Pattern succeeds multiple times
- Action: Add to "Best Practices" section
LOW - Observations:
- User questions or suggests alternatives
- Pattern: "Have you considered..." or "Why not try..."
- Action: Add to "Considerations" section
Workflow
- Signal Detection - Scan transcript for corrections/patterns
- Context Analysis - Extract 5-message context around signals
- Skill Mapping - Match signals to relevant skills
- Change Proposal - Generate diff of proposed updates
- User Review - Interactive approval with natural language editing
- Application - Safe YAML/markdown updates with backups
- Git Commit - Automatic commit with descriptive message
Scripts
Core Engine
scripts/reflect.py- Main orchestration logicscripts/extract_signals.py- Pattern detection enginescripts/update_skill.py- Safe skill file updatesscripts/present_review.py- Interactive review interface
Automation
scripts/hook-stop.sh- Stop hook integrationscripts/toggle-on.sh- Enable auto-reflectionscripts/toggle-off.sh- Disable auto-reflectionscripts/toggle-status.sh- Show status
Safety Features
- Timestamped backups before all edits
- YAML validation before writing
- Lock files prevent concurrent runs
- Graceful error handling with rollback
- Git status checks before commits
References
See references/signal-patterns.md for detailed pattern library.