Claude Reflect
FreeEnhance Claude's memory with user corrections.
Free · Opens the source repo
What Claude Reflect does
Claude Reflect is a self-learning system designed to improve the interaction quality of Claude Code by capturing and processing user corrections. It operates in two stages: the first stage automatically detects correction patterns during user sessions, such as phrases like "use X not Y" or "actually...". These corrections are queued for review in a JSON file, allowing users to systematically capture learnings without interrupting their workflow.
In the second stage, users can manually review the queued corrections by executing the /reflect command. This command allows them to apply changes to the CLAUDE.md files, which can be either global or project-specific. The skill also offers additional commands to scan past sessions for missed learnings, preview changes before applying them, or discard queued learnings altogether. This structured approach ensures that corrections are not only noted but also integrated into future interactions, enhancing the overall efficiency of the coding process.
Claude Reflect is particularly useful for developers and designers who frequently interact with Claude Code and want to ensure that their preferences and corrections are remembered for future sessions. By using this skill, users can create a more personalized experience, reducing the need to repeat instructions and improving the overall effectiveness of their coding sessions.
However, it is important to note that Claude Reflect requires a certain level of familiarity with the Claude environment and its command-line interface. Users who are not comfortable with these tools may find it challenging to leverage the full capabilities of this skill. Additionally, while the skill captures corrections effectively, it relies on user input for the processing stage, meaning that it cannot autonomously learn without user intervention.
When to use it
Use this skill when you want Claude Code to remember specific corrections or preferences for future sessions, especially after completing a feature or making significant changes.
When not to use it
Avoid using this skill if you are not familiar with command-line tools or if you require a fully autonomous learning system without manual intervention.
What you can build with it
Feature Completion
After completing a significant feature, use `/reflect` to ensure all corrections made during development are captured.
Session Review
At the end of a coding session, run `/view-queue` to check what corrections have been captured for future reference.
Discarding Corrections
If you realize that certain corrections are no longer relevant, use `/skip-reflect` to clear the queued learnings.
How to install Claude Reflect
View source1. Install with the skills CLI
npx skills add jeremylongshore/claude-code-plugins-plus-skills/claude-reflect --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by jeremylongshoreClaude 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]
Overview
Execute self-learning system that captures corrections during sessions and syncs them to CLAUDE.
Prerequisites
- Access to the Claude Reflect environment or API
- Required CLI tools installed and authenticated
- Familiarity with Claude Reflect concepts and terminology
Instructions
- Assess the current state of the Claude Reflect configuration
- Identify the specific requirements and constraints
- Apply the recommended patterns from this skill
- Validate the changes against expected behavior
- Document the configuration for team reference
Output
- Configuration files or code changes applied to the project
- Validation report confirming correct implementation
- Summary of changes made and their rationale
Error Handling
| Error | Cause | Resolution |
|---|---|---|
| Authentication failure | Invalid or expired credentials | Refresh tokens or re-authenticate with Claude Reflect |
| Configuration conflict | Incompatible settings detected | Review and resolve conflicting parameters |
| Resource not found | Referenced resource missing | Verify resource exists and permissions are correct |
Examples
Basic usage: Apply claude reflect to a standard project setup with default configuration options.
Advanced scenario: Customize claude reflect for production environments with multiple constraints and team-specific requirements.
Resources
- Official Claude Reflect documentation
- Community best practices and patterns
- Related skills in this plugin pack
Frequently asked questions about Claude Reflect
Similar skills
Skill Creator
Efficiently create and manage skills for Gemini CLI.
Agent Development
Create and manage autonomous agents for Claude Code.
Math Olympiad Solver
Solve and verify competition math problems effectively.
Microsoft Skill Creator
Create specialized skills for Microsoft technologies.
Doublecheck
A verification pipeline for AI-generated claims.
Skill Development for Claude Code
Create and enhance skills for Claude Code plugins.