claude-reflect

Category: Tools & Productivity | Uploader: BayramAnnakov | Downloads: 0 | Version: v1.0（Latest）

Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.

Changelog: Source: GitHub https://github.com/BayramAnnakov/claude-reflect

Directory Structure

Current level: Root

📁 .claude-plugin/
- 📄 marketplace.json 368 B
- 📄 plugin.json 481 B
📁 .github/
- 📁 workflows/
  - 📄 test.yml 1010 B
- 📄 FUNDING.yml 22 B
📁 assets/
- 📄 reflect-demo.jpg 80.1 KB
📁 commands/
- 📄 reflect-skills.md 12.4 KB
- 📄 reflect.md 61.6 KB
- 📄 skip-reflect.md 1.1 KB
- 📄 view-queue.md 4.3 KB
📁 hooks/
- 📄 hooks.json 990 B
📁 scripts/
- 📁 legacy/
  - 📄 capture-learning.sh 5.2 KB
  - 📄 check-learnings.sh 741 B
  - 📄 extract-session-learnings.sh 1.4 KB
  - 📄 extract-tool-rejections.sh 1.0 KB
  - 📄 post-commit-reminder.sh 1.1 KB
- 📁 lib/
  - 📄 __init__.py 39 B
  - 📄 reflect_utils.py 43.2 KB
  - 📄 semantic_detector.py 17.4 KB
- 📄 capture_learning.py 2.7 KB
- 📄 check_learnings.py 1.4 KB
- 📄 compare_detection.py 14.0 KB
- 📄 extract_session_learnings.py 1.1 KB
- 📄 extract_tool_errors.py 5.1 KB
- 📄 extract_tool_rejections.py 1.0 KB
- 📄 post_commit_reminder.py 1.6 KB
- 📄 read_queue.py 291 B
- 📄 session_start_reminder.py 2.0 KB
📁 tests/
- 📄 __init__.py 47 B
- 📄 test_integration.py 16.7 KB
- 📄 test_memory_hierarchy.py 16.4 KB
- 📄 test_reflect_utils.py 41.0 KB
- 📄 test_semantic_detector.py 25.9 KB
- 📄 test_tool_errors.py 12.0 KB
📄 .gitignore 13 B
📄 CHANGELOG.md 9.3 KB
📄 CLAUDE.md 7.6 KB
📄 DISTRIBUTION.md 10.2 KB
📄 LICENSE 1.0 KB
📄 README.md 15.3 KB
📄 RELEASING.md 1.0 KB
📄 SKILL.md 2.4 KB

SKILL.md

---
name: claude-reflect
description: Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.
---

# 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 |
| `/reflect-skills` | Discover skill candidates from repeating patterns |
| `/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)

## Learning Destinations

- `~/.claude/CLAUDE.md` - Global learnings (model names, general patterns)
- `./CLAUDE.md` - Project-specific learnings (conventions, tools, structure)
- `./CLAUDE.local.md` - Personal learnings (machine-specific, gitignored)
- `./.claude/rules/*.md` - Modular rules with optional path-scoping
- `~/.claude/rules/*.md` - Global modular rules
- `~/.claude/projects/<project>/memory/*.md` - Auto memory (low-confidence, exploratory)
- `commands/*.md` - Skill improvements (corrections during skill execution)

## 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]
```

Comments 0

Latest | Hot

Please login before commenting.

No comments yet. Be the first one!

claude-reflect

Directory Structure

SKILL.md

Report

Notice