Claude reflect
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.From its SKILL.md
npx -y skills add BayramAnnakov/claude-reflectAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
2.4 KB, 570 tokens by cl100k_base, as published. Nobody here has run it
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]
What ships with it: 38 files
417.1 KB alongside SKILL.md, 23 of them executable
.claude-plugin/
- marketplace.json368 B
- plugin.json481 B
assets/
- reflect-demo.jpg80.1 KB
commands/
- reflect.md61.6 KB
- reflect-skills.md12.4 KB
- skip-reflect.md1.1 KB
- view-queue.md4.3 KB
hooks/
- hooks.json990 B
scripts/
- capture_learning.pyruns2.7 KB
- check_learnings.pyruns1.4 KB
- compare_detection.pyruns14.0 KB
- extract_session_learnings.pyruns1.1 KB
- extract_tool_errors.pyruns5.1 KB
- extract_tool_rejections.pyruns1.0 KB
- legacy/capture-learning.shruns5.2 KB
- legacy/check-learnings.shruns741 B
- legacy/extract-session-learnings.shruns1.4 KB
- legacy/extract-tool-rejections.shruns1.0 KB
- legacy/post-commit-reminder.shruns1.1 KB
- lib/__init__.pyruns39 B
- lib/reflect_utils.pyruns43.2 KB
- lib/semantic_detector.pyruns17.4 KB
- post_commit_reminder.pyruns1.6 KB
- read_queue.pyruns291 B
- session_start_reminder.pyruns2.0 KB
tests/
- __init__.pyruns47 B
- test_integration.pyruns16.7 KB
- test_memory_hierarchy.pyruns16.4 KB
- test_reflect_utils.pyruns41.0 KB
- test_semantic_detector.pyruns25.9 KB
- test_tool_errors.pyruns12.0 KB
- CHANGELOG.md9.3 KB
- CLAUDE.md7.6 KB
- DISTRIBUTION.md10.2 KB
- .gitignore13 B
- LICENSE1.0 KB
- README.md15.3 KB
- RELEASING.md1.0 KB