本文へ移動
cccskills
無料GitHub で公開

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.

BayramAnnakov/claude-reflect
インストール方法を見る

含まれるファイル（51）

  • SKILL.md2.4 KB
  • .claude-plugin/marketplace.json590 B
  • .claude-plugin/plugin.json481 B
  • .github/FUNDING.yml22 B
  • .github/workflows/test.yml1010 B
  • .gitignore122 B
  • assets/reflect-demo.jpg80.1 KB
  • assets/reflect-mod-band.png38.0 KB
  • BACKLOG.md10.1 KB
  • CHANGELOG.md17.7 KB
  • CLAUDE.md7.6 KB
  • commands/reflect-skills.md12.6 KB
  • commands/reflect.md63.7 KB
  • commands/skip-reflect.md997 B
  • commands/view-queue.md4.3 KB
  • DISTRIBUTION.md10.2 KB
  • hooks/hooks.json990 B
  • LICENSE1.0 KB
  • mod/.claude-plugin/plugin.json461 B
  • mod/hooks/hooks.json34 B
  • mod/hooks/reflect.test.tsx10.7 KB
  • mod/hooks/register.tsx17.3 KB
  • mod/README.md4.0 KB
  • mod/types/index.d.ts956 B
  • README.md17.9 KB
  • RELEASING.md1.0 KB
  • scripts/capture_learning.py3.6 KB
  • scripts/check_learnings.py1.5 KB
  • scripts/clear_queue.py704 B
  • scripts/compare_detection.py14.0 KB
  • scripts/extract_session_learnings.py1.1 KB
  • scripts/extract_tool_errors.py5.1 KB
  • scripts/extract_tool_rejections.py1.0 KB
  • scripts/legacy/capture-learning.sh5.2 KB
  • scripts/legacy/check-learnings.sh741 B
  • scripts/legacy/extract-session-learnings.sh1.4 KB
  • scripts/legacy/extract-tool-rejections.sh1.0 KB
  • scripts/legacy/post-commit-reminder.sh1.1 KB
  • scripts/lib/__init__.py39 B
  • scripts/lib/reflect_utils.py73.8 KB
  • scripts/lib/semantic_detector.py17.4 KB
  • scripts/post_commit_reminder.py1.7 KB
  • scripts/project_paths.py2.2 KB
  • scripts/read_queue.py291 B
  • scripts/session_start_reminder.py2.0 KB
  • tests/__init__.py47 B
  • tests/test_integration.py17.3 KB
  • tests/test_memory_hierarchy.py60.0 KB
  • tests/test_reflect_utils.py53.8 KB
  • tests/test_semantic_detector.py25.9 KB
  • tests/test_tool_errors.py12.0 KB

SKILL.md（原文）

インストールする前に、エージェントに与えられる指示の中身を確認できます。

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

CommandPurpose
/reflectProcess queued learnings with human review
/reflect --scan-historyScan past sessions for missed learnings
/reflect --dry-runPreview changes without applying
/reflect-skillsDiscover skill candidates from repeating patterns
/skip-reflectDiscard all queued learnings
/view-queueView 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]

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

ログインしてレビューを書く
このスキルの問題を報告する