claude-reflect
仓库创建 2026年1月4日最近提交 4 个月前SkillHot 收录 21 天前
▸ 精选理由
能让 Claude 从会话纠正中迭代学习,适合长期训练与定制化改进。
▸ 风险提示
会将更正写入本地文件(如 ~/.claude/...),可能记录敏感会话内容。
这个 Skill 做什么
会话自学习系统,捕捉用户更正并提醒运行 /reflect 将更正写入 CLAUDE.md。
会话中自动捕捉用户的更正与偏好,把疑似更正放入学习队列,用户运行 /reflect 时再人工审核并写入 CLAUDE.md。适合长期与 Claude 交互、希望模型记住约定或修正行为的场景。特点是把即时纠正变成可控的两阶段学习流程,既能记忆又能人工把关。
▸ 展开 SKILL.md 英文原文
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.
1.3k
Stars
109
Forks
1
仓库内 Skill
+59
7 日增星
安装 / 使用
给你的 Agent 一句话(通用)
帮我安装这个 skill:https://raw.githubusercontent.com/BayramAnnakov/claude-reflect/main/SKILL.md或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/BayramAnnakov/claude-reflect/main/SKILL.md"SKILL.MD 节选查看完整文件 ↗
# 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 cavia SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有