reflection

仓库创建 2025年7月18日最近提交 6 小时前SkillHot 收录 20 天前

▸ 精选理由

帮助持续优化 agent 指令与团队协作质量。

这个 Skill 做什么

分析会话并改进 CLAUDE.md 指令与协作流程。

把一次开发或对话会话复盘，抽取可落地的学习要点并用来改进 CLAUDE.md 的指令和协作流程。当你想把聊天记录变成改进项、修正提示工程或提升 AI 与人的配合效率时会用。提供速评和深度两种模式：速评快速给出 CLAUDE.md 改进，深度模式做全面分析并捕获更多经验。

▸ 展开 SKILL.md 英文原文

Analyze development sessions, capture learnings, and improve Claude Code instructions. Use when the user wants to reflect on a session, improve CLAUDE.md, extract learnings, or optimize AI-human collaboration. Supports two modes: quick (default) focuses on CLAUDE.md improvements, deep mode performs comprehensive session analysis with learning capture.

Skill 开发管理会话分析反思指令优化Claude Code

1.6k

Stars

242

Forks

仓库内 Skill

+33

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/feiskyer/claude-code-settings/main/skills/reflection/SKILL.md

或 curl 直取 SKILL.md

curl -fsSL "https://raw.githubusercontent.com/feiskyer/claude-code-settings/main/skills/reflection/SKILL.md"

SKILL.MD 节选查看完整文件 ↗

# Reflection

Analyze the current session and improve Claude Code instructions. Operates in two modes based on user input.

## Mode Selection

- **Quick mode** (default): Triggered by `/reflection` or `/reflection quick`. Focuses on analyzing chat history to identify and implement improvements to CLAUDE.md instructions.
- **Deep mode**: Triggered by `/reflection deep` or `/reflection comprehensive`. Performs a full session analysis covering problems solved, patterns established, user preferences, system understanding, and knowledge gaps, then updates CLAUDE.md accordingly.

Determine the mode from the user's input. If no mode is specified, use Quick mode. If the user says "deep", "comprehens

via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有