REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
This repo is a collection of 16 skills
Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/vstorm-co-pydantic-deepagents)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 pydantic-deepagents | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | vstorm-co | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 16 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 1,122 | 467,235 | 234,125 | 149,873 | 144,332 |
| 最近代码更新 | 2026年10月30日 | 2026年11月18日 | 2026年4月20日 | 2026年11月18日 | 2026年11月18日 |
| 许可证 | MIT | MIT | – | Apache-2.0 | MIT |
vstorm-co 提供的 16 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
Install only the ones you use. Open a skill to see how to install it
If you want every one, let the AI install them in one go. Know 2 things first
Uploading to Claude on the web and apps: you need 16 uploads, one ZIP per skill. Open each skill in the list below to download it
Checked against official docs 2026年11月12日 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com
Building, compiling, and resolving dependency issues across languages
Review Python code for quality, security, and best practices
Comprehensive data analysis skill for CSV files using Python and pandas
Working with diverse data formats: binary, text, structured, and custom
Best practices for creating research diagrams with Excalidraw MCP tools
Systematic exploration of unknown environments before starting work
Git operations: commits, branches, PRs, and conflict resolution
Writing efficient code that handles large data and tight constraints
Refactor code to improve structure and maintainability
Guidelines for writing well-structured, cited research reports
Best practices for systematic research, source evaluation, and evidence gathering
Create new reusable skills from conversation context
Systematic approach to diagnosing and fixing errors
Generate pytest test cases for Python functions and classes
Generate comprehensive test suites for existing code
Thorough verification of completed work before declaring done
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
Claude Code
依据开发者 README 和 repo 中的文件夹
This repo has 16 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP
提问、分享技巧或报告无法使用。按“有帮助”数量排序。