给SkillAdam一个技能，告诉它你想改进什么。 它测试你在相关任务上的SKILL.md，从结果中学习，并在更新文件前检查拟议的更改。

支持平台：Codex ·Claude Code ·光标代理 ·GitHub Copilot。

• 提升工作流程中的技能。 描述你的目标，并举例说明你的技能应当处理的任务。
• 从早期尝试中学习。 利用之前修订的反馈指导下一步改进并纠正反复出现的错误。
• 进行有针对性的修改。 调整每次修订的范围，保留通过评估的修改。
• 保持在你偏好的代理中。 在你已经使用的代理中开始优化，并可选择审查单个编辑。

演示 · 快速入门 · 使用情况 · 引用

新闻

• [2026.09.08] 我们的论文《SkillAdam：智能体的稳定高效技能演进》现已在arXiv上发布。
• [2026.09] SkillAdam 已发布，集成了 Codex、Claude Code、Cursor Agent 和 GitHub Copilot 的集成。

演示

https://github.com/user-attachments/assets/a15049ee-90b5-4cda-a270-7628a60f76ed

快速启动

要求

• **Python 3。

SkillAdam: Better Skills for Your AI Agent

Give SkillAdam a skill and tell it what you want to improve. It tests your SKILL.md on relevant tasks, learns from the results, and checks proposed changes before updating the file.

Supported platforms: Codex · Claude Code · Cursor Agent · GitHub Copilot.

• Improve skills for your workflow. Describe your goal and provide examples of tasks your skill should handle.

• Learn from earlier attempts. Use feedback from previous revisions to guide the next improvement and address recurring mistakes.

• Make measured changes. Adapt the scope of each revision and keep changes that pass evaluation.

• Stay in your preferred agent. Start an optimization in the agent you already use, with the option to review individual edits.

  Demo · Quick Start · Usage · Citation

News

• [2026.09.08] Our paper, SkillAdam: Stable and Efficient Skill Evolution for Agents, is now available on arXiv.
• [2026.09] SkillAdam is released with integrations for Codex, Claude Code, Cursor Agent, and GitHub Copilot.

Demo

https://github.com/user-attachments/assets/a15049ee-90b5-4cda-a270-7628a60f76ed

Quick Start

Requirements

• Python 3.10+, with pip and venv, and Git.
• Your chosen agent’s CLI, installed, signed in, and available on your PATH: codex, claude, cursor-agent, or copilot.
• For Copilot’s default VS Code integration, the code CLI is also required. For Copilot CLI only, pass --skip-vscode-registration to its installer.

Cursor requires the Cursor Agent CLI; the desktop app alone is insufficient.

The default setup uses your existing agent sign-in and needs no local GPU, Docker, or separate model API key. Model calls consume your platform account’s quota, and skill and task content is sent to the configured model provider.

Installation

Clone this repository: