REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept.
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/leo-lilinxiao-codex-autoresearch)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 codex-autoresearch | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | leo-lilinxiao | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 3,237 | 468,733 | 234,332 | 150,287 | 144,566 |
| 最近代码更新 | 2026年11月19日 | 2026年11月19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 |
leo-lilinxiao 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
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。
Codex
依据开发者 README 和 repo 中的文件夹
GitHub account leo-lilinxiao (person), 8 years old
★ 3,237 stars · code last changed 2026年11月19日
12 scripts that can run on a computer: scripts/autoresearch.py, scripts/run_contributor_gate.sh, scripts/run_skill_e2e.sh, scripts/validate_skill_structure.sh and 8 more
No internet calls found in the scripts
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 0f54c57 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
Files are byte-for-byte the same as on GitHub at commit 0f54c57 · View on GitHub ↗
12 scripts
Once uploaded it runs on Claude’s systems, not on your computer. No need to unzip
All 35 files · 2.7 MB
CITATION.cff1 KBCONTRIBUTING.md3 KBLICENSE1 KBREADME.md9 KBSKILL.md2 KBagents/openai.yaml1 KBdocs/EXAMPLES.md5 KBdocs/GUIDE.md8 KBdocs/INSTALL.md2 KBdocs/i18n/README_DE.md4 KBdocs/i18n/README_ES.md4 KBdocs/i18n/README_FR.md4 KBdocs/i18n/README_JA.md4 KBdocs/i18n/README_KO.md4 KBdocs/i18n/README_PT.md4 KBdocs/i18n/README_RU.md6 KBdocs/i18n/README_ZH.md4 KBimage/autoresearch-report.png116 KBimage/banner.png2.3 MBreferences/background.md2 KBreferences/workflow.md7 KBscripts/autoresearch.py56 KBscripts/autoresearch_core.py46 KBscripts/autoresearch_report.py23 KBscripts/run_contributor_gate.sh1 KBscripts/run_skill_e2e.sh12 KBscripts/validate_skill_structure.sh1 KBtests/e2e-fixtures/counter_reduction/scripts/score.py1 KBtests/e2e-fixtures/counter_reduction/src/value.txt1 KBtests/e2e-fixtures/interactive_unittest_fix/prompt.txt1 KBtests/e2e-fixtures/interactive_unittest_fix/scripts/score.py1 KBtests/e2e-fixtures/interactive_unittest_fix/src/math_utils.py1 KBtests/e2e-fixtures/interactive_unittest_fix/tests/test_math_utils.py1 KBtests/test_autoresearch.py39 KBtests/test_structure.py2 KB+Create skillUpload a skillpick codex-autoresearch.zip
SettingsCapabilitiesCode execution and file creation
Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free
Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)
Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)
Checked against official docs 2026年11月12日 · Source: support.claude.com, support.claude.com, code.claude.com
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /codex-autoresearch,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/leo-lilinxiao/codex-autoresearch.git /tmp/popnx-skill-leo-lilinxiao-codex-autoresearch-0f54c57 && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-leo-lilinxiao-codex-autoresearch-0f54c57/.' ~/.claude/skills/codex-autoresearchChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
把 codex-autoresearch 文件夹放到 ~/.agents/skills/codex-autoresearch
~ 是你的主文件夹($HOME)
不用终端:下载 ZIP,解压后把 codex-autoresearch 文件夹移到 ~/.agents/skills
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/leo-lilinxiao/codex-autoresearch.git /tmp/popnx-skill-leo-lilinxiao-codex-autoresearch-0f54c57 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-leo-lilinxiao-codex-autoresearch-0f54c57/.' ~/.agents/skills/codex-autoresearchChecked against official docs 2026年11月15日 · Source: learn.chatgpt.com
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/leo-lilinxiao/codex-autoresearch.git /tmp/popnx-skill-leo-lilinxiao-codex-autoresearch-0f54c57 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-leo-lilinxiao-codex-autoresearch-0f54c57/.' ~/.agents/skills/codex-autoresearch复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 codex-autoresearch
Checked against official docs 2026年11月12日 · Source: cursor.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/leo-lilinxiao/codex-autoresearch.git /tmp/popnx-skill-leo-lilinxiao-codex-autoresearch-0f54c57 && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-leo-lilinxiao-codex-autoresearch-0f54c57/.' ~/.cursor/skills/codex-autoresearch适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
✓ 命令已检查 2026年11月16日
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
2,549 个字符 · 在 GitHub 打开完整文件
---
name: codex-autoresearch
description: "Run repeated, measured Git experiments toward a numeric target; keep improvements and revert failures. Use for autonomous optimization or managing an autoresearch run, not one-shot edits."
metadata:
short-description: "Run measurable autonomous experiments"
---
# Codex Autoresearch
Improve a repository through repeated, reversible experiments:
`hypothesize -> change -> measure -> learn -> keep or revert -> repeat`
Codex chooses hypotheses and makes code changes. The control script owns measurement, commits, rollback, and the event history.
## Respond To The Request
Resolve `<control>` to this skill's own `scripts/autoresearch.py`; do not assume it is installed in the target repository.
For a status or results request, run the corresponding command directly:
| Request | Command |
|---|---|
| Status | `python3 <control> status --repo <repo>` |
| History | `python3 <control> history --repo <repo>` |
| TSV export | `python3 <control> history --repo <repo> --format tsv` |
| HTML report | `python3 <control> report --repo <repo>` |
Report the requested result without starting or resuming experiments. Return the generated path for an HTML report.
Before starting or resuming an experiment, read the applicable workflow unless it is already in context:
- [Workflow](references/workflow.md): starting, continuing, resuming, or changing an experiment.
- [Background](references/background.md): launching or controlling a detached run.
## Experiment Boundary
- One run owns one Git repository, one numeric metric, one confirmed target, and approved path scopes.
- For a new foreground run, initialize successfully before creating its Goal; the Goal identifies the returned run id. If initialization reports `complete`, no Goal is needed.
- Use `finish` to finalize each coherent experiment. Do not manually commit, revert, or edit run artifacts during an active run.
- Only a verified target can mean `complete`; an iteration limit, error, or external blocker has its own status.
- Validate state through the control script on entry or resume. Use recorded experiments rather than guessing from conversation.
- Surface command and state errors with their diagnostic paths. Never bypass validation, fabricate metrics, or reconstruct missing events.
Foreground continuation belongs to the official Codex Goal. Background continuation belongs to the detached controller. An already launched background worker follows its supplied experiment contract, without starting a new launch flow.
提问、分享技巧或报告无法使用。按“有帮助”数量排序。