REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
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/uditgoenka-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 autoresearch | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | uditgoenka | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 6,845 | 468,733 | 234,332 | 150,287 | 144,566 |
| 最近代码更新 | 2026年10月31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 |
uditgoenka 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。
Claude CodeCodexOpenCode
依据开发者 README 和 repo 中的文件夹
GitHub account uditgoenka (person), 14 years old
★ 6,845 stars · code last changed 2026年10月31日
2 scripts that can run on a computer: scripts/orchestrate.sh, scripts/score-regression.sh
Scripts that go online: scripts/orchestrate.sh
Installing the maker’s way adds hooks that run without you asking: run every time the AI edits a file · run every time you send a message · run on the SubagentStart event · run every time a chat starts · run every time a chat closes
Checked automatically from the repo files at commit 7bddd05 (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 7bddd05 · View on GitHub ↗
2 scripts
Once uploaded it runs on Claude’s systems, not on your computer. No need to unzip
All 10 files · 75 KB
SKILL.md10 KBreferences/behavior-preserving-optimization.md3 KBreferences/fork-and-flush.md8 KBreferences/orchestrator-routing.md7 KBreferences/predict-personas.md3 KBreferences/reason-judge-protocol.md3 KBreferences/security-checklist.md3 KBscripts/orchestrate.sh29 KBscripts/score-regression.sh8 KBLICENSE1 KB+Create skillUpload a skillpick 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 /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。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
npx skills add uditgoenka/autoresearch摘自开发者 README,会下载并运行开发者的代码
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/uditgoenka/autoresearch.git /tmp/popnx-skill-uditgoenka-autoresearch-7bddd05 && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-uditgoenka-autoresearch-7bddd05/claude-plugin/skills/autoresearch' ~/.claude/skills/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 autoresearch 文件夹放到 ~/.agents/skills/autoresearch
~ 是你的主文件夹($HOME)
不用终端:下载 ZIP,解压后把 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/uditgoenka/autoresearch.git /tmp/popnx-skill-uditgoenka-autoresearch-7bddd05 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-uditgoenka-autoresearch-7bddd05/claude-plugin/skills/autoresearch' ~/.agents/skills/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/uditgoenka/autoresearch.git /tmp/popnx-skill-uditgoenka-autoresearch-7bddd05 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-uditgoenka-autoresearch-7bddd05/claude-plugin/skills/autoresearch' ~/.agents/skills/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 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/uditgoenka/autoresearch.git /tmp/popnx-skill-uditgoenka-autoresearch-7bddd05 && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-uditgoenka-autoresearch-7bddd05/claude-plugin/skills/autoresearch' ~/.cursor/skills/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
显示前 8,000 个字符 · 在 GitHub 打开完整文件
---
name: autoresearch
description: "Autonomous iteration loop: modify, verify, keep/discard against any metric"
version: 2.3.0
---
# Autoresearch — Autonomous Goal-directed Iteration
## Safety Invariants (all subcommands)
- Never push, publish, or deploy without explicit user approval.
- Bounded by default. Override with `Iterations: unlimited`.
- All results logged to `autoresearch/{subcommand}-{YYMMDD}-{HHMM}/` directory.
- Chain handoff via `handoff.json`. Evals reads `*-results.tsv`.
## Dispatch (bare `/autoresearch`)
Parse the invocation in this order:
| Condition | Mode |
|---|---|
| `Metric:` or `Verify:` present | **Classic** — existing metric loop, unchanged |
| Free-form natural-language goal, no metric/verify | **Orchestrator** — see Orchestrator section |
| Nothing | **Setup wizard** — interactive config builder |
| `--classic` flag | Force Classic regardless of goal text |
| `--auto` flag | Force Orchestrator regardless of goal text |
Print a banner on every invocation: `[autoresearch] mode: classic | orchestrator | wizard`.
## Subcommands
| Command | Does | Default Iterations |
|---|---|---|
| `/autoresearch` | Iterate against a metric: modify → verify → keep/discard | 25 |
| `/autoresearch:plan` | Convert a goal into validated Scope, Metric, Verify config | N/A |
| `/autoresearch:debug` | Hunt bugs: hypothesize → test → falsify → repeat | 15 |
| `/autoresearch:fix` | Crush errors one-by-one until zero remain | 20 |
| `/autoresearch:security` | STRIDE + OWASP audit with red-team personas | 15 |
| `/autoresearch:ship` | Ship through 8 phases: checklist → dry-run → deploy → verify | N/A |
| `/autoresearch:scenario` | Generate edge cases across 12 dimensions | 20 |
| `/autoresearch:predict` | 5 expert personas debate before implementation | N/A |
| `/autoresearch:learn` | Scout codebase → generate docs or wiki → validate → fix loop | 10 |
| `/autoresearch:reason` | Adversarial debate with blind judges until convergence | 8 |
| `/autoresearch:probe` | 8 personas interrogate requirements until saturation | 15 |
| `/autoresearch:improve` | Research ICP challenges, discover improvements, generate PRDs | 15 |
| `/autoresearch:evals` | Analyze iteration results: trends, plateaus, regressions | N/A |
| `/autoresearch:regression` | Regression stability gate: baseline vs candidate, verdict STABLE/UNSTABLE | N/A |
### Subcommand routing
To run a subcommand yourself (an orchestrator hop or a `--chain` target), Read its protocol file and follow it:
`../../commands/autoresearch/<name>.md` (relative to this skill's directory), or `../../commands/autoresearch.md` for the classic loop.
The commands are user-typed only, so the model loads them from here instead of invoking them.
## Universal Flags
| Flag | Applies To | Purpose |
|---|---|---|
| `Iterations: N` | All looping | Set iteration count |
| `Iterations: unlimited` | All looping | Opt-in unbounded |
| `--evals` | All looping | Mid-loop checkpoints + final summary |
| `--evals-interval N` | All looping | Override checkpoint frequency |
| `--chain <targets>` | All | Sequential handoff after completion |
| `--<subcommand>` | All | Shorthand for `--chain <subcommand>` |
| `--dry-run` | Orchestrator | Print derived config + planned pipeline; no execution |
| `--max-cycles N` | Orchestrator | Hard ceiling on orchestration cycles (default 50) |
| `--classic` | Bare `/autoresearch` | Force Classic metric-loop mode |
| `--auto` | Bare `/autoresearch` | Force Orchestrator mode |
| `--no-fork` | Metric loops | Disable fork-and-flush rounds |
| `Forks: K` | Metric loops | Branches per fork-and-flush round (default 4; 2 when Verify is slow or uses a shared resource) |
| `Guided: R` | Metric loops | Fraction of fork branches given an Advisor-assigned experiment (default 0.5; 0 = all random) |
## Getting Unstuck: Fork-and-Flush
Metric loops run fork-and-flush rounds on a fixed schedule: at 33% and 66% of the budget, plus early when 5
iterations pass with no `keep`. A round forks K fresh-context branches from the best commit so far, runs each
for a small budget, and keeps the winner. A fresh context means the files and results log only, with none of
the leader's reasoning. Half the branches (by default) are random and pick their own ideas; the other half are
guided, each given one distinct experiment by a stateless Advisor that reads the results log. Protocol:
`references/fork-and-flush.md` (arXiv:2610.07447, arXiv:2610.07625).
## Orchestrator
Activated when a plain-language goal is given without `Metric:`/`Verify:`. Classifies the goal into a **Goal archetype** — see `references/orchestrator-routing.md` for the archetype table and router decision table.
Resolve every `scripts/...` path below relative to this installed skill directory, never relative to the caller's working directory.
For performance, latency, throughput, runtime, CPU, memory, allocations, binary
size, power, energy, bandwidth, or compute-cost goals, read
`references/behavior-preserving-optimization.md`. The working metric ranks
candidates; independent behavior evidence decides whether a candidate survives.
**Two modes based on archetype:**
- **Orchestration loop** — predicate-bearing archetypes (ship-ready, optimize-metric, fix-broken, harden, build-feature, explore). Goal has a mechanical Success predicate; the loop runs until that predicate is met.
- **Single-pass dispatch** — subjective/terminal archetypes (document, what-to-build, decide-design). Routes once to the fitting subcommand (learn / improve / reason), lets it self-terminate, then reports. No loop, no Plateau, no ship gate.
### Orchestration Loop Steps
Backed by `scripts/orchestrate.sh` (deterministic seam — all routing logic lives there). Subcommands exposed: `classify`, `next-hop`, `units`, `plateau`, `screen-cmd`, `verdict`, `validate-state`, `screen-state-predicate`.
1. **Classify** — `scripts/orchestrate.sh classify "<goal>"` → archetype label + mode.
2. **Derive predicate** — reuse `plan` logic to produce a concrete Success predicate: exact shell command + expected output. For `optimize-metric`, run the full plan/wizard derivation internally.
3. **Confirm** — ONE `AskUserQuestion` showing: archetype, mode, concrete predicate (command + expected output), terminal choice (stop-at-verified vs proceed-to-ship). Misclassifications are caught here, not mid-run.
4. **Round-0 dry-run** — prove the predicate command runs and returns a value; safety-screen every derived command via `screen-cmd`; print projected cycle budget. Stop here if `--dry-run`.
5. **Loop** until predicate satisfied:
a. Assess state via cheap signals (last `handoff.json`, regression verdict, error count) + affected-test verify.
b. `scripts/orchestrate.sh next-hop orchestrator-state.json` → next subcommand.
c. Run subcommand via Subcommand routing (its own bounded inner loop).
d. Record per-hop outcome ∈ {progressed, no-op, failed, blocked}.
e. Fold hop's `handoff.json` into `orchestrator-state.json`.
f. `scripts/orchestrate.sh units` → recompute **Units remaining** and append the number or `unknown` to the state's `units_remaining` array.
6. **Stop conditions** (checked after each hop):
- Predicate met → ship gate (only if ship is in the pipeline) else `CONVERGED`.
- Cycles > ceiling (default 50, override `--max-cycles N`) → stop + report `CEILING`. Checked first: a reached ceiling is never extended by fork rounds.
- `scripts/orchestrate.sh plateau orchestrator-state.json` → exit 0 (flat): unless `--no-fork` or `fork_rounds_since_progress` is already 2, run one fork-and-flush round from the incumbent (`references/fork-and-flush.md`), add 1 to `fork_rounds_since_progress`, and continue; otherwise stop + report `PLATEAU`. Exit 1: continue. Exit 3: stop + report `BLOCKED`.
- Hop outcome `blocked`/`failed` with no alternative route → checkpoint + stop + report `BLOCKED`.
### Orchestrator State
`orchestrator-state.json` — orchestrator-owned, additive. Tracks: goal,提问、分享技巧或报告无法使用。按“有帮助”数量排序。