What makes Huo15 Autoresearch Loop notable?

1.2K downloads. Trust evidence available

How should Huo15 Autoresearch Loop be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Huo15 Autoresearch Loop

基于 Karpathy 自主研究循环的 OpenClaw Skill，Modify → Verify → Keep/Discard → Repeat forever Skill: Huo15 Autoresearch Loop Owner: zhaobod1 Summary: 基于 Karpathy 自主研究循环的 OpenClaw Skill，Modify → Verify → Keep/Discard → Repeat forever Tags: latest:1.0.3 Version history: v1.0.3 | 2026-04-24T04:15:23.163Z | auto No file changes detected for this version. - No updates or changes were made in version 1.0.3. - The skill contents remain identical to the previous version (1.0.2). v1.0.2 | 2026-04-23T03:21:34.748Z | us

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 11, 2026

Version

1.0.3

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.2K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.3release · observed Apr 24, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17f6q72skfgyjycm2frgdc8dn83v5mk:huo15-autoresearch-loop

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-zhaobod1-huo15-autoresearch-loop/snapshot"

Documentation

CLAWHUB

12,004 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: huo15-autoresearch-loop
version: 1.0.2
aliases:
  - 火一五自动迭代
  - 火一五自动循环
  - 自动迭代循环
description: 基于 Karpathy 自主研究循环的 OpenClaw Skill，Modify → Verify → Keep/Discard → Repeat forever
---

# huo15-autoresearch-loop

> 基于 [uditgoenka/autoresearch](https://github.com/uditgoenka/autoresearch)（Karpathy 自主研究循环）的 OpenClaw Skill 实现。

## 触发词

- 自动迭代
- autoresearch
- 跑起来别停
- 自动循环

## 功能

实现 Karpathy 的 **Modify → Verify → Keep/Discard → Repeat forever** 自主研究循环。

## 核心流程

1. 用户说「自动迭代 [目标] [验证命令]」
2. 初始化状态（目标/验证命令/迭代次数/范围）
3. 循环：
   - 修改代码/文件
   - 调用验证命令
   - 成功 → git commit + 记录
   - 失败 → git revert
   - 判断是否继续（迭代次数/收敛检测）
4. 输出摘要

## 使用方式

```
自动迭代 [目标描述] [验证命令]
```

示例：
```
自动迭代 优化性能瓶颈 make test
自动迭代 修复所有lint错误 ./scripts/lint.sh
```

## 配置说明

`config.json` 控制循环行为：

```json
{
  "max_iterations": 50,
  "verify_command": "",
  "scope_globs": ["**/*.py", "**/*.js"],
  "convergence_threshold": 3,
  "commit_each_success": true,
  "revert_on_fail": true
}
```

## 非侵入设计

- 只通过 `exec` 调用脚本
- 不修改 OpenClaw 内核
- 状态持久化在本地文件

## 状态文件

每次迭代的状态保存在 `~/.openclaw/tmp/autoresearch-loop-state.json`：

```json
{
  "goal": "优化性能",
  "verify_command": "make test",
  "iteration": 5,
  "successes": 3,
  "failures": 2,
  "last_success": "2026-04-22T00:30:00Z",
  "history": [...]
}
```

## 停止条件

- 达到 `max_iterations`
- 连续失败超过 `convergence_threshold`
- 用户发送「停止迭代」
- 收敛检测（连续 N 次成功）

## version

1.0.0

_meta.json

{
  "ownerId": "kn7byevkn40d6z4p7ghdb097z983tj33",
  "slug": "huo15-autoresearch-loop",
  "version": "1.0.3",
  "publishedAt": 1777004123163
}

skill-card.md

## Description:

Runs an OpenClaw autonomous iteration loop that modifies files, verifies the result, keeps successful changes, and discards failed changes.

This skill is ready for commercial/non-commercial use.

## Publisher:

[zhaobod1](https://clawhub.ai/user/zhaobod1)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and engineers use this skill to run repeated code-change and verification cycles against a stated goal and verification command.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill can run arbitrary shell commands and may commit, reset, or delete repository changes.

Mitigation: Review the task and verification command before execution, use a disposable or clean Git worktree, and avoid repositories with uncommitted or sensitive files.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/zhaobod1/skills/huo15-autoresearch-loop)
- [uditgoenka/autoresearch](https://github.com/uditgoenka/autoresearch)

## Skill Output:

**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]

**Output Format:** [Terminal text, Markdown summaries, shell commands, local state JSON, and git commits when configured]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Uses a caller-supplied goal, verification command, iteration limits, scope globs, and local state files.]

## Skill Version(s):

1.0.3 (source: server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

config.json

{
  "name": "huois-autoresearch-loop",
  "version": "1.0.0",
  "description": "Karpathy 自主研究循环 - Modify → Verify → Keep/Discard → Repeat forever",
  "max_iterations": 50,
  "verify_command": "",
  "scope_globs": ["**/*.py", "**/*.js", "**/*.ts"],
  "convergence_threshold": 3,
  "commit_each_success": true,
  "revert_on_fail": true,
  "state_file": "~/.openclaw/tmp/autoresearch-loop-state.json",
  "log_file": "~/.openclaw/tmp/autoresearch-loop.log"
}

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.