← 返回 Skills 市场

Auto Research Agent

Name: Auto Research Agent
Author: tyronecoh

作者 TyroneMok · GitHub ↗ · v1.0.2 · MIT-0

linux ✓ 安全检测通过

128

总下载

当前安装

版本数

在 OpenClaw 中安装

/install gpu-research

功能描述

A reference framework for understanding autonomous AI research pipelines. Learn how AI can optimize ML training with fixed time budgets and metric-driven ite...

使用说明 (SKILL.md)

\r \r

AutoResearch Framework\r

\r A reference guide for understanding how autonomous AI research works. This skill documents the methodology from karpathy/autoresearch for educational purposes.\r \r

What This Is\r

\r This skill does NOT run any code. It serves as a reference for understanding:\r \r

Fixed time budget experiments (5 minutes)\r
Metric-driven iteration (val_bpb)\r
Single-file training scope\r
Self-contained ML training setup\r \r

Key Concepts\r

\r | Concept | Description |\r |---------|------------|\r | val_bpb | Validation bits per byte — lower is better |\r | Fixed Budget | Experiments run for exactly 5 minutes |\r | Single Scope | One file to modify per experiment |\r \r

Architecture Overview\r

\r The framework consists of three files:\r \r | File | Purpose |\r |------|---------|\r | prepare.py | Data preparation (do not modify) |\r | train.py | Model training loop reference |\r | program.md | Research strategy template |\r \r

Design Patterns\r

Fixed time budget: Makes experiments directly comparable\r
Single file scope: Keeps changes manageable\r
Metric-driven: Uses val_bpb to compare results\r \r

For Educational Use\r

\r This skill is a reference implementation based on karpathy/autoresearch by Andrej Karpathy. It demonstrates autonomous research methodologies used in modern AI development.\r \r

Inspiration\r

\r Based on karpathy/autoresearch by Andrej Karpathy.\r

安全使用建议

This appears to be a harmless, read-only educational guide. Before installing, consider: (1) If you expected runnable example code, note that the referenced files are not included—the skill is documentation-only. (2) The declared dependency on python3 is unnecessary for pure documentation but not harmful. (3) Because the skill can be invoked by the agent, review the SKILL.md to confirm it contains only the documentation you expect; if you need runnable experiments, obtain the code from the original karpathy/autoresearch repository and verify it separately.

能力评估

ℹ Purpose & Capability

The skill's name/description match the SKILL.md content (an educational reference about autoresearch). However, the manifest claims three files (prepare.py, train.py, program.md) that are not included, and the skill declares python3 as a required binary despite stating it does not run code. These are small inconsistencies but not evidence of malicious intent.

✓ Instruction Scope

SKILL.md is documentation only and does not instruct the agent to read system files, access credentials, or transmit data externally. The instructions stay within an educational scope.

✓ Install Mechanism

No install spec and no code files are present, so nothing would be written to disk or executed during installation.

✓ Credentials

No environment variables, credentials, or config paths are requested; requested privileges are minimal and proportionate to a read-only documentation skill.

✓ Persistence & Privilege

The skill is not always-enabled and doesn't request persistent system presence or modifications to other skills or system-wide settings.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install gpu-research
安装完成后，直接呼叫该 Skill 的名称或使用 /gpu-research 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.2

- Converted the skill from runnable code to a reference/educational guide; no code execution is supported. - Clarified description and documentation to emphasize the didactic and conceptual focus. - Updated all sections to center on explaining autonomous AI research workflows and design patterns, rather than providing setup or code execution instructions. - Simplified requirements and architecture overview for easier understanding. - Maintained credit to karpathy/autoresearch as source inspiration.

v1.0.1

- Updated setup instructions to install uv via python3 -m pip instead of a shell script. - Adjusted metadata to require python3 instead of uv. - Changed references and links to TinyStories dataset for simplicity. - Removed direct external links and clarified install and usage documentation.

v1.0.0

Initial release of an autonomous AI research framework for single-GPU model optimization. - Enables automated experimentation with LLM training code, model architecture, and hyperparameters, constrained to 5-minute runs. - AI agent modifies only the training script (`train.py`) and uses results to iteratively improve models. - Simple, reproducible workflow geared for single NVIDIA GPU systems. - Provides practical tips for running experiments on limited hardware. - Inspired by Andrej Karpathy’s autoresearch concept.

元数据

Slug gpu-research

版本 1.0.2

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 3

常见问题