← Back to Skills Marketplace
tyronecoh

Auto Research Agent

by TyroneMok · GitHub ↗ · v1.0.2 · MIT-0
linux ✓ Security Clean
128
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install gpu-research
Description
A reference framework for understanding autonomous AI research pipelines. Learn how AI can optimize ML training with fixed time budgets and metric-driven ite...
README (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

\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

Usage Guidance
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.
Capability Assessment
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.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install gpu-research
  3. After installation, invoke the skill by name or use /gpu-research
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
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.
Metadata
Slug gpu-research
Version 1.0.2
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 3
Frequently Asked Questions

What is Auto Research Agent?

A reference framework for understanding autonomous AI research pipelines. Learn how AI can optimize ML training with fixed time budgets and metric-driven ite... It is an AI Agent Skill for Claude Code / OpenClaw, with 128 downloads so far.

How do I install Auto Research Agent?

Run "/install gpu-research" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Auto Research Agent free?

Yes, Auto Research Agent is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Auto Research Agent support?

Auto Research Agent is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux).

Who created Auto Research Agent?

It is built and maintained by TyroneMok (@tyronecoh); the current version is v1.0.2.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191113 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments