OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Research Agents

Auto Research Skills

A public, CC0-licensed GitHub repository that indexes and packages reusable autonomous-research skills, agents, systems, benchmarks, and curated lists.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Auto Research Skills — OpenViST project profile in Research Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you need a starting catalog for assembling an autonomous or agent-assisted research workflow and want to compare reusable components before building your own integration.

Who it is for

  • Researchers exploring agent-assisted literature review, experimentation, data analysis, or paper writing.
  • Developers building workflows with Claude Code, Codex, OpenClaw, or other LLM agents.
  • Technical users who want to inspect and combine open research components locally.

Documented uses

  • Discover research skills and agents organized by research stage.
  • Assemble resources for workflows from research ideation through experimentation and paper preparation.
  • Inspect related systems, benchmarks, and curated lists in one repository.
  • Initialize the collection and its included repositories through the documented setup script.
Before you choose

Requirements & limits

The supplied project information identifies the repository as public, active, accessible, and licensed under CC0-1.0. The documented use is repository-based and requires local Git and script execution for setup.

  • It is a curated collection rather than a single end-user research application.
  • The collection is organized through Git submodules, so local initialization is part of the documented setup.
  • Its scope covers skills, systems, benchmarks, and lists, allowing discovery beyond one research workflow.
  • Name collisions among included skills can make selection important when building a combined agent profile.
  • The README identifies Claude Code, Codex, OpenClaw, and other LLM agents as target consumers.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the curated research repository

Clone Auto Research Skills and initialize its documented Git submodules.

Before you start

  • Git
  • A local environment able to run the repository’s setup script

Steps

  1. Clone https://github.com/brycewang-stanford/Auto-Research-Skills.git.

  2. Change into the cloned Auto-Research-Skills directory.

  3. Run ./setup.sh to initialize the top-level and nested submodules.

  4. If the repository was already cloned, run ./setup.sh again to fill in missing submodules.

Expected outcome

The repository’s curated skills, systems, benchmarks, and lists are initialized locally through its documented submodule setup.

Guide limitations

  • The setup documentation does not describe how to run each included project.
  • The README warns that nested submodule mappings in upstream repositories can affect checkout behavior.
  • The collection may contain same-named skills with different content; consult catalog/collisions.json or the local collisions page before combining them.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
30 September 2026
Original website title
brycewang-stanford/Auto-Research-Skills · Official homepage title · retained in its source language
How we review sourcesSuggest a correction