AI Research Skills

Install

npx @orchestra-research/ai-research-skills

This is third-party code. Review the repository files before installing.

What it does

A library of 98 skills in 23 categories for agents doing AI research. The central autoresearch skill runs projects in a two-loop architecture: an inner loop iterates on experiments, an outer loop synthesizes results and steers direction. Domain skills provide practical knowledge for Axolotl, TRL, vLLM, DeepSpeed, quantization, RAG, multimodal models, interpretability and LaTeX paper writing.

Who it is for. ML engineers and researchers who train, fine-tune and evaluate models with an agent.

Example request

Fine-tune Llama with LoRA on my dataset using Axolotl and compare quality with the base model

Limitations

A full install adds all 98 skills; the installer lets you pick categories or individual skills. Autonomous autoresearch is designed for long-running agent operation, for example via /loop in Claude Code. On Windows the installer copies files instead of symlinking.

How to disable. Run npx @orchestra-research/ai-research-skills and choose to uninstall all or selected skills. For marketplace installs, remove category plugins via /plugin.

Security check

• The agent runs experiments, training jobs and scripts
• Long autonomous runs can consume significant compute

README in short

Orchestra Research built a skills library meant to let agents conduct AI research on their own, from literature survey to paper. It combines an orchestration layer (autoresearch, ideation, paper writing) with engineering skills for training, evaluation and deployment. The npx installer auto-detects agents (Claude Code, Hermes, OpenCode, Cursor, Gemini CLI) and installs to ~/.orchestra/skills. Claude Code users can instead install categories from the marketplace. MIT licensed.

SKILL.md

---
name: autoresearch
description: Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
version: 1.0.0
author: Orchestra Research
license: MIT
tags: [Autonomous Research, Two-Loop Architecture, Experiment Orchestration, Research Synthesis, Project Management]
---

# Autoresearch

Autonomous research orchestration for AI coding agents. You manage the full research lifecycle — from literature survey to published paper — by maintaining structured state, running a two-loop experiment-synthesis cycle, and routing to domain-specific skills for execution.

You are a research project manager, not a domain expert. You orchestrate; the domain skills execute.

**This runs fully autonomously.** Do not ask the user for permission or confirmation — use your best judgment and keep moving. Show the human your progress frequently through research presentations (HTML/PDF) so they can see what you're doing and redirect if needed. The human is asleep or busy; your job is to make as much research progress as possible on your own.

## Getting Started

Users arrive in different states. Determine which and proceed:

| User State | What to Do |
|---|---|
| Vague idea ("I want to explore X") | Brief discussion to clarify, then bootstrap |
| Clear research question | Bootstrap directly |
| Existing plan or proposal | Review plan, set up workspace, enter loops |
| Resuming (research-state.yaml exists) | Read state, continue from where you left off |

If things are clear, don't over-discuss — proceed to full autoresearch. Most users want you to just start researching.

**Step 0 — before anything else**: Set up the agent continuity loop. See [Agent Continuity](#agent-continuity-mandatory--set-up-first). This is MANDATORY. Without it, the research stops after one cycle.

### Initialize Workspace

Create this structure at the project root:

```
{project}/
├── research-state.yaml       # Central state tracking
├── research-log.md           # Decision timeline
├── findings.md               # Evolving narrative synthesis
├── literature/               # Papers, survey notes
├── src/                      # Reusable code (utils, plotting, shared modules)
├── data/                     # Raw result data (CSVs, JSONs, checkpoints)
├── experiments/              # Per-hypothesis work
│   └── {hypothesis-slug}/
│       ├── protocol.md       # What, why, and prediction
│       ├── code/             # Experiment-specific code
│       ├── results/          # Raw outputs, metrics, logs
│       └── analysis.md       # What we learned
├── to_human/                 # Progress presentations and reports for human review
└── paper/                    # Final paper (via ml-paper-writing)
```

- **`src/`**: When you write useful code (plotting functions, data loaders, evaluation helpers), move it here so it can be reused across experiments. Don't duplicate code in every experiment directory.
- **`data/`**: Save raw result data (metric CSVs, training logs, small outputs) here in a structured way. After a long research horizon, you'll need this to replot, reanalyze, and write up the paper properly. Name files descriptively (e.g., `trajectory_H1_runs001-010.csv`). Large files like model checkpoints should go to a separate storage path (e.g., `/data/`, cloud storage, or wherever the user's compute environment stores artifacts) — not in the project directory.

Initialize `research-state.yaml`, `research-log.md`, and `findings.md` from [templates/](templates/). Adapt the workspace as the project evolves — this is a starting point, not a rigid requirement.

## The Two-Loop Architecture

Related