autoresearch

Orchestrate autonomous AI research projects from literature survey to published results.

Updated Mar 30, 2026
One-click install
npx skills add https://github.com/KappTech88/AI-RESEARCH-SKILLS-MCP --skill autoresearch-kapptech88
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: autoresearch
Source: https://github.com/KappTech88/AI-RESEARCH-SKILLS-MCP/tree/main/skills/autoresearch
Command: npx skills add https://github.com/KappTech88/AI-RESEARCH-SKILLS-MCP --skill autoresearch-kapptech88

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

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.

Core Features & Use Cases

  • Two-loop architecture: fast experimentation with clear targets and periodic synthesis for direction.
  • Domain-skill routing: routes tasks to domain skills for execution and ensures continuous operation via Claude Code /loop and OpenClaw heartbeat.
  • Human-facing outputs: generates research presentations and papers to communicate progress and findings.
  • Use Case: starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.

Quick Start

Boot the autoresearch workflow, initialize a project workspace, and start the inner loop of experiments immediately.

Frequently Asked Questions about autoresearch

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate literature surveys and experiment management for an autonomous research project?

Automated literature surveys and experiment management are orchestrated through a two-loop architecture. The inner loop runs rapid experiment iterations with optimization targets, while the outer loop synthesizes results and steers research direction end-to-end.

What is the best way to run continuous autonomous experiments without manual intervention?

Continuous autonomous experiments are sustained using Claude Code /loop and OpenClaw heartbeat mechanisms. These provide heartbeat-based continuity, ensuring the research agent operates without manual intervention across multi-hypothesis efforts.

Can I use domain-specific skills for routing tasks during autonomous research orchestration?

Domain skill routing is supported for task execution during autonomous research orchestration. The system dynamically routes research tasks to domain-specific skills, ensuring specialized execution while the two-loop engine maintains overall project continuity.

How do I synthesize research findings into presentations and papers automatically?

Research findings are synthesized into presentations and papers automatically by the outer loop. It identifies patterns from experimentation results and generates human-facing outputs to communicate progress and publish findings.

What prerequisites or environment setup do I need to start an autonomous AI research workflow?

Starting an autonomous AI research workflow requires booting the orchestration workflow and initializing a project workspace. This immediately launches the inner experiment loop, requiring no additional dependencies to begin processing.

Does autonomous research orchestration work for managing multi-hypothesis research efforts?

Autonomous research orchestration is designed specifically for managing multi-hypothesis research efforts. The two-loop architecture handles rapid experimentation and periodic synthesis, effectively steering multiple hypotheses toward published results.