autoresearch

Orchestrate autonomous AI research workflows with two-loop experiment and synthesis cycles.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/box755/simlens-research --skill autoresearch-box755
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: autoresearch
Source: https://github.com/box755/simlens-research/tree/main/skill-packs/AI-Research-SKILLs/0-autoresearch-skill
Command: npx skills add https://github.com/box755/simlens-research --skill autoresearch-box755

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Autoresearch eliminates the manual overhead of managing an AI research project by coordinating literature intake, hypothesis formulation, iterative experiments, and final synthesis into publishable outputs.

Core Features & Use Cases

  • Two-loop research orchestration: Runs an inner loop for rapid hypothesis experiments and an outer loop for reflective synthesis that updates the narrative and research direction.
  • Autonomous routing to domain skills: Delegates domain execution (training/evaluation/data/analysis) to specialized skills while the orchestrator manages state, protocols, and bookkeeping.
  • Continuous research operation: Maintains a wall-clock continuity loop (Claude Code /loop and OpenClaw heartbeat) so research keeps progressing across time ticks.
  • Research artifacts and human-visible progress: Creates a structured workspace with state, logs, findings, per-hypothesis experiment folders, and progress presentations (HTML/PDF).

Quick Start

Use autoresearch to start a new research project from a question by first creating the workspace and then letting it run the mandatory continuity loop before beginning experiments.

Frequently Asked Questions about autoresearch

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

FAQPage Schema
How do I automate literature review and hypothesis testing for a research project?

You can automate autonomous research workflows by using a two-loop architecture that alternates between rapid hypothesis experiments and reflective synthesis to scan literature, test hypotheses, and generate paper-level conclusions.

What is a two-loop architecture for AI research synthesis?

A two-loop research architecture runs an inner loop for rapid experiment iterations and an outer loop for reflective synthesis, continuously updating the research narrative and direction until paper-level conclusions are reached.

How do I set up a workspace for autonomous AI research orchestration?

You set up autonomous research orchestration by initializing a structured workspace containing a research-state.yaml file and a findings.md file to track progress, then running a mandatory wall-clock continuity loop before experiments begin.

Can I run continuous experiment orchestration without manual intervention?

Yes, continuous experiment orchestration operates autonomously by maintaining wall-clock continuity via a loop command or cron heartbeat, ensuring research keeps progressing across time ticks without manual intervention.

Does autonomous research routing work with specialized domain skills for data analysis?

Autonomous research routing delegates domain execution like training, evaluation, and data analysis to specialized domain skills while the orchestrator manages state, protocols, and bookkeeping for the overall workflow.

What are the limitations of using an autonomous loop for paper writing and progress reporting?

The autonomous loop requires a structured workspace initialization and a continuous wall-clock heartbeat to function; without this mandatory continuity loop, the research orchestration cannot maintain progress or generate paper-level outputs.