othmanadi/researchclaw-skill

Эта страница переведена автоматически. Технические детали смотрите в оригинале. Открыть оригинал

26 stars Качество 56 Тренд 11MIT

Turn your coding agent into a one-command autonomous research paper generator. Wraps AutoResearchClaw's 23-stage pipeline with setup automation, interactive config, error diagnosis, and self-healing...

Обзор

Turn your coding agent into a one-command autonomous research paper generator. It is a wrapper that simplifies setup, configuration, execution, and troubleshooting — it does not replace the upstream project. Install AutoResearchClaw first, then install this skill on top. AutoResearchClaw is a fully autonomous 23-stage research pipeline by aiming-lab. You give it a research topic. It gives you a conference-grade LaTeX paper. The pipeline includes 3 human-approval gates, anti-fabrication guards, and a self-learning system (MetaClaw) that gets smarter with each run. AutoResearchClaw is powerful but painful to set up. 55+ issues filed in the first 5 days — most about setup failures, config confusion, and Stage 10 crashes. Works with Claude Code, Cursor, Codex, Gemini CLI, OpenClaw, and any agent supporting the Agent Skills spec.

README

Показан фрагмент оригинального README. Открыть оригинал.

Turn your coding agent into a one-command autonomous research paper generator.

中文文档 Chinese Documentation

This skill requires AutoResearchClaw to be installed. It is a wrapper that simplifies setup, configuration, execution, and troubleshooting — it does not replace the upstream project. Install AutoResearchClaw first, then install this skill on top.

AutoResearchClaw is a fully autonomous 23-stage research pipeline by aiming-lab. You give it a research topic. It gives you a conference-grade LaTeX paper.

What happens in those 23 stages:

Phase	What It Does
Research Scoping	Parses your topic, decomposes it into sub-problems
Literature Discovery	Searches arXiv, Semantic Scholar, OpenAlex for real papers
Knowledge Synthesis	Clusters findings, identifies gaps, generates testable hypotheses
Experiment Design	Plans experiments, generates hardware-aware Python code