autoresearchclaw-autonomous-research
AutoResearchClaw is an autonomous 23-stage research pipeline that converts a natural language topic into an academic paper. It performs literature reviews using arXiv and Semantic Scholar, executes sandboxed Python experiments, conducts multi-agent peer reviews, and generates LaTeX deliverables.
Is autoresearchclaw-autonomous-research safe to install?
Review the source first: our audit of autoresearchclaw-autonomous-research's source files found 11 shell commands, 1 external URL, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The tool executes arbitrary Python code in a sandbox, runs shell commands for pipeline management, and makes network requests to LLM APIs and academic databases.
How we audit skills: our security review methodology.
Who is this skill for?
Researchers and developers who need to automate the academic paper generation process, including literature collection, experiment execution, and citation verification.
What can you do with it?
- Automated generation of academic papers from research topics
- Execution of sandboxed Python experiments for research validation
- Multi-agent peer review and evidence-consistency checking
- Automated literature collection and citation verification
- Generation of conference-ready LaTeX documents
How good is this skill?
Quality score: 5/10. The documentation is comprehensive, providing clear installation steps, configuration examples, and a detailed breakdown of the 23-stage pipeline.
What does the skill file contain?
# AutoResearchClaw — Autonomous Research Pipeline > Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. AutoResearchClaw is a fully autonomous 23-stage research pipeline that takes a natural language topic and produces a complete academic paper: real arXiv/Semantic Scholar citations, sandboxed experiments, statistical analysis, multi-agent peer review, and conference-ready LaTeX (NeurIPS/ICML/ICLR). No hallucinated references. No human babysitting. --- ## Installation ```bash # Clone and install git clone https://github.com/aiming-lab/AutoResearchClaw.git cd AutoResearchClaw...
Frequently asked questions
Does the tool hallucinate citations?
No. The pipeline includes a 4-layer citation verification process involving arXiv, CrossRef, and DataCite lookups to prevent hallucinated references.
Can I run experiments locally?
Yes. The tool supports a sandbox mode that executes Python code using a specified local Python path.
How does the tool handle human approval?
The pipeline includes gate stages at steps 5, 9, and 20 that pause for human approval in interactive mode. Users can bypass these gates using the --auto-approve flag.
What LLM providers are supported?
The tool supports OpenAI, OpenRouter, and the Agent Client Protocol (ACP).
Related skills
lark-workflow-meeting-summary
219.7KUsers who need to summarize meeting minutes, generate weekly reports, or review meeting history within the Lark ecosystem
The lark-workflow-meeting-summary skill provides a structured workflow for agents to aggregate meeting minutes from Lark VC, generate summaries, and create or update reports in Lark Docs.
programmatic-seo
83.5KContent strategists, SEO specialists, and marketers building large-scale, data-driven website content
The programmatic-seo skill provides a framework for generating SEO-optimized pages at scale using templates and data. It guides users through keyword research, data sourcing, template design, internal linking, and indexation strategies while emphasizing content uniqueness to avoid search engine penalties.
ai-seo
70.6KContent creators, SEO professionals, and digital marketers aiming to improve their brand's presence in AI-generated search results
The ai-seo skill provides a framework for optimizing web content to increase visibility and citation rates in AI-powered search engines and LLM-based assistants like ChatGPT, Perplexity, and Google AI Overviews.
ad-creative
64.0KPerformance marketers, growth teams, and advertisers who need to produce ad copy at scale or optimize existing ad creative
The ad-creative skill generates, iterates, and scales ad copy for paid advertising platforms including Google, Meta, LinkedIn, TikTok, and Twitter. It provides frameworks for creating ad headlines, descriptions, and primary text based on product context and performance data.