Agent skill · research science · aradotso
autoresearchclaw-autonomous-research
Fully autonomous research pipeline that turns a topic idea into a complete academic paper with real citations, experiments, and conference-ready LaTeX.
Why this skill is useful
Adds a fully autonomous research pipeline that generates complete academic papers with real citations and experiments, which the AI cannot generate on its own.
What it needs
Requires python installed locally. Requires openai, openrouter account access. About 6k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
AutoResearchClaw — Autonomous Research Pipeline Skill by 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 Requirements: Python 3.11+ --- Configuration Minimum config (config.arc.yaml) OpenRouter config (200+ models) ACP (Agent Client Protocol) — no API key needed The agent CLI (e.g. claude) handles its own authentication. OpenClaw bridge (optional advanced capabilities) --- Key CLI Commands Gate stages (5, 9, 20) pause for human approval in interactive mode. Pass --auto-approve to skip all gates. --- Python API --- Output Structure After a run, all outputs land in artifacts/rc-YYYYMMDD-HHMMSS-<hash>/: --- Pipeline Stages Reference Phase Stage # Name Notes ------- --------- ------ ------- A 1 TOPICINIT Parse and scope research topic A 2 PROBLEMDECOMPOSE Break into sub-problems B 3 SEARCHSTRATEGY Build search queries B 4 LITERATURECOLLECT Real API calls to arXiv + Semantic Scholar B 5 LITERATURESCREEN Gate — approve/reject literature B 6 KNOWLEDGEEXTRACT Extract structured knowledge C 7 SYNTHESIS Synthesize findings C 8 HYPOTHESISGEN Multi-agent debate to form hypotheses D 9 EXPERIMENTDESIGN Gate — approve/reject design D 10 CODEGENERATION Generate experiment code D 11 RESOURCEPLANNING GPU/MPS/CPU auto-detection E 12 EXPERIMENTRUN Sandboxed execution E 13 ITERATIVEREFINE Self-healing on failure F 14 RESULTANALYSIS Multi-agent analysis F 15 RESEARCHDECISION PROCEED / REFINE / PIVOT G 16 PAPEROUTLINE Structure paper G 17 PAPERDRAFT Write full paper G 18 PEERREVIEW Evidence-consistency check G 19 PAPERREVISION Incorporate review feedback H 20 QUALITYGATE Gate — final approval H 21 KNOWLEDGEARCHIVE Save lessons to KB H 22 …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/autoresearchclaw-autonomous-research