Skip to main content

Research Agent Skills

Research Agent Skills by Kalaris Labs Open-source AI agent skills for researchers, students and labs. Use them for manuscripts, theses, grant proposals, systematic reviews, reviewer responses and scientific data analysis. Skills help you revise prose in your own voice and verify references against scholarly records. Built for academia across machine learning, AI, biology, chemistry, medicine and physics.
Created by Sayan Chowdhury at Kalaris Labs · MIT licensed. Choose the skills and agent harnesses you need for this project, or add --global for your user account. See installation options for Claude Code, OpenAI Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf.

Choose a research workflow

Built for academics

What makes it different

  • No AI slop. unslop-academic-writing finds stock phrasing, empty emphasis, stacked hedges and monotone rhythm, then rewrites toward specific, evidence-backed prose in your own voice. How it works
  • No hallucinated citations. citation-verification checks every reference against Crossref, OpenAlex and arXiv. On our labeled benchmark it flags every fabricated and corrupted reference (results).
  • Current venue rules, not remembered ones. Journal skills make the agent read the current author guidelines before formatting.
  • Measured. Every skill receives a static quality score. Reviewed prompt sets test trigger routing; selected skills have with-vs-without-skill task evaluations. Benchmarks
  • Secure. Every file is scanned for prompt injection and malicious code, and releases are checksummed, signed and attested.
Install Research Agent Skills · Browse all skills
Last modified on October 4, 2026