Research Agent Skills

Research skills for academia: AI, machine learning, biology, chemistry, medicine and physics

280+ open-source skills that turn Claude Code, Codex, Cursor, Gemini CLI and GitHub Copilot into careful research assistants.

imageValidate imageSkill security imageBenchmarks imageOpenSSF Scorecard imageLicense: MIT imageGitHub stars

Install · Who it's for · Benchmarks · Skills · skills.sh · Docs · FAQ

Research Agent Skills, maintained by Kalaris Labs, is a free, open-source library of Agent Skills for students, researchers and research teams. Each skill is a folder with a SKILL.md playbook, references and tested scripts. Your AI agent loads a skill only when a task needs it: drafting a manuscript, formatting for Nature or IEEE, verifying references, running a PRISMA systematic review, analyzing single-cell data, or answering reviewers.

It is built around the three ways AI research assistance goes wrong:

1. AI slop. unslop-academic-writing finds stock phrasing ("delves into", "pivotal role"), empty emphasis, stacked hedges and monotone rhythm, then rewrites toward specific, evidence-backed prose in the author's own voice.
2. Hallucinated citations. citation-verification checks every reference against Crossref, OpenAlex and arXiv. On our labeled benchmark it flagged every fabricated and corrupted reference and passed every correct one.
3. Outdated venue rules. Journal skills make the agent read the current author guidelines before formatting, instead of trusting memory.

Install in 30 seconds

npx skills add KalarisLabs/research-agent-skills

The skills.sh CLI lets you select individual skills and agent harnesses. It installs into the current project; add --global for a user-level installation. To inspect all available skills first, run npx skills add KalarisLabs/research-agent-skills --list. Then ask your agent, for example "Verify every reference in refs.bib" or "Unslop this introduction without changing any claims".

Choose a starting skill for your field with a command that works today:

The planned npm installer will add curated bundles for these fields after its first release. Browse all categories when you need a specialist skill.

The complete collection: research-agent-skills is the single collection entry, with an index of all 280 specialist skills. On skills.sh, each specialist also has its own installable entry. To install the complete set into this project for Codex, run npx skills add KalarisLabs/research-agent-skills --skill '*' --agent codex --yes. Replace codex with your agent.

Other installation methods

The research-agent-skills npm CLI and standalone installers require the first tagged release.

Our npm and standalone installers verify pinned release downloads with SHA-256. The skills.sh CLI manages its own installation flow. npx research-agent-skills doctor checks your setup. Full guide: Installation.

Installer targets: Claude Code · OpenAI Codex · Cursor · Gemini CLI · GitHub Copilot · OpenCode · Windsurf · generic .agents/skills (including compatible Cline, Amp and Goose setups). The skills follow the Agent Skills specification; other harnesses can use the folders if they support that specification. Tool permissions and advanced features may vary by harness. Every skill passes the specification's reference validator.

Built for researchers

Find an agent skill for your research task

Explore scientific agent skills by discipline

For more workflows and installation choices, see skills by field.

What you can ask

"Draft the Results section from results/ and the figures in figs/, then unslop it."
"Verify every reference in refs.bib and tell me which ones don't exist."
"Reformat this manuscript for Cell: Summary, Highlights, eTOC blurb and STAR Methods."
"Run a PRISMA 2020 systematic review on exercise and depression: search strings, dedup, flow diagram."
"Write a point-by-point response to these three reviewers within the rebuttal limit."
"Build a citation graph of my Zotero library and find the papers that bridge the two clusters."
"Check my LaTeX source before I upload it to arXiv."
"Analyze this scRNA-seq dataset with scanpy and write the methods section."

Measured, not claimed

Every skill goes through a three-tier evaluation (methodology and full results):

Quality and routing gates run on every pull request, so a weak or overlapping skill can't be merged silently.

Featured skills

Journal and venue formats

Nature · Nature Communications · Scientific Reports · Science · Science Advances · Cell · Neuron · Cell Reports · IEEE Transactions · IEEE Access · ACM (sigconf, acmsmall: CHI, KDD, SIGGRAPH) · Elsevier (elsarticle, CAS) · Springer LNCS · PLOS ONE · PLOS Biology · APA 7th edition · arXiv · NeurIPS · ICML · ICLR · ACL/ARR · AAAI · COLM · OSDI/NSDI/ASPLOS/SOSP · NIH and NSF grants · conference posters and slides.

Skill catalog

Grouped by category and generated from catalog/skills.json. The documentation directory has a page per skill.

research-writing (15) · Scientific and research paper writing, grants, peer review, critical appraisal

journal-formats (11) · Journal, conference and venue formatting: LaTeX templates, submission checklists

literature-review (18) · Literature search, systematic reviews, citation management and reference managers

ideation-and-design (12) · Hypothesis generation, experimental design, statistics planning, validation

data-science-and-ml (30) · Data analysis, statistics and machine learning libraries

visualization-and-presentation (11) · Figures, schematics, posters, slides and talks

knowledge-and-rag (7) · Vector databases, embeddings, RAG and knowledge graphs over research corpora

scientific-databases (12) · Programmatic access to public scientific databases and APIs

life-sciences (33) · Genomics, single-cell, proteomics, neuroscience and systems biology

chemistry-and-drug-discovery (12) · Cheminformatics, molecular modelling, protein design and pharmacology

clinical-and-health (7) · Clinical research, medical imaging, pathology and health data

physical-sciences (10) · Physics, astronomy, quantum computing, materials and earth science

lab-automation (11) · Lab platforms, ELNs, liquid handlers and manufacturing integrations

research-automation (9) · Autonomous research loops, agent harnesses and research artifacts

ml-training (32) · Model architectures, tokenization, fine-tuning, post-training, distributed training, optimization

ml-evaluation-and-safety (11) · Evaluation harnesses, interpretability and safety/alignment

ml-inference-and-ops (13) · Inference serving, GPU infrastructure, MLOps and observability

llm-applications (9) · Agent frameworks, prompt engineering and structured generation

multimodal-and-emerging (18) · Vision, audio, robotics, data processing and emerging techniques

Documentation

• Getting started: Installation · Quickstart
• Guides: Write a research paper with AI · Thesis and dissertation · No-slop academic writing · Systematic reviews · Skills by field
• Reference: CLI · Architecture · Benchmarks · Security · Contributing
• For AI search and agents: llms.txt

Security

Skills are instructions and code that your agent runs with your permissions, so they are treated like software dependencies. Every pull request runs spec validation, a prompt-injection and payload linter over all files, the Cisco AI Defense skill-scanner, CodeQL, Semgrep, Bandit, secret scanning and dependency review. Scripts may only contact reviewed domains. Releases are checksummed, signed and attested, and the installer detects tampered files. Details and vulnerability reporting: SECURITY.md.

FAQ

Can AI write my research paper?

It can make you much faster at outlining, drafting from your results, editing, formatting and reference checking. You remain the author: every claim, number and citation must be yours and verified. Disclose AI assistance as your venue requires.

How do I stop AI from inventing citations?

Never accept references written from memory. Export them from publishers or Crossref, then run citation-verification.

How do I make AI-assisted writing not sound like AI?

Use unslop-academic-writing. It fixes vague content before word choice and calibrates to a sample of your own writing. It improves clarity. It is not a way to hide AI use.

Is it free? Can I use it at my university or company?

Yes. MIT license. Some skills document third-party software or bundle publisher templates with their own licenses (see THIRD_PARTY_NOTICES.md).

More in the FAQ.

Contributing

Researchers are welcome to contribute skills for their field. Start with CONTRIBUTING.md and the research-skill-creator skill. make check runs everything CI runs. See also GOVERNANCE.md and SUPPORT.md.

Citation

If Research Agent Skills helped your work, please cite it ("Cite this repository" on GitHub uses CITATION.cff):

@software{chowdhury_research_agent_skills_2026,
  author  = {Chowdhury, Sayan and {Kalaris Labs}},
  title   = {Research Agent Skills: AI agent skills for academic writing and scientific research},
  year    = {2026},
  version = {1.1.1},
  url     = {https://github.com/KalarisLabs/research-agent-skills},
  license = {MIT}
}

License

MIT © 2026 Kalaris Labs. Portions of some skills are adapted from third-party MIT-licensed projects, and their notices are in THIRD_PARTY_NOTICES.md.

Created by Sayan Chowdhury · Kalaris Labs

If this saves you time, please ⭐ the repository so other researchers can find it.

imageLive GitHub star count

Sponsored by Mintlify for documentation.

imageStar History Chart