open-research-skills
AGENTS.md8 starsChanged 5 months agoMITView on GitHub
A curated collection of research-domain skills for AI agents. Authored by Pradyumna Jayaram, 2026. This file is the entry point for AI agents and human contributors. It supersedes and replaces CONTRIBUTING.md (which is kept as a thin alias for the GitHub "Contribute" button). open-research-skills (ORS) is a comprehensive skill library for AI agents working alongside researchers, academics, graduate students, postdocs, and R&D engineers. It covers the full lifecycle of research: 19 categories, 123 skills — see INDEX.md for the per-skill…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository125 other files it gives its agents.
- skills/AGENTS.mdAGENTS.md
- batch-processingSkill
- bowtie2-alignmentSkill
- bwa-alignmentSkill
- bwa-mem2-alignmentSkill
- codon-usageSkill
- compressed-sequence-filesSkill
- fastq-quality-scoresSkill
- filter-sequencesSkill
- format-conversionSkill
- hisat2-alignmentSkill
- motif-searchSkill
- paired-end-fastqSkill
- pysam-genomicsSkill
- read-write-sequencesSkill
- reverse-complementSkill
- sam-bam-basicsSkill
- samtools-bam-processingSkill
- seq-objectsSkill
- sequence-propertiesSkill
- sequence-slicingSkill
- sequence-statisticsSkill
- star-alignmentSkill
- transcription-translationSkill
- academic-cvSkill
- faculty-interviewSkill
- fellowship-applicationSkill
- industry-transitionSkill
- negotiationSkill
- tenure-dossierSkill
- admet-predictionSkill
- conformer-generationSkill
- covalent-designSkill
- docking-rescoringSkill
- free-energy-calculationsSkill
- generative-designSkill
- molecular-descriptorsSkill
- molecular-ioSkill
- molecular-standardizationSkill
- pharmacophore-modelingSkill
- pose-validationSkill
- protac-degradersSkill
- qsar-modelingSkill
- retrosynthesisSkill
- scaffold-analysisSkill
- shape-similaritySkill
- similarity-searchingSkill
- substructure-searchSkill
- virtual-screeningSkill
- snakemake-workflow-engineSkill
- ai-disclosureSkill
- data-privacySkill
- image-integritySkill
- irb-protocolSkill
- ai-detection-awarenessSkill
- ai-disclosure-statementSkill
- scientific-voice-styleSkill
- text-humanizing-editorialSkill
- cellprofiler-pipelinesSkill
- image-analysis-best-practicesSkill
- The first 60 shown.
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 107
Every skill lives at skills/<category>/<slug>/SKILL.md and has the form:
- Very specific: line 134
Read skills/AGENTS.md — the skill-authoring guide.
- Very specific: line 138
Run python scripts/validate-skills.py skills/ to validate.
- Very specific: line 139
Run python scripts/build-index.py to regenerate INDEX.md.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
open-research-skills — agent and contributor guide
A curated collection of research-domain skills for AI agents. Authored by Pradyumna Jayaram, 2026.
This file is the entry point for AI agents and human contributors. It supersedes and replaces CONTRIBUTING.md (which is kept as a thin alias for the GitHub "Contribute" button).
What this repo is
open-research-skills (ORS) is a comprehensive skill library for AI agents working alongside researchers, academics, graduate students, postdocs, and R&D engineers. It covers the full lifecycle of research:
literature search → experimental design → analysis → writing → publication → grant writing → mentorship → ethicsCurrent status (v0.3.0)
19 categories, 123 skills — see INDEX.md for the per-skill table.
Layout
open-research-skills/
├── README.md # main readme
├── LICENSE # MIT
├── AGENTS.md # this file
├── CONTRIBUTING.md # alias for GitHub "Contribute" button
├── CHANGELOG.md # release notes
├── ROADMAP.md # what's done, what's next
├── INDEX.md # per-skill table
├── SCHEMA.md # frontmatter spec (legacy, see spec/)
├── TAXONOMY.md # 18 categories (legacy, see spec/)
├── THIRD_PARTY_NOTICES.md # upstream attributions
│
├── .claude-plugin/ # Claude Code plugin marketplace
│ └── marketplace.json
│
├── spec/ # ORS specification
│ ├── README.md
│ ├── skill-format.md
│ └── category-taxonomy.md
│
├── template/ # template for new skills
│ └── SKILL.md
│
├── examples/ # worked examples
│ ├── README.md
│ ├── claude-code-installation.md
│ ├── api-integration.md
│ └── multi-skill-workflow.md
│
├── scripts/ # repo automation
│ ├── README.md
│ ├── validate-skills.py
│ └── build-index.py
│
├── tests/ # test suite
│ ├── test_frontmatter.py
│ ├── test_skill_structure.py
│ └── fixtures/
│
├── .github/workflows/ # CI
│ ├── validate.yml
│ └── release.yml
│
└── skills/ # all 123 skills, organized in 19 categories
├── AGENTS.md # skill-authoring guide
├── bioinformatics-sequence/ # 23 skills
├── chemoinformatics/ # 19 skills
├── research-grants/ # 9 skills
└── ... (15 more categories)Installation
As a Claude Code plugin (recommended)
/plugin marketplace add pradyumnasagar/open-research-skills
/plugin install ors-research@pradyumnasagar
/plugin install ors-bioinformatics@pradyumnasagar
/plugin install ors-career-ethics@pradyumnasagarAs a git clone
git clone https://github.com/pradyumnasagar/open-research-skills.git
cd open-research-skills
claudeIn the chat, ask Claude to use a specific skill by name:
> Use the bwa-alignment skill to align these reads to GRCh38.See examples/claude-code-installation.md for more.
Programmatically (API)
See examples/api-integration.md for Python, TypeScript, Bedrock, and Vertex examples.
Skill format
Every skill lives at skills/<category>/<slug>/SKILL.md and has the form:
---
name: <kebab-case-slug>
description: <one or two sentences — what & when>
license: MIT # optional
---
<!-- metadata: ... (optional) -->
# Skill Title
> Tagline
## When to use
## Workflow
## Code patterns
## Pitfalls
## Validation
## ReferencesThe full spec is in spec/skill-format.md.
Adding a new skill
- Read
skills/AGENTS.md— the skill-authoring guide. - Copy
template/SKILL.mdtoskills/<category>/<your-slug>/SKILL.md. - Fill in the frontmatter (
nameanddescriptionare required). - Fill in the body and the optional
<!-- metadata: ... -->block. - Run
python scripts/validate-skills.py skills/to validate. - Run
python scripts/build-index.pyto regenerateINDEX.md. - Open a PR.
Adding a new category
See spec/category-taxonomy.md — the bar is high. Propose in an issue first.
License
MIT. All skills authored by Pradyumna Jayaram unless explicitly co-authored in a PR. See THIRD_PARTY_NOTICES.md for upstream attributions.
No AI co-authorship
This repo is authored by Pradyumna Jayaram. Commits must not include Co-Authored-By: lines for AI assistants.
Versioning
Semantic versioning:
- Major — break the frontmatter contract, remove/rename categories.
- Minor — add categories, add skills, backwards-compatible schema additions.
- Patch — fix typos, update tooling versions, add validation tests.
Current: v0.3.0 (restructure to match Anthropic skills pattern).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

