Curated skill libraries powering AI agents for scientific research, biomedicine, genomics, and academic writing.
Official registries and community-built skill collections for scientific AI agents.

Hermes Agent's built-in cross-registry search and install UI for skills. Aggregates 88K+ skills across multiple registries (Built-in, Optional, Community) into a single browse/search/install interface. Not a skill collection itself but the discovery layer over many — including Anthropic Skills, ClawHub, and community sources. Reached from inside Hermes via /skills or from the web docs. MIT (as part of Hermes Agent).

Official Agent Skills repository by Anthropic. The canonical source for Claude Code skills — community contributions, curated quality, and production-ready templates.

The official OpenClaw skill registry. Publish, version, search, and install text-based agent skills. 6,300+ skills with vector search, starring, commenting, and admin curation.

Official ClawHub mirror for mainland China. Same 6,300+ skills, accelerated access without VPN. Full registry sync, search, and install support.

Tencent official OpenClaw skills community, optimized for Chinese users. Browse, share, and install curated AI agent skills with WeChat integration.

Full academic pipeline: 13-agent deep research team, 12-agent paper writing (LaTeX/DOCX/MD), multi-perspective peer review with scoring rubrics, and 10-stage pipeline orchestrator.
Curated prompts and agent skills for AI-assisted research writing. Translation, polishing, analysis, and more. Practical templates for every stage of paper preparation. 16.3K stars.

170+ ready-to-use skills across 17 scientific domains: bioinformatics, cheminformatics, proteomics, clinical research, materials science, physics, and more. Connected to 250+ databases.
Claude Code skill that removes signs of AI-generated writing from text. Makes academic prose sound natural and human-written. 12.8K stars.

Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework lock-in — works with Claude Code, Codex, OpenClaw.

86 skills across 22 categories for autonomous AI research. Covers ideation, ML paper writing, fine-tuning, distributed training, inference, safety, agents, RAG, multimodal, and more.
Skill package for ML/CV/NLP paper writing. Write or rewrite Abstract, Introduction, Methods, Experiments, Conclusion. Claim-evidence alignment, reviewer self-audit. Adapted from Prof. Peng Sida's notes.
Official Google DeepMind skill collection for agentic scientific workflows. Spans genomics, structural biology, cheminformatics, and literature search. Integrates AlphaGenome, AlphaFold DB (AFDB), UniProt, OpenAlex, ClinVar, and 30+ other databases. Designed for higher token efficiency and better grounding. Bundled with Google Antigravity; install via npx skills add or via Antigravity's Build with Google plugins. Apache-2.0 with a published technical report.

A set of SKILLS.md for doing bioinformatics with agents like Claude Code. Curated bioinformatics skill templates ready to drop into your agent workflow.
7-skill pipeline for automated research paper writing, implementing arXiv:2604.05018 (Google). Outline → Plotting → Literature Review → Section Writing → Content Refinement + Benchmark. No API keys, no SDK — pure skill instructions + deterministic helpers. Works with any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider, OpenCode).
196 ready-to-use scientific skills covering genomics, proteomics, drug discovery, biostatistics, scientific computing, and writing. Supports Claude Code Plugin mode (/plugin install). Pixi-managed environment.
Open-source agent skills for AI for Science: topic exploration, literature survey, experiments, paper writing, and integrity audit. Driven by any coding agent — Claude Code, OpenCode, and others.
Cognitive frameworks of 52 Nobel Medicine laureates (2004–2025), distilled into runnable SKILL.md files. Each laureate gets a thinking model, evidence, and application guide — from Karikó's anti-consensus persistence to Yamanaka's reprogramming intuition.
Collective cognitive OS from 50 top bioinformatics scholars. 7 mental models, 10 decision heuristics, 6 school-of-thought tensions. 970 lines of research + 389 lines of dialogue analysis. Covers genomics, single-cell, structural biology, cancer genomics, systems biology, microbiome. By zwbao.
Domain-specific Claude Code skills for agentic, interpretable, and reproducible chromatin data analysis — all packaged in a Docker environment. Covers ATAC-seq / ChIP-seq (QC, peak calling, differential accessibility, motif discovery, footprinting), WGBS (DMR, UMR/LMR, methylation variability), Hi-C (compartments, TADs, loops), and multi-omics integration. Translates natural-language analysis intents into assay-aware, tool-guided workflows. Starts from processed inputs (BAM / cool / methylation tables) — no FASTQ mapping or HPC pipelines. From Tongji University Zhanglab.
No LICENSE file as of 2026-04-20 — consider asking the maintainers to add one.

The largest open-source medical AI skills library. 869 curated skills covering clinical, genomics, drug discovery, bioinformatics. Connected to PubMed, ClinicalTrials.gov, ChEMBL, DrugBank.

Bioinformatics-native AI agent skill library. 24 skills + 8,000 Galaxy tools. Local-first, reproducible. Features pharmacogenomics, GWAS lookup, polygenic risk scores, UK Biobank queries.

45 skills for biomedical research and drug discovery. Covers drug discovery, protein analysis & engineering, and single-cell omics. By PharMolix + Tsinghua AIR.

Self-Evolving LLM Agent for Biomedical Research. Autonomous multimodal agent platform from Princeton, Stanford, UCLA. Performs biomedical research tasks without API keys. Published on bioRxiv.
Two skill packs shipped with the BioDSA framework. Agent development (8 files: BaseAgent, single-agent, multi-agent, tool wrappers, deliverables & testing, user workflows) teaches the assistant to build a new biomedical agent from a natural-language spec. Agent execution (5 files: agent catalog, execution patterns, output & deliverables) teaches it to run the 8 published agents and batch-evaluate them on benchmarks. One-command installers for Claude Code, OpenClaw, Cursor, Codex CLI, and Gemini CLI.
35 skills for metagenomics and multi-omics, shipped with the MetaClaw analysis agent. Covers microbiome downstream (diversity, PERMANOVA, ALDEx2/ANCOM-BC2/MaAsLin2, QIIME2, taxonomy, functional prediction), metabolomics (XCMS preprocessing through pathway enrichment), machine learning (classification, clustering, regression, Cox, all with SHAP), and 4 deep-learning models from the Kang Ning lab — MGM microbiome foundation model, APEX peptide MIC prediction, BGC-Prophet, ONN4ARG. Every skill is a SKILL.md contract plus a read-only reference script, runs in a pinned container, records parameters and random seed to JSON, and exits non-zero on failure instead of falling back silently. Includes skill-adapter, which converts third-party SKILL.md tools into the same contract.

Two skills for producing Nature-journal-standard academic work: nature-figure (publication-ready matplotlib figures with semantic palette + editable SVG) and nature-polishing (25-rule prose polishing with 12-step workflow). Rules derived from primary Nature papers and author guidelines.

Skill quality management framework — create, evaluate, package, and govern reusable agent skills. Zero-cost static checks + LLM-based blind eval.

200+ medical research skills covering Evidence Insights, Protocol Design, Data Analysis (R/Python bioinformatics, statistical modeling, ML pipelines), and Academic Writing. One-click OpenClaw install script.

350+ academic research skills, MCP configs, and plugins for Research-Claw and AI agents. Covers literature review, paper writing, experiment tracking, and more.

Academic literature search skill powered by AMiner. 28 APIs + 6 workflows for scholar/paper/institution/journal/patent queries. Natural language search like "latest advances in Transformers".

Official Bioclaw Skills (bioskills) library for bioinformatics and multi-omics workflows. Organized by top-level omics categories to reduce complexity and attention fragmentation. Built on BioClaw skills. Community-driven, open for contributions. (Renamed from OmicSkills.)

5,400+ community skills filtered and categorized from the official Skills Registry. Install via clawhub install <slug> or manual copy. Maintained by VoltAgent.

AAS Core: local, agent-first control plane backed by 1,987+ agentic skills for Claude Code, Antigravity, and Cursor. Catalog discovery, stack validation, CLI, local MCP, and Workbench. Formerly Antigravity Awesome Skills.

500+ agent skills from official dev teams and community, compatible with Claude Code, Codex, Antigravity, Gemini CLI, Cursor, and more.

Curated collection of high-quality Claude Code skills by Baoyu (宝玉). 9.6K+ stars. Covers coding, writing, research, and productivity workflows.

192 Claude Code skills and agent plugins for Claude Code, Codex, Gemini CLI, Cursor, and 8+ coding agents. Covers engineering, marketing, product, compliance, and advisory.

339+ curated best skills, weekly updated from ClawHub + GitHub + community. Includes academic-deep-research, data-analysis, perplexity search, and more. Install via clawhub install.

The open ecosystem for AI agent skills. 250K+ skills with 114M+ installs. Discover, share, and install reusable skills for Claude Code, Codex, Cursor, Windsurf, and Roo Code.

Discover and compare open-source Agent Skills, tools and MCP servers. Quality scoring, trending analysis, automated GitHub sync.

The Agent Skills Directory by Vercel. 89,000+ skills for 20+ AI agents (Claude Code, Copilot, Cursor, Gemini, Codex). One-command install: npx skills add <repo>.