Skip to content
Back to search

Awesome-Scientific-Skills

An open, curated collection of Agent Skills for scientific research — clone it, use it, extend it!

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/internscience--awesome-scientific-skills/badge.svg)](/listings/internscience--awesome-scientific-skills)

HTML

<a href="/listings/internscience--awesome-scientific-skills"><img src="/api/listings/internscience--awesome-scientific-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Option 1 — Browse and pick

Explore the [Skill Sources](#Skill Sources) above, find what you need, and copy individual skill folders into your project:

your-project/
└── .claude/
    └── skills/
        ├── pubmed-search/
        ├── rdkit-molecular-analysis/
        └── scientific-writer/

Option 2 — Clone the science stack (Phase 2)

# Coming soon — once we consolidate skills into this repo
git clone https://github.com/InternScience/Awesome-Scientific-Skills.git
cp -r Awesome-Scientific-Skills/skills/ your-project/.claude/skills/

Compatibility

Skills follow the open [Agent Skills](https://agentskills.io) specification. They work with:

- **Claude Code** — `/skills` or `.claude/skills/` directory - **Cursor** — reads from `.claude/skills/` and `.codex/skills/` - **Codex** — `.codex/skills/` directory - **Gemini CLI / Antigravity** — compatible via the Agent Skills standard

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

readme.md · README · 276 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <div align="center">
  2. # Awesome Scientific Skills
  3. **An open, curated collection of Agent Skills for scientific research — clone it, use it, extend it.**
  4. **中文说明 / Chinese README:** [readme_CN.md](readme_CN.md)
  5. ### **Latest News**
  6. - We open-sourced [Skiller](https://github.com/qishisuren123/skiller.git) — an automated tool that turns conversation logs or plain-text requirements into standards-compliant skill packages.
  7. - We released [skill-metric](https://github.com/ddd9898/skill-metric) — a skills evaluation framework that screens high-quality skill repos across three dimensions. Results can also be found in /skills-metric.
  8. [![Awesome](https://awesome.re/badge-flat2.svg)](https://awesome.re) ![Skills](https://img.shields.io/badge/skills-curated-blue?style=flat-square) ![License](https://img.shields.io/badge/license-MIT-green?style=flat-square) ![Last Commit](https://img.shields.io/github/last-commit/InternScience/Awesome-Scientific-Skills?style=flat-square)
  9. <a href="fig.jpg"><img src="fig.jpg" alt="Awesome Scientific Skills figure" width="920" /></a>
  10. ⭐ **Star us on GitHub! Your support means the world to us!** 🙏😊
  11. [Why this repo?](#why-this-repo) · [Skill Sources](#skill-sources) · [Categories](#scientific-skill-categories) · [Quick Start](#quick-start) · [Contributing](#contributing)
  12. </div>
  13. ---
  14. ## The Problem
  15. Thousands of Agent Skills are scattered across official registries and community repos. A researcher who needs to run a gene ontology enrichment, draft a grant proposal, and plot dose-response curves shouldn't have to dig through 30,000+ entries to find the right three skills. And once found, they shouldn't have to wire them together from scratch.
  16. ## The Goal
  17. Build a **single, clone-ready repository** of high-quality skills selected and organized for scientific research — spanning bioinformatics, cheminformatics, data analysis, scientific writing, literature search, and beyond.
  18. > **Phase 1 (current):** A curated link collection — the reading list before the library.
  19. >
  20. > **Phase 2:** Import and reorganize selected skills into a unified directory structure.
  21. >
  22. > **Phase 3:** Composition recipes — multi-skill workflows for real research tasks.
  23. ---
  24. ## Why This Repo?
  25. | Feature | What it means for you |
  26. |---|---|
  27. | **Science-first curation** | Every skill is evaluated for relevance to real research workflows — not marketing demos |
  28. | **Fully clonable** | `git clone` once, get a working skill library — no account, no registry, no API key |
  29. | **Cross-agent compatible** | Works with Claude Code, Cursor, Codex, Gemini CLI, and any agent supporting the open [Agent Skills](https://agentskills.io) standard |
  30. | **Open & auditable** | Every skill's source is public. Review before you run |
  31. ---
  32. ## Skill Sources
  33. We draw from two tiers of upstream repositories:
  34. ### Official Skill Registries
  35. | Repository | Description |
  36. |---|---|
  37. | [anthropics/skills](https://github.com/anthropics/skills) | Anthropic's official Agent Skills — skill-creator, web artifacts, MCP builder, brand guidelines, and more |
  38. | [openai/skills](https://github.com/openai/skills) | OpenAI's official skill definitions |
  39. | [huggingface/skills](https://github.com/huggingface/skills) | Hugging Face's skill collection for model-centric workflows |
  40. | [openclaw/clawhub](https://github.com/openclaw/clawhub) | OpenClaw's community skill registry (13,700+ skills) |
  41. ### Community Curations
  42. | Repository | Stars | Description |
  43. |---|---|---|
  44. | [VoltAgent/awesome-openclaw-skills](https://github.com/VoltAgent/awesome-openclaw-skills) | 25K+ | 5,400+ skills filtered from ClawHub — the largest community-curated awesome list |
  45. | [travisvn/awesome-claude-skills](https://github.com/travisvn/awesome-claude-skills) | 7K+ | Curated Claude Skills with detailed progressive-disclosure architecture docs |
  46. | [ComposioHQ/awesome-claude-skills](https://github.com/ComposioHQ/awesome-claude-skills) | 39K+ | 50+ verified skills for Claude Code / Claude.ai / API, plus 500+ app integrations via Composio |
  47. | [heilcheng/awesome-agent-skills](https://github.com/heilcheng/awesome-agent-skills) | 2K+ | Cross-agent skill collection |
  48. | [InternScience/scp/skills](https://github.com/InternScience/scp/tree/main/skills) | 113 | 206 scientific skills spanning drug discovery, genomics, protein engineering, chemistry, and related research workflows |
  49. | [obra/superpowers/skills](https://github.com/obra/superpowers/tree/main/skills) | 68K+ | Opinionated "superpowers" skill set for power users |
  50. | [vercel-labs/agent-skills](https://github.com/vercel-labs/agent-skills) | 21K+ | Vercel Labs' experimental agent skill toolkit |
  51. | [nextlevelbuilder/ui-ux-pro-max-skill](https://github.com/nextlevelbuilder/ui-ux-pro-max-skill) | 36K+ | UI/UX focused skill for high-fidelity frontend generation |
  52. | [coreyhaines31/marketingskills](https://github.com/coreyhaines31/marketingskills) | 11K+ | Marketing-oriented agent skills for CRO, copywriting, SEO, analytics, and growth workflows |
  53. | [agentskills/agentskills](https://github.com/agentskills/agentskills) | 12K+ | Official specification and documentation for the open Agent Skills standard |
  54. | [kepano/obsidian-skills](https://github.com/kepano/obsidian-skills) | 12K+ | Agent skills for Obsidian workflows (Markdown, Bases, JSON Canvas, and CLI integration) |
  55. | [muratcankoylan/Agent-Skills-for-Context-Engineering](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering) | 13K+ | Comprehensive skill collection for context engineering and production multi-agent systems |
  56. | [ynulihao/AgentSkillOS](https://github.com/ynulihao/AgentSkillOS) | 233 | Searchable skill retrieval and orchestration system for building agents from 90,000+ skills |
  57. | [OthmanAdi/planning-with-files](https://github.com/OthmanAdi/planning-with-files) | 15K+ | Persistent markdown planning workflow skill for Claude Code |
  58. | [sickn33/antigravity-awesome-skills](https://github.com/sickn33/antigravity-awesome-skills) | 20K+ | Large cross-agent collection (900+ skills) for Claude Code, Antigravity, and Cursor |
  59. | [hesreallyhim/awesome-claude-code](https://github.com/hesreallyhim/awesome-claude-code) | 26K+ | Curated ecosystem list for Claude Code: skills, hooks, commands, apps, and plugins |
  60. | [affaan-m/everything-claude-code](https://github.com/affaan-m/everything-claude-code) | 60K+ | Broad Claude Code ecosystem toolkit focused on performance, security, memory, and research workflows |
  61. ### Science-Specific
  62. #### Specialized Domain Tools (Top Priority)
  63. | Repository | Stars | Description |
  64. |---|---|---|
  65. | [K-Dense-AI/claude-scientific-skills](https://github.com/K-Dense-AI/claude-scientific-skills) | 11.5K+ | **148+ scientific skills** covering 250+ databases (PubMed, ChEMBL, UniProt, COSMIC, ClinicalTrials.gov, SEC EDGAR, etc.) - a broad foundation for this project's science tier |
  66. | [jaechang-hits/scicraft](https://github.com/jaechang-hits/scicraft) | 17 | **140 validated life-science computational skills** for AI coding agents, with CI-validated structure and workflow-oriented references |
  67. #### Academic Writing
  68. | Repository | Stars | Description |
  69. |---|---|---|
  70. | [K-Dense-AI/claude-scientific-writer](https://github.com/K-Dense-AI/claude-scientific-writer) | 937 | Deep research + scientific writing tool with real-time literature search and verified citations |
  71. | [HughYau/AcademicForge](https://github.com/HughYau/AcademicForge) | 250 | Curated skill collection for academic writing and research workflows (focused integration over broad skill quantity) |
  72. | [Agnuxo1/PaperClaw](https://github.com/Agnuxo1/PaperClaw) | 1 | Apache-licensed scientific paper generation workflow with IMRaD structure, local model support, LaTeX output, and optional Lean 4 blocks |
  73. #### Literature Search
  74. | Repository | Stars | Description |
  75. |---|---|---|
  76. | [Intelligent-Internet/II-Commons-Skills](https://github.com/Intelligent-Internet/II-Commons-Skills) | 2 | Fast, daily-updated skill and CLI for deterministic retrieval across arXiv, PubMed/PMC, and supported US policy corpora |
  77. | [yorkeccak/scientific-skills](https://github.com/yorkeccak/scientific-skills) | 21 | Natural-language scientific literature search skills with semantic retrieval across PubMed, arXiv, ChEMBL, DrugBank, and more |
  78. | [Weizhena/Deep-Research-skills](https://github.com/Weizhena/Deep-Research-skills) | 90 | Structured deep-research workflow skill (outline + investigation) with human-in-the-loop control for academic, technical, and market research |
  79. #### Neuroscience
  80. | Repository | Stars | Description |
  81. |---|---|---|
  82. | [HughYau/neuroforge-skills](https://github.com/HughYau/neuroforge-skills) | 1 | Neuroscience skill set built around major Python toolchains (Brian2, MNE-Python, Nilearn, SpikeInterface, pyNIBS) |
  83. | [HaoxuanLiTHUAI/awesome_cognitive_and_neuroscience_skills](https://github.com/HaoxuanLiTHUAI/awesome_cognitive_and_neuroscience_skills) | 9 | Cognitive science and neuroscience skill collection spanning EEG/ERP, fMRI, modeling, and subdomains; repository notes substantial AI-generated content |
  84. ---
  85. ## Scientific Skill Categories
  86. Below is the target taxonomy. Skills from the sources above are mapped into these categories. Checked boxes indicate categories already well-covered upstream; unchecked indicate gaps we aim to fill.
  87. ### Wet-Lab & Life Sciences
  88. - [x] **Bioinformatics & Genomics** — sequence analysis, single-cell RNA-seq (Scanpy), variant annotation, phylogenetics, gene regulatory networks
  89. - [x] **Cheminformatics & Drug Discovery** — molecular property prediction (RDKit), docking, ADMET, compound library search (ChEMBL)
  90. - [x] **Structural Biology** — protein structure prediction, PDB retrieval, molecular visualization
  91. - [x] **Clinical & Medical Research** — ClinicalTrials.gov search, ICD coding, adverse event analysis, COSMIC/TCGA queries
  92. ### Computational & Data Science
  93. - [x] **Statistical Analysis** — hypothesis testing, Bayesian inference, survival analysis, power calculations
  94. - [x] **Machine Learning for Science** — PyTorch Lightning workflows, scikit-learn pipelines, hyperparameter tuning
  95. - [ ] **Simulation & Modeling** — molecular dynamics, finite element analysis, agent-based modeling
  96. - [ ] **High-Performance Computing** — job submission (SLURM/PBS), distributed training, GPU profiling
  97. ### Literature & Knowledge
  98. - [x] **Literature Search & Retrieval** — PubMed, arXiv, Semantic Scholar, CrossRef, DOI resolution
  99. - [x] **Scientific Writing** — paper drafting, grant proposals, peer review assistance, citation management
  100. - [ ] **Knowledge Graphs** — ontology navigation (Gene Ontology, MeSH), entity linking, relationship extraction
  101. ### Research Operations
  102. - [x] **Data Wrangling** — tabular data cleaning, format conversion, missing data imputation
  103. - [x] **Visualization** — publication-quality plots (Matplotlib/Seaborn), interactive dashboards, figure layout
  104. - [ ] **Reproducibility** — environment capture, notebook-to-pipeline conversion, data provenance tracking
  105. - [x] **Document Processing** — PDF extraction, DOCX/PPTX generation, LaTeX compilation
  106. ### Quantitative & Financial Research
  107. - [x] **Financial Data** — SEC EDGAR, Alpha Vantage, OFR Hedge Fund Monitor, Treasury fiscal data
  108. - [ ] **Econometrics** — time series analysis, causal inference, panel data methods
  109. ---
  110. ## Quick Start
  111. ### Option 1 — Browse and pick
  112. Explore the [Skill Sources](#Skill Sources) above, find what you need, and copy individual skill folders into your project:
  113. ```
  114. your-project/
  115. └── .claude/
  116. └── skills/
  117. ├── pubmed-search/
  118. ├── rdkit-molecular-analysis/
  119. └── scientific-writer/
  120. ```
  121. ### Option 2 — Clone the science stack (Phase 2)
  122. ```bash
  123. # Coming soon — once we consolidate skills into this repo
  124. git clone https://github.com/InternScience/Awesome-Scientific-Skills.git
  125. cp -r Awesome-Scientific-Skills/skills/ your-project/.claude/skills/
  126. ```
  127. ### Compatibility
  128. Skills follow the open [Agent Skills](https://agentskills.io) specification. They work with:
  129. - **Claude Code** — `/skills` or `.claude/skills/` directory
  130. - **Cursor** — reads from `.claude/skills/` and `.codex/skills/`
  131. - **Codex** — `.codex/skills/` directory
  132. - **Gemini CLI / Antigravity** — compatible via the Agent Skills standard
  133. ---
  134. ## Selection Criteria
  135. Not every skill makes the cut. We apply these filters:
  136. | Criterion | Requirement |
  137. |---|---|
  138. | **Scientific relevance** | Must serve a real research workflow — not a demo or toy example |
  139. | **Source quality** | Published by a known team or actively maintained community project |
  140. | **Documentation** | Clear SKILL.md with description, usage, and dependencies |
  141. | **Open license** | MIT, Apache 2.0, or equivalent permissive license |
  142. | **Security** | No network calls without explicit disclosure; no credential harvesting |
  143. | **Non-redundant** | If two skills do the same thing, we keep the better-maintained one |
  144. ---
  145. ## Contributing
  146. Contributions are welcome. This is a curated list — quality over quantity.
  147. **To suggest a skill:**
  148. 1. Fork this repository
  149. 2. Add the skill to the appropriate section in `readme.md` with format:
  150. ```
  151. | [skill-name](https://github.com/...) | Brief description of what it does |
  152. ```
  153. 3. Submit a Pull Request with a short note on why this skill is useful for scientific research
  154. **What we're looking for:**
  155. - Skills that solve real problems researchers face daily
  156. - Skills that compose well with others (e.g., a search skill whose output feeds into an analysis skill)
  157. - Skills maintained by their authors — not abandoned after initial commit
  158. **What we don't accept:**
  159. - Crypto/blockchain/DeFi skills (off-scope)
  160. - Skills with no documentation
  161. - Bulk-generated or spam skills
  162. - Skills that require proprietary backends without free tiers
  163. ---
  164. ## Security Notice
  165. > Skills can execute arbitrary code in your agent's environment. **Always review a skill's `SKILL.md` and any bundled scripts before installing.** The skills listed here are curated, not audited — they may be updated or modified by their original maintainers at any time.
  166. ---
  167. ## Roadmap
  168. - [x] Phase 1 — Curated link collection with source taxonomy
  169. - [ ] Phase 2 — Community skill registry with ratings and usage metrics
  170. - [ ] Phase 3 — Test skill in OpenClaw and Claude Code
  171. - [ ] Phase 4 — Develop skill creator which can create skill from paper and agentic trace
  172. ---
  173. ## Related Projects
  174. Companion open-source tools from our team for skill generation and repository evaluation:
  175. | Project | Description |
  176. |---|---|
  177. | [K-Dense-AI/claude-scientific-writer](https://github.com/K-Dense-AI/claude-scientific-writer) | Deep research + scientific writing tool with real-time literature search and verified citations |
  178. | [K-Dense-AI/claude-skills-mcp](https://github.com/K-Dense-AI/claude-skills-mcp) | MCP server for vector-search-based skill retrieval |
  179. | [qishisuren123/skiller](https://github.com/qishisuren123/skiller.git) | Skiller - an automated skill generation tool that turns conversation logs or plain-text requirements into standards-compliant skill packages in one shot; validated under a full static-evaluation rubric and improves by 57 percentage points over the no-skill baseline |
  180. | [ddd9898/skill-metric](https://github.com/ddd9898/skill-metric) | A skills evaluation framework that screens high-quality skill repositories across three dimensions and provides structured metrics for skill quality assessment |
  181. | [agentskills.io](https://agentskills.io) | The open Agent Skills specification |
  182. ---
  183. ## License
  184. This curated list is released under [MIT](LICENSE). Individual skills retain their own licenses as specified in their respective `SKILL.md` files.
  185. ---
  186. <div align="center">
  187. **If this saves you time in your research, give it a star and share it with your lab.**
  188. </div>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.