{"id":51453058,"url":"https://github.com/InternScience/Awesome-Scientific-Skills","last_synced_at":"2026-07-07T12:02:16.173Z","repository":{"id":343220033,"uuid":"1171290857","full_name":"InternScience/Awesome-Scientific-Skills","owner":"InternScience","description":"An open, curated collection of Agent Skills for scientific research — clone it, use it, extend it!","archived":false,"fork":false,"pushed_at":"2026-05-26T02:53:39.000Z","size":1159,"stargazers_count":445,"open_issues_count":8,"forks_count":29,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-06-20T21:02:57.372Z","etag":null,"topics":["agent-skills","awesome-list","openclaw-skills","scientific-data","scientific-discovery","scientific-skill"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/InternScience.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-03-03T04:14:39.000Z","updated_at":"2026-06-20T19:57:28.000Z","dependencies_parsed_at":null,"dependency_job_id":"d40cc5fd-9cbb-4779-bf6a-d3f55e899e1f","html_url":"https://github.com/InternScience/Awesome-Scientific-Skills","commit_stats":null,"previous_names":["internscience/awesome-scientific-skills"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/InternScience/Awesome-Scientific-Skills","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InternScience%2FAwesome-Scientific-Skills","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InternScience%2FAwesome-Scientific-Skills/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InternScience%2FAwesome-Scientific-Skills/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InternScience%2FAwesome-Scientific-Skills/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/InternScience","download_url":"https://codeload.github.com/InternScience/Awesome-Scientific-Skills/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InternScience%2FAwesome-Scientific-Skills/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35226918,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-07T02:00:07.222Z","response_time":90,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-skills","awesome-list","openclaw-skills","scientific-data","scientific-discovery","scientific-skill"],"created_at":"2026-07-05T23:00:20.600Z","updated_at":"2026-07-07T12:02:16.155Z","avatar_url":"https://github.com/InternScience.png","language":null,"funding_links":[],"categories":["Other Notable Awesome Lists!","Vibe Coding","Suites, Systems \u0026 Meta"],"sub_categories":["Awesome Lists \u0026 Ecosystem Maps"],"readme":"\u003cdiv align=\"center\"\u003e\n\n# Awesome Scientific Skills\n\n**An open, curated collection of Agent Skills for scientific research — clone it, use it, extend it.**\n\n**中文说明 / Chinese README:** [readme_CN.md](readme_CN.md)\n\n### **Latest News**\n\n- 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.\n- 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.\n\n\n[![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)\n\u003ca href=\"fig.jpg\"\u003e\u003cimg src=\"fig.jpg\" alt=\"Awesome Scientific Skills figure\" width=\"920\" /\u003e\u003c/a\u003e\n\n\n⭐ **Star us on GitHub! Your support means the world to us!** 🙏😊\n\n[Why this repo?](#why-this-repo) · [Skill Sources](#skill-sources) · [Categories](#scientific-skill-categories) · [Quick Start](#quick-start) · [Contributing](#contributing)\n\n\u003c/div\u003e\n\n---\n\n## The Problem\n\nThousands 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.\n\n## The Goal\n\nBuild 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.\n\n\u003e **Phase 1 (current):** A curated link collection — the reading list before the library.\n\u003e\n\u003e **Phase 2:** Import and reorganize selected skills into a unified directory structure.\n\u003e\n\u003e **Phase 3:** Composition recipes — multi-skill workflows for real research tasks.\n\n---\n\n## Why This Repo?\n\n| Feature | What it means for you |\n|---|---|\n| **Science-first curation** | Every skill is evaluated for relevance to real research workflows — not marketing demos |\n| **Fully clonable** | `git clone` once, get a working skill library — no account, no registry, no API key |\n| **Cross-agent compatible** | Works with Claude Code, Cursor, Codex, Gemini CLI, and any agent supporting the open [Agent Skills](https://agentskills.io) standard |\n| **Open \u0026 auditable** | Every skill's source is public. Review before you run |\n\n---\n\n## Skill Sources\n\nWe draw from two tiers of upstream repositories:\n\n### Official Skill Registries\n\n| Repository | Description |\n|---|---|\n| [anthropics/skills](https://github.com/anthropics/skills) | Anthropic's official Agent Skills — skill-creator, web artifacts, MCP builder, brand guidelines, and more |\n| [openai/skills](https://github.com/openai/skills) | OpenAI's official skill definitions |\n| [huggingface/skills](https://github.com/huggingface/skills) | Hugging Face's skill collection for model-centric workflows |\n| [openclaw/clawhub](https://github.com/openclaw/clawhub) | OpenClaw's community skill registry (13,700+ skills) |\n\n### Community Curations\n\n| Repository | Stars | Description |\n|---|---|---|\n| [VoltAgent/awesome-openclaw-skills](https://github.com/VoltAgent/awesome-openclaw-skills) | 25K+ | 5,400+ skills filtered from ClawHub — the largest community-curated awesome list |\n| [travisvn/awesome-claude-skills](https://github.com/travisvn/awesome-claude-skills) | 7K+ | Curated Claude Skills with detailed progressive-disclosure architecture docs |\n| [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 |\n| [heilcheng/awesome-agent-skills](https://github.com/heilcheng/awesome-agent-skills) | 2K+ | Cross-agent skill collection |\n| [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 |\n| [obra/superpowers/skills](https://github.com/obra/superpowers/tree/main/skills) | 68K+ | Opinionated \"superpowers\" skill set for power users |\n| [vercel-labs/agent-skills](https://github.com/vercel-labs/agent-skills) | 21K+ | Vercel Labs' experimental agent skill toolkit |\n| [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 |\n| [coreyhaines31/marketingskills](https://github.com/coreyhaines31/marketingskills) | 11K+ | Marketing-oriented agent skills for CRO, copywriting, SEO, analytics, and growth workflows |\n| [agentskills/agentskills](https://github.com/agentskills/agentskills) | 12K+ | Official specification and documentation for the open Agent Skills standard |\n| [kepano/obsidian-skills](https://github.com/kepano/obsidian-skills) | 12K+ | Agent skills for Obsidian workflows (Markdown, Bases, JSON Canvas, and CLI integration) |\n| [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 |\n| [ynulihao/AgentSkillOS](https://github.com/ynulihao/AgentSkillOS) | 233 | Searchable skill retrieval and orchestration system for building agents from 90,000+ skills |\n| [OthmanAdi/planning-with-files](https://github.com/OthmanAdi/planning-with-files) | 15K+ | Persistent markdown planning workflow skill for Claude Code |\n| [sickn33/antigravity-awesome-skills](https://github.com/sickn33/antigravity-awesome-skills) | 20K+ | Large cross-agent collection (900+ skills) for Claude Code, Antigravity, and Cursor |\n| [hesreallyhim/awesome-claude-code](https://github.com/hesreallyhim/awesome-claude-code) | 26K+ | Curated ecosystem list for Claude Code: skills, hooks, commands, apps, and plugins |\n| [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 |\n\n### Science-Specific\n\n#### Specialized Domain Tools (Top Priority)\n\n| Repository | Stars | Description |\n|---|---|---|\n| [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 |\n| [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 |\n\n#### Academic Writing\n\n| Repository | Stars | Description |\n|---|---|---|\n| [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 |\n| [HughYau/AcademicForge](https://github.com/HughYau/AcademicForge) | 250 | Curated skill collection for academic writing and research workflows (focused integration over broad skill quantity) |\n\n#### Literature Search\n\n| Repository | Stars | Description |\n|---|---|---|\n| [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 |\n| [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 |\n| [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 |\n\n#### Neuroscience\n\n| Repository | Stars | Description |\n|---|---|---|\n| [HughYau/neuroforge-skills](https://github.com/HughYau/neuroforge-skills) | 1 | Neuroscience skill set built around major Python toolchains (Brian2, MNE-Python, Nilearn, SpikeInterface, pyNIBS) |\n| [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 |\n\n---\n\n## Scientific Skill Categories\n\nBelow 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.\n\n### Wet-Lab \u0026 Life Sciences\n\n- [x] **Bioinformatics \u0026 Genomics** — sequence analysis, single-cell RNA-seq (Scanpy), variant annotation, phylogenetics, gene regulatory networks\n- [x] **Cheminformatics \u0026 Drug Discovery** — molecular property prediction (RDKit), docking, ADMET, compound library search (ChEMBL)\n- [x] **Structural Biology** — protein structure prediction, PDB retrieval, molecular visualization\n- [x] **Clinical \u0026 Medical Research** — ClinicalTrials.gov search, ICD coding, adverse event analysis, COSMIC/TCGA queries\n\n### Computational \u0026 Data Science\n\n- [x] **Statistical Analysis** — hypothesis testing, Bayesian inference, survival analysis, power calculations\n- [x] **Machine Learning for Science** — PyTorch Lightning workflows, scikit-learn pipelines, hyperparameter tuning\n- [ ] **Simulation \u0026 Modeling** — molecular dynamics, finite element analysis, agent-based modeling\n- [ ] **High-Performance Computing** — job submission (SLURM/PBS), distributed training, GPU profiling\n\n### Literature \u0026 Knowledge\n\n- [x] **Literature Search \u0026 Retrieval** — PubMed, arXiv, Semantic Scholar, CrossRef, DOI resolution\n- [x] **Scientific Writing** — paper drafting, grant proposals, peer review assistance, citation management\n- [ ] **Knowledge Graphs** — ontology navigation (Gene Ontology, MeSH), entity linking, relationship extraction\n\n### Research Operations\n\n- [x] **Data Wrangling** — tabular data cleaning, format conversion, missing data imputation\n- [x] **Visualization** — publication-quality plots (Matplotlib/Seaborn), interactive dashboards, figure layout\n- [ ] **Reproducibility** — environment capture, notebook-to-pipeline conversion, data provenance tracking\n- [x] **Document Processing** — PDF extraction, DOCX/PPTX generation, LaTeX compilation\n\n### Quantitative \u0026 Financial Research\n\n- [x] **Financial Data** — SEC EDGAR, Alpha Vantage, OFR Hedge Fund Monitor, Treasury fiscal data\n- [ ] **Econometrics** — time series analysis, causal inference, panel data methods\n\n---\n\n## Quick Start\n\n### Option 1 — Browse and pick\n\nExplore the [Skill Sources](#Skill Sources) above, find what you need, and copy individual skill folders into your project:\n\n```\nyour-project/\n└── .claude/\n    └── skills/\n        ├── pubmed-search/\n        ├── rdkit-molecular-analysis/\n        └── scientific-writer/\n```\n\n### Option 2 — Clone the science stack (Phase 2)\n\n```bash\n# Coming soon — once we consolidate skills into this repo\ngit clone https://github.com/InternScience/Awesome-Scientific-Skills.git\ncp -r Awesome-Scientific-Skills/skills/ your-project/.claude/skills/\n```\n\n### Compatibility\n\nSkills follow the open [Agent Skills](https://agentskills.io) specification. They work with:\n\n- **Claude Code** — `/skills` or `.claude/skills/` directory\n- **Cursor** — reads from `.claude/skills/` and `.codex/skills/`\n- **Codex** — `.codex/skills/` directory\n- **Gemini CLI / Antigravity** — compatible via the Agent Skills standard\n\n---\n\n## Selection Criteria\n\nNot every skill makes the cut. We apply these filters:\n\n| Criterion | Requirement |\n|---|---|\n| **Scientific relevance** | Must serve a real research workflow — not a demo or toy example |\n| **Source quality** | Published by a known team or actively maintained community project |\n| **Documentation** | Clear SKILL.md with description, usage, and dependencies |\n| **Open license** | MIT, Apache 2.0, or equivalent permissive license |\n| **Security** | No network calls without explicit disclosure; no credential harvesting |\n| **Non-redundant** | If two skills do the same thing, we keep the better-maintained one |\n\n---\n\n## Contributing\n\nContributions are welcome. This is a curated list — quality over quantity.\n\n**To suggest a skill:**\n\n1. Fork this repository\n2. Add the skill to the appropriate section in `readme.md` with format:\n   ```\n   | [skill-name](https://github.com/...) | Brief description of what it does |\n   ```\n3. Submit a Pull Request with a short note on why this skill is useful for scientific research\n\n**What we're looking for:**\n\n- Skills that solve real problems researchers face daily\n- Skills that compose well with others (e.g., a search skill whose output feeds into an analysis skill)\n- Skills maintained by their authors — not abandoned after initial commit\n\n**What we don't accept:**\n\n- Crypto/blockchain/DeFi skills (off-scope)\n- Skills with no documentation\n- Bulk-generated or spam skills\n- Skills that require proprietary backends without free tiers\n\n---\n\n## Security Notice\n\n\u003e 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.\n\n---\n\n## Roadmap\n\n- [x] Phase 1 — Curated link collection with source taxonomy\n- [ ] Phase 2 — Community skill registry with ratings and usage metrics\n- [ ] Phase 3 — Test skill in OpenClaw and Claude Code\n- [ ] Phase 4 — Develop skill creator which can create skill from paper and agentic trace\n\n---\n\n## Related Projects\n\nCompanion open-source tools from our team for skill generation and repository evaluation:\n\n| Project | Description |\n|---|---|\n| [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 |\n| [K-Dense-AI/claude-skills-mcp](https://github.com/K-Dense-AI/claude-skills-mcp) | MCP server for vector-search-based skill retrieval |\n| [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 |\n| [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 |\n| [agentskills.io](https://agentskills.io) | The open Agent Skills specification |\n\n---\n\n## License\n\nThis curated list is released under [MIT](LICENSE). Individual skills retain their own licenses as specified in their respective `SKILL.md` files.\n\n---\n\n\u003cdiv align=\"center\"\u003e\n**If this saves you time in your research, give it a star and share it with your lab.**\n\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FInternScience%2FAwesome-Scientific-Skills","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FInternScience%2FAwesome-Scientific-Skills","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FInternScience%2FAwesome-Scientific-Skills/lists"}