Skip to content
Back to search

SciAgent-Skills

197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Powers OmicsHorizon.

Safety scan

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

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/jaechang-hits/SciAgent-Skills with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/jaechang-hits/SciAgent-Skills'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/jaechang-hits--sciagent-skills/badge.svg)](/listings/jaechang-hits--sciagent-skills)

HTML

<a href="/listings/jaechang-hits--sciagent-skills"><img src="/api/listings/jaechang-hits--sciagent-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.

These steps run a script from the network that findsafeskills does not scan.

Prerequisites

- An AI coding agent: [Claude Code](https://docs.anthropic.com/en/docs/claude-code), [OpenAI Codex CLI](https://github.com/openai/codex), [Cursor](https://www.cursor.com/), or [Windsurf](https://windsurf.com/) - Git - Python 3.12+ (only needed if you want to run validation scripts)

> **Note:** SciAgent-Skills is **not** an npm package. Skills are plain markdown files read directly by your AI agent — no `npx`, `npm install`, or runtime dependencies needed. Just clone the repository and point your agent at the skill files.

Step 1: Clone the Repository

git clone https://github.com/jaechang-hits/SciAgent-Skills.git
cd SciAgent-Skills

Step 2: Choose Your Setup Method

Method A: Claude Code Plugin (Recommended)

Load SciAgent-Skills as a Claude Code plugin for the current session:

claude --plugin-dir /path/to/SciAgent-Skills

To verify the plugin loaded, run `/plugin` inside Claude Code and check that `sciagent-skills` appears in the Installed tab.

Skills become available as `/sciagent-skills:<skill-name>`:

/sciagent-skills:scanpy-scrna-seq
/sciagent-skills:rdkit-cheminformatics
/sciagent-skills:pymc-bayesian-modeling

Or just describe your task — the agent finds the relevant skill automatically:

> "Perform differential expression analysis on this RNA-seq count matrix"

**Persistent installation** — to load the plugin automatically in every session, use the plugin install command inside Claude Code:

/plugin marketplace add jaechang-hits/SciAgent-Skills
/plugin install sciagent-skills

Method B: Project-Level Integration (Claude Code)

Clone into your project directory:

cd your-project
git clone https://github.com/jaechang-hits/SciAgent-Skills.git .sciagent-skills

Add the canonical guidance to your project's `AGENTS.md`:

## Scientific Skills
Reference skills in `.sciagent-skills/skills/` for domain-specific analysis.
Registry: `.sciagent-skills/registry.yaml`

If the project does not already have a `CLAUDE.md`, add this compatibility shim so Claude Code imports the same guidance:

@AGENTS.md

Using with Other Agents

SciAgent-Skills works with any AI agent that can read project files. Clone the repo into your project, then configure the agent to discover skills via `registry.yaml`.

**Method C: OpenAI Codex CLI**

cd your-project
git clone https://github.com/jaechang-hits/SciAgent-Skills.git .sciagent-skills
cp .sciagent-skills/integration-templates/AGENTS.md ./AGENTS.md

Codex reads `AGENTS.md` at the project root automatically. If you already have an `AGENTS.md`, append the contents from the template.

**Method D: Cursor**

cd your-project
git clone https://github.com/jaechang-hits/SciAgent-Skills.git .sciagent-skills
mkdir -p .cursor/rules
cp .sciagent-skills/integration-templates/cursor-rules.md .cursor/rules/sciagent-skills.md

Cursor loads rules from `.cursor/rules/` automatically. Alternatively, you can use the `AGENTS.md` template — Cursor supports it as well.

**Method E: Windsurf**

cd your-project
git clone https://github.com/jaechang-hits/SciAgent-Skills.git .sciagent-skills
mkdir -p .windsurf/rules
cp .sciagent-skills/integration-templates/windsurf-rules.md .windsurf/rules/sciagent-skills.md

Windsurf loads rules from `.windsurf/rules/` automatically. Alternatively, you can use the `AGENTS.md` template — Windsurf supports it as well.

**Other agents**: If your agent reads project files, clone the repo as `.sciagent-skills/` and instruct the agent (via its config mechanism) to read `.sciagent-skills/registry.yaml` for skill discovery.

Step 3: Install Dependencies

cd SciAgent-Skills
pixi install

[Pixi](https://pixi.sh) handles the Python environment and all required packages. If you don't have pixi installed:

curl -fsSL https://pixi.sh/install.sh | bash

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.

.claude-plugin/marketplace.json · Manifest · 33 lines

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

  1. {
  2. "name": "sciagent-skills",
  3. "owner": {
  4. "name": "jaechang-hits"
  5. },
  6. "metadata": {
  7. "description": "197 validated life sciences skills for Claude Code",
  8. "version": "1.0.0"
  9. },
  10. "plugins": [
  11. {
  12. "name": "sciagent-skills",
  13. "source": "./",
  14. "description": "197 validated life sciences skills — genomics, proteomics, drug discovery, biostatistics, scientific computing",
  15. "version": "1.0.0",
  16. "author": {
  17. "name": "jaechang-hits"
  18. },
  19. "homepage": "https://github.com/jaechang-hits/SciAgent-Skills",
  20. "repository": "https://github.com/jaechang-hits/SciAgent-Skills",
  21. "license": "CC-BY-4.0",
  22. "keywords": [
  23. "life-sciences",
  24. "bioinformatics",
  25. "drug-discovery",
  26. "genomics",
  27. "scientific-computing"
  28. ],
  29. "category": "scientific-research",
  30. "tags": ["science", "biology", "chemistry", "ai-scientist"]
  31. }
  32. ]
  33. }
README.md · README · 311 lines · 1 finding marked

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

  1. # SciAgent-Skills
  2. <p align="center">
  3. <img src="https://img.shields.io/badge/skills-199-blue?style=for-the-badge" alt="199 Skills">
  4. <img src="https://img.shields.io/badge/BixBench-92.0%25-brightgreen?style=for-the-badge" alt="BixBench 92.0%">
  5. <img src="https://img.shields.io/badge/license-CC--BY--4.0-lightgrey?style=for-the-badge" alt="CC-BY-4.0">
  6. <img src="https://img.shields.io/github/stars/jaechang-hits/SciAgent-Skills?style=for-the-badge" alt="GitHub Stars">
  7. </p>
  8. > **Turn your AI coding agent into a life sciences expert** — 199 bioinformatics skills for Claude Code covering RNA-seq, single-cell analysis, genomics, proteomics, drug discovery, and more. Boosted [BixBench](https://github.com/Future-House/BixBench) from 65% to 92%. Open source.
  9. **SciAgent-Skills** is the largest open-source skill library for scientific AI agents. It equips [Claude Code](https://docs.anthropic.com/en/docs/claude-code) (and any markdown-compatible agent) with domain-specific knowledge for computational biology, bioinformatics, cheminformatics, and biostatistics — no fine-tuning required, just plug in and analyze.
  10. **Keywords:** bioinformatics AI agent, Claude Code skills, scientific computing, RNA-seq analysis, single-cell RNA-seq, drug discovery pipeline, protein structure prediction, computational biology tools, life science automation, BixBench benchmark
  11. ## Benchmark: 92.0% on BixBench-Verified-50
  12. <p align="center">
  13. <img src="assets/benchmark.png" alt="BixBench bioinformatics benchmark results — SciAgent-Skills achieves 92.0% accuracy" width="700">
  14. </p>
  15. [BixBench](https://github.com/Future-House/BixBench) is a benchmark for evaluating AI agents on real-world bioinformatics tasks. **SciAgent-Skills achieved 92.0% accuracy** on BixBench-Verified-50, the highest among all tested systems:
  16. | System | BixBench-Verified-50 Accuracy |
  17. |--------|:----------------------------:|
  18. | Claude Code (Opus 4.6) **+ SciAgent-Skills** | **92.0%** |
  19. | Claude Code (Opus 4.6) baseline | 65.3% |
  20. Simply equipping Claude Code with these domain-specific skills yields a **+26.7 percentage point improvement** — no fine-tuning, no custom model, just structured scientific knowledge.
  21. ## Try It Now — HyperLab
  22. Want to try these skills without any setup? **[HyperLab](https://hyperlab.ai/en/)** (하이퍼랩) is the web platform powered by SciAgent-Skills. Sign up and start analyzing your bioinformatics data directly in your browser — RNA-seq, proteomics, drug screening, and more.
  23. [![Try HyperLab](https://img.shields.io/badge/Try-HyperLab-blue?style=for-the-badge)](https://hyperlab.ai/en/)
  24. ---
  25. **199 ready-to-use scientific skills for AI coding agents** — covering genomics, proteomics, drug discovery, biostatistics, scientific computing, and scientific writing.
  26. Each skill is a self-contained SKILL.md file with runnable code examples, key parameters, troubleshooting guides, and best practices. Designed for [Claude Code](https://docs.anthropic.com/en/docs/claude-code), but compatible with any AI agent that reads markdown skill files ([setup guides below](#using-with-other-agents)).
  27. ## What's Inside
  28. | Category | Skills | Examples |
  29. |----------|:------:|----------|
  30. | Genomics & Bioinformatics | 65 | Scanpy, BioPython, pysam, gget, KEGG, PubMed, scvi-tools, Bakta, Roary |
  31. | Structural Biology & Drug Discovery | 26 | RDKit, AutoDock Vina, ChEMBL, PDB, DeepChem, datamol |
  32. | Scientific Computing | 24 | Polars, Dask, NetworkX, SymPy, UMAP, PyG, Zarr, SimPy |
  33. | Cell Biology | 15 | pydicom, histolab, FlowIO |
  34. | Biostatistics | 12 | scikit-learn, statsmodels, PyMC, SHAP, survival analysis |
  35. | Scientific Writing | 21 | Manuscript writing, peer review, LaTeX posters, slides, figure guides |
  36. | Systems Biology & Multi-omics | 11 | COBRApy, LaminDB, Reactome, STRING |
  37. | Proteomics & Protein Engineering | 10 | ESM, UniProt, PyOpenMS, matchms, HMDB |
  38. | Lab Automation | 6 | Opentrons, Benchling |
  39. | Data Visualization | 5 | Plotly, Seaborn |
  40. | Molecular Biology | 3 | CRISPR sgRNA design, gene expression, cloning |
  41. **Skill types:** 72 toolkits, 53 database connectors, 37 guides, 37 pipelines
  42. ## Installation
  43. ### Prerequisites
  44. - An AI coding agent: [Claude Code](https://docs.anthropic.com/en/docs/claude-code), [OpenAI Codex CLI](https://github.com/openai/codex), [Cursor](https://www.cursor.com/), or [Windsurf](https://windsurf.com/)
  45. - Git
  46. - Python 3.12+ (only needed if you want to run validation scripts)
  47. > **Note:** SciAgent-Skills is **not** an npm package. Skills are plain markdown files read directly by your AI agent — no `npx`, `npm install`, or runtime dependencies needed. Just clone the repository and point your agent at the skill files.
  48. ### Step 1: Clone the Repository
  49. ```bash
  50. git clone https://github.com/jaechang-hits/SciAgent-Skills.git
  51. cd SciAgent-Skills
  52. ```
  53. ### Step 2: Choose Your Setup Method
  54. #### Method A: Claude Code Plugin (Recommended)
  55. Load SciAgent-Skills as a Claude Code plugin for the current session:
  56. ```bash
  57. claude --plugin-dir /path/to/SciAgent-Skills
  58. ```
  59. To verify the plugin loaded, run `/plugin` inside Claude Code and check that `sciagent-skills` appears in the Installed tab.
  60. Skills become available as `/sciagent-skills:<skill-name>`:
  61. ```
  62. /sciagent-skills:scanpy-scrna-seq
  63. /sciagent-skills:rdkit-cheminformatics
  64. /sciagent-skills:pymc-bayesian-modeling
  65. ```
  66. Or just describe your task — the agent finds the relevant skill automatically:
  67. > "Perform differential expression analysis on this RNA-seq count matrix"
  68. **Persistent installation** — to load the plugin automatically in every session, use the plugin install command inside Claude Code:
  69. ```
  70. /plugin marketplace add jaechang-hits/SciAgent-Skills
  71. /plugin install sciagent-skills
  72. ```
  73. #### Method B: Project-Level Integration (Claude Code)
  74. Clone into your project directory:
  75. ```bash
  76. cd your-project
  77. git clone https://github.com/jaechang-hits/SciAgent-Skills.git .sciagent-skills
  78. ```
  79. Add the canonical guidance to your project's `AGENTS.md`:
  80. ```markdown
  81. ## Scientific Skills
  82. Reference skills in `.sciagent-skills/skills/` for domain-specific analysis.
  83. Registry: `.sciagent-skills/registry.yaml`
  84. ```
  85. If the project does not already have a `CLAUDE.md`, add this compatibility shim so Claude Code imports the same guidance:
  86. ```markdown
  87. @AGENTS.md
  88. ```
  89. #### Using with Other Agents
  90. SciAgent-Skills works with any AI agent that can read project files. Clone the repo into your project, then configure the agent to discover skills via `registry.yaml`.
  91. **Method C: OpenAI Codex CLI**
  92. ```bash
  93. cd your-project
  94. git clone https://github.com/jaechang-hits/SciAgent-Skills.git .sciagent-skills
  95. cp .sciagent-skills/integration-templates/AGENTS.md ./AGENTS.md
  96. ```
  97. Codex reads `AGENTS.md` at the project root automatically. If you already have an `AGENTS.md`, append the contents from the template.
  98. **Method D: Cursor**
  99. ```bash
  100. cd your-project
  101. git clone https://github.com/jaechang-hits/SciAgent-Skills.git .sciagent-skills
  102. mkdir -p .cursor/rules
  103. cp .sciagent-skills/integration-templates/cursor-rules.md .cursor/rules/sciagent-skills.md
  104. ```
  105. Cursor loads rules from `.cursor/rules/` automatically. Alternatively, you can use the `AGENTS.md` template — Cursor supports it as well.
  106. **Method E: Windsurf**
  107. ```bash
  108. cd your-project
  109. git clone https://github.com/jaechang-hits/SciAgent-Skills.git .sciagent-skills
  110. mkdir -p .windsurf/rules
  111. cp .sciagent-skills/integration-templates/windsurf-rules.md .windsurf/rules/sciagent-skills.md
  112. ```
  113. Windsurf loads rules from `.windsurf/rules/` automatically. Alternatively, you can use the `AGENTS.md` template — Windsurf supports it as well.
  114. **Other agents**: If your agent reads project files, clone the repo as `.sciagent-skills/` and instruct the agent (via its config mechanism) to read `.sciagent-skills/registry.yaml` for skill discovery.
  115. ### Step 3: Install Dependencies
  116. ```bash
  117. cd SciAgent-Skills
  118. pixi install
  119. ```
  120. [Pixi](https://pixi.sh) handles the Python environment and all required packages. If you don't have pixi installed:
  121. ```bash
  122. curl -fsSL https://pixi.sh/install.sh | bash
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 180 on GitHub
  123. ```
  124. ## How Skills Work
  125. Each skill follows a structured template:
  126. ```
  127. skills/<category>/<skill-name>/
  128. SKILL.md # Main skill file (300-550 lines)
  129. references/ # Optional deep-dive reference files
  130. assets/ # Optional templates, configs
  131. ```
  132. A **SKILL.md** contains:
  133. - **Frontmatter** — name, description, license (for agent discovery)
  134. - **Overview & When to Use** — what the tool does and when to reach for it
  135. - **Prerequisites** — packages, data, environment setup
  136. - **Quick Start** — minimal copy-paste example
  137. - **Workflow / Core API** — step-by-step pipeline or module-by-module API guide
  138. - **Key Parameters** — tunable settings with defaults and ranges
  139. - **Common Recipes** — self-contained snippets for common tasks
  140. - **Troubleshooting** — problem/cause/solution table
  141. The agent reads only the `description` field during planning. Full skill content is loaded on demand when relevant.
  142. ## Directory Structure
  143. ```
  144. SciAgent-Skills/
  145. ├── .claude-plugin/
  146. │ └── plugin.json # Claude Code plugin manifest
  147. ├── integration-templates/ # Config templates for Codex, Cursor, Windsurf
  148. ├── skills/ # All 199 skills organized by category
  149. │ ├── genomics-bioinformatics/
  150. │ ├── structural-biology-drug-discovery/
  151. │ ├── scientific-computing/
  152. │ ├── cell-biology/
  153. │ ├── biostatistics/
  154. │ ├── scientific-writing/
  155. │ ├── systems-biology-multiomics/
  156. │ ├── proteomics-protein-engineering/
  157. │ ├── lab-automation/
  158. │ ├── data-visualization/
  159. │ └── molecular-biology/
  160. ├── templates/ # Skill authoring templates
  161. ├── registry.yaml # Index of all skills
  162. ├── AGENTS.md # Skill authoring guide
  163. └── scripts/
  164. └── validate_registry.py
  165. ```
  166. ## Example Use Cases
  167. **Single-Cell RNA-seq Analysis** (scRNA-seq)
  168. > "Load 10X data, QC filter, normalize, cluster, find marker genes, and annotate cell types"
  169. Uses: `anndata-data-structure` → `scanpy-scrna-seq`
  170. **Bulk RNA-seq Differential Expression**
  171. > "Run DESeq2-style differential expression analysis on this count matrix, generate volcano plot"
  172. Uses: `pydeseq2-differential-expression` → `matplotlib-scientific-plotting`
  173. **Drug Discovery Pipeline**
  174. > "Search ChEMBL for EGFR inhibitors with IC50 < 100nM, filter with Lipinski rules using RDKit, dock top candidates with AutoDock Vina"
  175. Uses: `chembl-database-bioactivity` → `rdkit-cheminformatics` → `autodock-vina-docking`
  176. **Protein Structure Prediction & Analysis**
  177. > "Get the AlphaFold structure for UniProt P04637, assess confidence, find high-confidence binding regions"
  178. Uses: `uniprot-protein-database` → `alphafold-database-access`
  179. **Bayesian Biostatistics**
  180. > "Fit a hierarchical Bayesian model to this clinical trial data with patient-level random effects"
  181. Uses: `pymc-bayesian-modeling` → `matplotlib-scientific-plotting`
  182. **Multi-omics Integration**
  183. > "Integrate transcriptomics and proteomics data, run pathway enrichment, build a protein interaction network"
  184. Uses: `lamindb-data-management` → `reactome-pathway-analysis` → `string-protein-interaction`
  185. ## Contributing
  186. ### Adding a New Skill
  187. 1. Read `AGENTS.md` for the full authoring workflow
  188. 2. Classify your topic (pipeline / toolkit / database / guide)
  189. 3. Pick a category from the table above
  190. 4. Use the appropriate template from `templates/`
  191. 5. Add the entry to `registry.yaml`
  192. 6. Validate: `python scripts/validate_registry.py`
  193. ### Skill Templates
  194. | Template | Use When |
  195. |----------|----------|
  196. | `SKILL_TEMPLATE.md` | Linear input→process→output pipeline (e.g., DESeq2) |
  197. | `SKILL_TEMPLATE_TOOLKIT.md` | Collection of independent modules (e.g., RDKit) |
  198. | `SKILL_TEMPLATE_PROSE.md` | Conceptual guide, decision frameworks (e.g., statistical test selection) |
  199. ## Requirements
  200. - Python 3.12+ (for validation scripts)
  201. - No runtime dependencies — skills are markdown files read by the agent
  202. - Individual skills list their own tool-specific prerequisites (e.g., `pip install scanpy`)
  203. ## Comparison with Other Tools
  204. | Feature | SciAgent-Skills | GPTomics/bioSkills | ClawBio |
  205. |---------|:-:|:-:|:-:|
  206. | Total skills | **199** | ~30 | ~20 |
  207. | BixBench benchmark | **92.0%** | — | — |
  208. | Skill types | Pipeline, Toolkit, Database, Guide | Pipeline | Pipeline |
  209. | Multi-agent support | Claude Code, Codex, Cursor, Windsurf | Claude Code | Claude Code |
  210. | Claude Code plugin | Yes | No | No |
  211. | Web platform | [HyperLab](https://hyperlab.ai/en/) | No | No |
  212. ## License
  213. CC-BY-4.0 for original content. Individual skills note the license of their underlying tools.
  214. ## Acknowledgments
  215. This project builds on 50+ open-source scientific Python packages. If you find a skill useful, consider starring the underlying tool's repository and supporting its maintainers.
  216. ---
  217. <sub>**Related searches:** bioinformatics AI agent, Claude Code scientific skills, RNA-seq analysis tool, single-cell RNA-seq AI, drug discovery AI pipeline, protein structure prediction, computational biology automation, life science AI tools, 바이오인포매틱스 AI, 오믹스 호라이즌, 생명과학 AI 에이전트, BixBench benchmark</sub>

Ratings and comments

Sign in to rate this skill.

Sign in

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