claude-scientific-skills

Comprehensive collection of 128+ ready-to-use scientific skills for Claude enabling research across biology, chemistry, medicine, genomics, and adva…

执行命令联网写文件读环境变量（配置）严重 88 · 高危 6Microck/ordinary-claude-skills

它会碰到什么

扫了多少630 个文本文件，7191 KB

它会碰到什么执行命令联网写文件读环境变量（配置）

命中总数794 处

命中统计严重 88 · 高 6 · 中 3 · 低 16

关于「读环境变量（配置）」：这个技能会读 process.env 之类的环境变量，但读到的都是端口、目录、超时这类配置项，没有读取密钥类变量。扫描规则原本把「读环境变量」一律算作「读凭据」，本站按变量名做了细化区分，命中明细仍如实列在下面。

逐条看命中（30 条严重或高危）

严重 docs/scientific-skills.md:157cred-paths

- **Generate Image** - AI-powered image generation and editing for scientific illustrations, schematics, and visualizations using OpenRouter's image generation

严重 README.md:109exec-pipe-to-shell

curl -fsSL https://claude.ai/install.sh | bash

严重 README.md:177exec-pipe-to-shell

curl -LsSf https://astral.sh/uv/install.sh | sh

严重 scientific-skills/adaptyv/reference/api_reference.md:6cred-paths

https://kq5jp7qj7wdqklhsxmovkzn4l40obksv.lambda-url.eu-central-1.on.aws

严重 scientific-skills/adaptyv/reference/examples.md:17cred-paths

BASE_URL = "https://kq5jp7qj7wdqklhsxmovkzn4l40obksv.lambda-url.eu-central-1.on.aws"

严重 scientific-skills/adaptyv/reference/examples.md:40cred-paths
```
Create a `.env` file:
```

严重 scientific-skills/adaptyv/reference/protein_optimization.md:600cred-paths

"https://kq5jp7qj7wdqklhsxmovkzn4l40obksv.lambda-url.eu-central-1.on.aws/experiments",

严重 scientific-skills/adaptyv/SKILL.md:24cred-paths
```
Or create a `.env` file:
```

严重 scientific-skills/adaptyv/SKILL.md:50cred-paths

base_url = "https://kq5jp7qj7wdqklhsxmovkzn4l40obksv.lambda-url.eu-central-1.on.aws"

严重 scientific-skills/alphafold-database/references/api_reference.md:304exec-pipe-to-shell
```
curl https://sdk.cloud.google.com | bash
```
严重 scientific-skills/benchling-integration/references/authentication.md:181cred-paths
```
# Load from .env file (add .env to .gitignore!)
```
严重 scientific-skills/benchling-integration/references/authentication.md:181cred-paths
```
# Load from .env file (add .env to .gitignore!)
```
严重 scientific-skills/biomni/references/llm_providers.md:29cred-paths
```
# Or in .env file
```
严重 scientific-skills/biomni/references/llm_providers.md:30cred-paths
```
echo "ANTHROPIC_API_KEY=sk-ant-..." >> .env
```

严重 scientific-skills/biomni/SKILL.md:41cred-paths

Configure API keys (store in `.env` file or environment variables):

严重 scientific-skills/biomni/SKILL.md:290cred-paths
```
# Or check .env file in working directory
```
严重 scientific-skills/denario/references/installation.md:66cred-paths
```
docker run -p 8501:8501 --env-file .env --rm pablovd/denario:latest
```
严重 scientific-skills/denario/references/llm_configuration.md:70cred-paths
```
export GOOGLE_APPLICATION_CREDENTIALS="/path/to/credentials.json"
```
严重 scientific-skills/denario/references/llm_configuration.md:82cred-paths
```
### Method 2: .env Files
```
严重 scientific-skills/denario/references/llm_configuration.md:84cred-paths
```
Create a `.env` file in your project directory:
```
严重 scientific-skills/denario/references/llm_configuration.md:116cred-paths
```
docker run -p 8501:8501 --env-file .env --rm pablovd/denario:latest
```
严重 scientific-skills/denario/references/llm_configuration.md:121cred-paths
```
-e GOOGLE_APPLICATION_CREDENTIALS=/credentials.json \
```
严重 scientific-skills/denario/references/llm_configuration.md:122cred-paths
```
-v /local/path/to/creds.json:/credentials.json \
```
严重 scientific-skills/denario/references/llm_configuration.md:137exec-pipe-to-shell
```
curl https://sdk.cloud.google.com | bash
```
严重 scientific-skills/denario/references/llm_configuration.md:167cred-paths
```
gcloud iam service-accounts keys create credentials.json \
```
严重 scientific-skills/denario/references/llm_configuration.md:175cred-paths
```
os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = '/path/to/credentials.json'
```
严重 scientific-skills/denario/references/llm_configuration.md:226cred-paths
```
```gitignore
```
严重 scientific-skills/denario/references/llm_configuration.md:229cred-paths
```
credentials.json
```
严重 scientific-skills/denario/references/llm_configuration.md:249cred-paths
```
- Check `.env` file is in correct directory
```
严重 scientific-skills/denario/references/llm_configuration.md:263cred-paths
```
- Use `docker run --env-file .env` to pass environment
```

这一栏是扫描器报的事实，不是结论。命中多不等于有毒（安全工具、规则库、示例脚本本来就会包含危险写法），命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系，需要你自己看。

技能内容

Claude Scientific Skills Collection

A comprehensive collection of 128+ ready-to-use scientific skills that transforms Claude into an AI research assistant capable of executing complex multi-step scientific workflows.

Scientific Domains

🧬 Bioinformatics & Genomics

Sequence analysis, single-cell RNA-seq, gene regulatory networks, variant annotation, phylogenetic analysis

🧪 Cheminformatics & Drug Discovery

Molecular property prediction, virtual screening, ADMET analysis, molecular docking, lead optimization

🔬 Proteomics & Mass Spectrometry

LC-MS/MS processing, peptide identification, spectral matching, protein quantification

🏥 Clinical Research & Precision Medicine

Clinical trials, pharmacogenomics, variant interpretation, drug safety, precision therapeutics

🧠 Healthcare AI & Clinical ML

EHR analysis, physiological signal processing, medical imaging, clinical prediction models

🖼️ Medical Imaging & Digital Pathology

DICOM processing, whole slide image analysis, computational pathology, radiology workflows

🤖 Machine Learning & AI

Deep learning, reinforcement learning, time series analysis, model interpretability, Bayesian methods

🔮 Materials Science & Chemistry

Crystal structure analysis, phase diagrams, metabolic modeling, computational chemistry

🌌 Physics & Astronomy

Astronomical data analysis, cosmological calculations, symbolic mathematics, physics computations

⚙️ Engineering & Simulation

Discrete-event simulation, optimization, metabolic engineering, systems modeling

Included Skill Categories

26+ Scientific Databases - OpenAlex, PubMed, ChEMBL, UniProt, COSMIC, ClinicalTrials.gov
54+ Python Packages - RDKit, Scanpy, PyTorch, scikit-learn, BioPython, PennyLane, Qiskit
15+ Scientific Integrations - Benchling, DNAnexus, LatchBio, OMERO, Protocols.io
20+ Analysis & Communication Tools - Literature review, scientific writing, peer review

Getting Started

Each skill within this collection includes:

Comprehensive documentation (SKILL.md)
Practical code examples
Use cases and best practices
Integration guides
Reference materials

Explore the scientific-skills/ subdirectory for individual skill implementations and detailed documentation.

想直接用这个技能？

本站把开放许可（MIT / Apache 等）的技能按仓库打包整理到网盘，点一下转存到你自己的网盘，不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接，不打包。

去原始仓库

它属于哪个仓库

仓库Microck/ordinary-claude-skills

星标★ 398

本站分层T2

该仓技能数2148

原文件路径skills_categorized/scientific-computing/claude-scientific-skills/SKILL.md

同一个仓库里的其他技能

看这个仓库的全部 2148 个技能

同名技能的其他版本

有 2 个不同仓库或目录里都有叫 claude-scientific-skills 的技能。它们内容并不相同，别混用：

Microck/ordinary-claude-skills — Comprehensive collection of 128+ ready-to-use scientific skills for Claude enabling resear