skills/cas/SKILL.md
Look up chemicals in CAS Common Chemistry (name, CAS RN, SMILES, InChI; ~500k compounds)
npx skillsauth add lamm-mit/scienceclaw casInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Query CAS Common Chemistry for compound names, CAS Registry Numbers®, molecular formula, mass, SMILES, InChI, and experimental properties. Covers nearly 500,000 compounds (CC BY-NC 4.0).
API access: Request a free API key at https://www.cas.org/services/commonchemistry-api. The script works without a key for public endpoints; if CAS requires a key, set CAS_API_KEY or use ~/.scienceclaw/cas_config.json.
aspirin*), CAS RN, SMILES, or InChI/InChIKeyreferences/cas-common-chemistry-api.mdpython3 {baseDir}/scripts/cas_search.py --query "aspirin"
python3 {baseDir}/scripts/cas_search.py --cas "50-78-2"
python3 {baseDir}/scripts/cas_search.py --query "atrazin*"
python3 {baseDir}/scripts/cas_search.py --query "caffeine" --format json
| Parameter | Description | Default |
|-----------|-------------|---------|
| --query | Name, SMILES, or InChI (name supports trailing *) | - |
| --cas | CAS Registry Number (e.g. 50-78-2) | - |
| --max-results | Max search results | 10 |
| --format | summary, detailed, json | summary |
CAS_API_KEY or config file if CAS requires authenticationtools
Onboard and manage Paperclip AI for research-paper knowledge and agent orchestration
development
Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.
testing
Generate a structured scientific PDF report from a JSON description. Accepts a JSON file specifying title, authors, abstract, sections (headings, text, tables, figures), and inline data panels (heatmap, bar, scatter, line). Produces a publication-style A4 PDF using reportlab with no LaTeX dependency. All figures are either loaded from PNG paths or generated on-the-fly from inline data.
development
Execute arbitrary Python code and return stdout. NumPy, pandas, scipy, matplotlib, and other scientific libraries are available.