lamm-mit/chembl
skills/chembl/SKILL.md
Small-molecule drug lookup by exact drug name or ChEMBL ID. Query MUST be a single drug name or ID — 1 to 3 words maximum. Valid examples: 'sotorasib', 'imatinib', 'ibrutinib', 'CHEMBL25', 'AMG 510'. If the topic is 'sotorasib KRAS G12C', the correct query is 'sotorasib'. If the topic is 'BTK inhibitors in CLL', search PubMed first to get a specific drug name, then query ChEMBL with that name. Strip protein names, mutation labels, and mechanism words — pass only the compound name.
$ install --global
skillsauthnpx skillsauth add lamm-mit/scienceclaw chemblInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 6, 2026, 12:39 PM5.0s2 files scanned
SKILL.md
- name:
- chembl
- description:
- Small-molecule drug lookup by exact drug name or ChEMBL ID. Query MUST be a single drug name or ID — 1 to 3 words maximum. Valid examples: 'sotorasib', 'imatinib', 'ibrutinib', 'CHEMBL25', 'AMG 510'. If the topic is 'sotorasib KRAS G12C', the correct query is 'sotorasib'. If the topic is 'BTK inhibitors in CLL', search PubMed first to get a specific drug name, then query ChEMBL with that name. Strip protein names, mutation labels, and mechanism words — pass only the compound name.
ChEMBL Drug and Compound Lookup
Query the ChEMBL database for drug-like molecules, drug targets, and bioactivity data. ChEMBL is EBI's open database of drug discovery and medicinal chemistry.
IMPORTANT: Query must be a specific drug or compound name
ChEMBL searches by molecule name. Always use a specific drug name or compound identifier (e.g. sotorasib, ibrutinib, CHEMBL1873475). Do NOT pass topic phrases like "kinase inhibitor resistance" — these will return garbage results. If the topic mentions multiple drugs, pick the most specific one.
When NOT to Use This Skill
Do NOT use ChEMBL when the query is any of the following — it will return large biologics, cell therapy entries, or protein records with MW=?, logP=?, phase=-1:
- Biological therapies: cell therapies, stem cells, antibodies, CAR-T, biologics (e.g. "allogeneic mesenchymal stem cells", "anti-PD1 antibody")
- Mechanism or concept phrases: "proximity-induced degradation", "PROTAC linker", "covalent warhead", "undruggable target"
- Disease names without a specific drug: "Alzheimer's disease", "pancreatic cancer", "KRAS oncogenesis"
- Pathway or process terms: "mTOR signaling", "ubiquitin-proteasome pathway", "kinase cascade"
Correct workflow for mechanism-based topics (e.g. PROTAC, degrader, proximity):
- Search PubMed first with the mechanism query
- Extract specific small-molecule compound names from the papers (e.g. "ARV-110", "dBET6", "MZ1")
- Then query ChEMBL with those specific names
Overview
- Search molecules by name or ChEMBL ID
- Retrieve molecular properties, SMILES, drug indications
- Find targets and bioactivity (IC50, Ki, etc.)
- No API key required
Usage
Search by compound or drug name
python3 {baseDir}/scripts/chembl_search.py --query "aspirin"
Get molecule by ChEMBL ID
python3 {baseDir}/scripts/chembl_search.py --chembl-id CHEMBL25
Detailed output
python3 {baseDir}/scripts/chembl_search.py --query "imatinib" --format detailed
Limit search results
python3 {baseDir}/scripts/chembl_search.py --query "kinase inhibitor" --max-results 5
Parameters
| Parameter | Description | Default |
|-----------|-------------|---------|
| --query | Compound or drug name or search term | - |
| --chembl-id | ChEMBL molecule ID (e.g. CHEMBL25) | - |
| --max-results | Max results for search | 10 |
| --format | Output: summary, detailed, json | summary |
Output
- Summary: ChEMBL ID, pref_name, molecular formula, MW, SMILES, max_phase
- Detailed: Adds drug type, first approval, indications, targets
- JSON: Full API response
Notes
- ChEMBL IDs look like CHEMBL25, CHEMBL1234567
- Use --query for name or text search
- Use --chembl-id when you know the exact molecule ID
Related Skills
lamm-mit/paperclip
tools
VerifiedTrustedCommunity
Onboard and manage Paperclip AI for research-paper knowledge and agent orchestration
203SKILL.mdUpdated May 22, 2026
lamm-mit/perplexity-search
development
VerifiedTrustedCommunity
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.
184SKILL.mdUpdated Apr 6, 2026
lamm-mit/scientific-report-pdf
testing
VerifiedTrustedCommunity
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.
161SKILL.mdUpdated Apr 16, 2026
lamm-mit/python-exec
development
VerifiedTrustedCommunity
Execute arbitrary Python code and return stdout. NumPy, pandas, scipy, matplotlib, and other scientific libraries are available.
161SKILL.mdUpdated Apr 16, 2026