skills.rest
tamagusko
tamaguskoCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

database-lookup

Query 78 public scientific and economic database REST APIs and return structured JSON results.

Updated Oct 7, 2022
Search Tags:#json#genomics#rest api#economic data#pubchem#identifier resolution#scientific databases
One-click install
npx skills add https://github.com/tamagusko/linux-cfg --skill database-lookup-tamagusko
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: database-lookup
Source: https://github.com/tamagusko/linux-cfg/tree/main/dotfiles/claude/skills/database-lookup
Command: npx skills add https://github.com/tamagusko/linux-cfg --skill database-lookup-tamagusko

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Finding reliable data across dozens of public scientific, biomedical, and economic databases requires knowing each API's endpoints, identifier formats, authentication requirements, and rate limits. This Skill removes that burden by selecting the right databases for a question, querying their REST APIs, and returning raw structured JSON results. ## Core Features & Use Cases - Guided database selection: Decision tables map user intent (compounds, genes, variants, clinical trials, patents, economic indicators, earthquakes, weather) to the right primary and fallback databases across 78 sources. - Identifier resolution workflows: Converts between gene symbols, UniProt accessions, Ensembl IDs, PubChem CIDs, ChEMBL IDs, rsIDs, and ontology terms so cross-database queries succeed. - API key and access handling: Documents which databases need free keys (FRED, NCBI, Materials Project, etc.), how to load them from the environment or a .env file, and free alternatives for restricted sources like DrugBank and COSMIC. - Use Case: Ask "what is known about aspirin" and the Skill queries PubChem, ChEMBL, DrugBank alternatives, Reactome, and FDA in parallel, returning the raw JSON from each with the endpoints used. ## Quick Start Ask the assistant to look up a compound, gene, variant, clinical trial, patent, or economic indicator and specify that it should query the relevant public database APIs and return the raw JSON results.

Frequently Asked Questions about database-lookup

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I look up a compound across PubChem, ChEMBL, and DrugBank?▼

Resolve the compound name to a PubChem CID first, then convert to a ChEMBL ID via UniChem or ChEMBL molecule search. Query PubChem for properties, ChEMBL for bioactivity, and use OpenFDA plus DailyMed as free alternatives since DrugBank requires a paid license.

How do I convert a gene symbol to Ensembl or UniProt identifiers?▼

Search NCBI Gene by symbol to get the NCBI Gene ID, then use the Ensembl xrefs endpoint with the symbol and species to get the Ensembl ID, or search UniProt with gene_exact and organism_id filters to get the UniProt accession.

Which databases require API keys and how are they loaded?▼

FRED, BEA, BLS, NCBI, OpenFDA, Materials Project, NASA, and about a dozen others need free registration keys. The Skill checks shell environment variables first, then a .env file in the working directory, and proceeds without a key at lower rate limits if none is found.

Why do some database queries fail with WebFetch?▼

Open Targets, gnomAD, RummaGEO, and GDC/TCGA require HTTP POST or GraphQL, which GET-only fetch tools cannot perform. Use curl through a shell tool with the appropriate JSON body and headers instead.

What should I do when a database returns no results or an error?▼

Check the identifier format against the common formats table, try alternative identifiers such as SMILES or InChIKey for compounds, then fall back to the alternative databases listed in the selection guide and report which source failed.

Can I query multiple databases in parallel for one question?▼

Yes, queries to different databases can run in parallel since most APIs have generous rate limits. Serialize requests only to rate-limited sources like NCBI at 3 requests per second without a key or SEC EDGAR at 10 per second.

Related Skills

Explore More Education & Research Skills→
anxiety135790anxiety135790

api-key-env-migration

Migrates plaintext API keys in Hermes config files to environment variable references.

Community
Basic
Ming-Kai-LCMing-Kai-LC

data-science-educator

Create structured data science lessons covering pandas, visualization, and machine learning workflows.

Community
Basic
qinyan-aiqinyan-ai
48

bindingdb-database

Retrieves binding affinity data from BindingDB by target or compound.

Community
Intermediate
zainhaszainhas
2

together-batch-inference

Batch-process inference requests asynchronously via Together AI's Batch API.

Community
Advanced