Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Public Database Lookup (database-lookup)

Retrieve facts from 78 documented public database APIs reproducibly, with explicit endpoints, pagination, and provenance.

Data & AnalyticsIntermediate★ 33,030⑂ 3,248AI score 9/10Last updated: Aug 9, 2026

What it does

  • Ships reference files for 78 public databases (PubChem, UniProt, ClinicalTrials.gov, GDC/TCGA, FRED, SEC EDGAR, WHO GHO and more) with endpoints, parameters, rate limits and pagination behaviour, so the agent calls the real API instead of guessing from general knowledge.
  • Forces a retrieval contract up front: target entity, accepted identifiers, organism/genome build/date constraints, output fields, and whether an exhaustive dataset or a targeted lookup is needed.
  • Returns auditable output: databases queried, endpoints, parameters, access date, identifier conversions, count reconciliation (expected vs retrieved vs locally filtered) and explicit warnings.
  • Includes built-in identifier resolution paths (gene symbol ↔ NCBI Gene ID ↔ Ensembl ↔ UniProt; compound name ↔ PubChem CID ↔ ChEMBL) plus an error-recovery ladder.
  • Documents which databases need free API keys, which are POST-only (Open Targets, gnomAD, RummaGEO), and which are paid/restricted with free substitutes.
  • Treats API payloads as untrusted third-party data: no embedded-instruction following, no raw text piped into shell commands, no secrets in provenance.

Who it's for

  • Researchers and grad students who need citable, source-verified numbers rather than model recall
  • Bioinformatics, pharma and clinical data people working with genes, variants, compounds and trials
  • Data analysts pulling macroeconomic and demographic series (FRED, BLS, World Bank, Census, Eurostat)
  • Research/IP teams tracking patents and regulatory filings (USPTO, SEC EDGAR, OpenFDA)

Examples

  1. "List every recruiting clinical trial mentioning TP53" → cursor-paginates ClinicalTrials.gov, reconciles total vs retrieved counts, returns a table plus a provenance block.
  2. "Compare aspirin's ChEMBL bioactivity with its PubChem properties" → resolves name → CID 2244 → CHEMBL25 and records the conversion chain.
  3. "US unemployment and CPI over the last 10 years" → silently tests for FRED_API_KEY, proceeds anonymously if absent and notes the lower rate limit.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/database-lookup/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/database-lookup folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/database-lookup/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/database-lookup ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal (Terminal on macOS/Linux, Git Bash or WSL on Windows).
  2. Clone the repository: 
    git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Copy the whole skill folder — the references/ directory must come with it or the skill can't work: 
    mkdir -p ~/.claude/skills
cp -r scientific-agent-skills/skills/database-lookup ~/.claude/skills/
  4. Verify the install: 
    ls ~/.claude/skills/database-lookup/references | head
  5. (Optional) Register for free API keys for the databases you use most and export them in your shell profile or a project .env, e.g. export FRED_API_KEY=..., export NCBI_API_KEY=...
  6. Restart Claude Code and try a prompt like: "Use the database-lookup skill to get the gnomAD allele frequency for rs334."
View source on GitHub ↗License: MIT