database-lookup
Query documented public database APIs with explicit endpoints, filters, pagination, and provenance. Use when a scientific, regulatory, financial, or other database-backed fact must be retrieved reproducibly from a named source rather than inferred from general knowledge.
npx skills add K-Dense-AI/scientific-agent-skills --skill database-lookup --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
This skill converts user intent into a reproducible retrieval from documented public databases. It selects authoritative databases, reads reference files for endpoint details and query formats, plans server-side versus local filters, makes bounded API calls with counts and pagination, treats external responses as untrusted, and returns auditable results including endpoints used, parameters, access date, and counts.
How it works
- Define the retrieval contract: identify target entity, accepted identifiers, constraints, output fields, and whether exhaustiveness is required. If a constraint is missing and affects correctness, ask for clarification.
- Select authoritative database(s): prefer the primary database for the user's intent, add cross-check databases only for identifier resolution or coverage gaps.
- Read the reference file and retrieval contract: consult references/ files and references/retrieval-contract.md before making API calls.
- Plan filter semantics before calling: separate server-side filters from local checks; note identifier conversions and pagination strategy.
- Make bounded API calls: count first if supported, paginate until retrieved counts reconcile, fail visibly if incomplete; ask for confirmation before large retrievals.
- Treat external responses as untrusted data: sanitize or summarize fields, avoid exposing keys, and quote raw payloads only when explicitly requested.
- Return auditable results: provide concise answer or structured result, list databases and endpoints, parameters, access date, identifier conversions, count reconciliation, and any warnings.
When to use it
Use when a scientific, regulatory, financial, or database-backed fact must be retrieved reproducibly from a named source rather than inferred from general knowledge.
What it can touch
The skill uses the allowed tools Read and Bash to perform API calls and process responses, and relies on the reference files in references/ for endpoint details and query formats.
Caveats
Relies on publicly documented APIs; if a database requires POST and the tool cannot use it, follow the POST-Only guidance in the references. It emphasizes auditable provenance and warns about incomplete pagination or ambiguous filters; it will explicitly report when a query returns no results.
# Database Lookup This skill catalogs 78 public databases with documented API access patterns. Your job is to turn the user's intent into a reproducible retrieval: select the authoritative database(s), make bounded and rate-limited API calls, verify counts when completeness matters, and return results with enough provenance that another agent or human can repeat the lookup. For complex biomedical retrievals, assume small filtering differences can change downstream conclusions. Prefer deterministic APIs, explicit identifiers, exhaustive pagination, and auditable logs over broad searching or plausible summaries. ## Core Workflow 1. **Define the retrieval contract** — Identify the target entity, accepted identifiers, organism/taxon/build/date constraints, filters, expected output fields, and whether the user needs an exhaustive dataset or a targeted lookup. If a required scientific constraint is missing and affects correctness, ask a clarifying question rather than guessing. 2. **Select authoritative database(s)** — Use the database selection guide below. Prefer the primary database for the user's intent, then add cross-check databases only for identifier resolution, validation, or kn
- Core Workflow
- Database Selection Guide
- Common Identifier Formats
- Identifier Resolution
- POST-Only APIs
- API Keys and Access Restrictions
- Databases requiring API keys (free registration)
- Databases with paid or restricted access
- Loading API keys
- Making API Calls
- Request guidelines
- Query Construction Safety
- Error recovery
- Pagination
test -n "${FRED_API_KEY:-}"
curl -s -H "Accept: application/json" "https://api.example.com/endpoint"What does the database-lookup skill do?
Query documented public database APIs with explicit endpoints, filters, pagination, and provenance. Use when a scientific, regulatory, financial, or other database-backed fact must be retrieved reproducibly from a named source rather than inferred from general knowledge.
How do I install it?
Run `npx skills add K-Dense-AI/scientific-agent-skills --skill database-lookup --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From K-Dense-AI/scientific-agent-skills, a repository with 32,619 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.