Database Lookup
This is a comprehensive reference wrapper around 78 public scientific and economic APIs, from PubChem and UniProt to FRED and NASA. It's built as a lookup router: you ask about a gene, compound, protein, or economic indicator, and it figures out which databases to hit, reads the right reference file, makes the calls, and returns raw JSON plus a list of what it queried. The organism-aware routing is thoughtful (it won't assume human when you're asking about mouse genes), and the cross-database coverage means you can ask "what pathways is this gene in" without needing to know whether that's a Reactome or KEGG question. It's a solid time-saver if you're tired of hunting down API docs for ENCODE, gnomAD, or the USGS every time you need one data point.
- skills.sh installs
- 2.2K
- GitHub stars
- 56.6K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add k-dense-ai/scientific-agent-skills --skill database-lookup --agent claude-codeInstalls into .claude/skills of the current project.
Files
Database Lookup
This skill catalogs 80 databases with public, registered, or licensed 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
- 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.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/k-dense-ai/scientific-agent-skills
- Categories
- Backend & APIs, AI & Agent Building, Finance & Trading, Databases
- First seen
- Jun 3, 2026
More from k-dense-ai/scientific-agent-skills
All 137- Scholar Evaluation2.2K
- Polars2.2K
- Latex Posters2.2K
- Pptx Posters2.2K
- Bgpt Paper Search2.2K
- Research Grants2.1K
- Sympy2.1K
- Pytorch Lightning2.1K
- Networkx2.1K
- Aeon2.1K
- Transformers2.1K
- Shap2.1K
- Pyzotero2.1K
- Generate Image2.1K
- Dask2.1K
- Infographics2.1K
- Market Research Reports2.1K
- Matlab2.1K
- Get Available Resources2.1K
- Optimize For Gpu2.1K
- Pymc2.1K
- Umap Learn2.1K
- Parallel Web2.1K
- Venue Templates2.1K
Recommended
More Backend & APIs
cloudbase-document-database-in-wechat-miniprogramtencentcloudbase/skillsUse CloudBase document database WeChat MiniProgram SDK to query, create, update, and delete data. Supports complex queries, pagination, aggregation, and geoloca1.5Kskills.sh installs
cuopt-numerical-optimization-api-clinvidia/skillsLP, MILP, and QP (beta) with cuOpt — CLI only (MPS/LP/QPS files, cuopt_cli). Use when the user is solving LP, MILP, or QP from an MPS or LP file via command lin1.3Kskills.sh installs
vtex-io-auth-and-policiesvtex/skillsApply when deciding or implementing permissions and authorization boundaries for VTEX IO apps. Covers manifest policies, outbound-access rules, least-privilege 1.2Kskills.sh installs
agent-docs-api-openapiruvnet/rufloAgent skill for docs-api-openapi - invoke with $agent-docs-api-openapi1.2Kskills.sh installs
rust-backendwindmill-labs/windmillRust coding guidelines for the Windmill backend. MUST use when writing or modifying Rust code in the backend directory.1.1Kskills.sh installs