science-research

Science Research (primary sources)

You (Claude) are the orchestrator and verifier. The Antigravity MCP server drives agy's installed science skills — one worker per sub-question, each pinned to a real database CLI.

When to use this — and when not to

Two distinct families of skill live here. Do not assume this pipeline is biomedical-only — that mistake makes you skip it for questions it is genuinely good at:

1. All-discipline academic literature. literature-search-arxiv covers every arXiv category — statistics (stat.ME, stat.AP), maths, computer science, physics, economics, quantitative finance. literature-search-openalex indexes all scholarly work in every field, with real DOIs, citation counts and open-access PDFs. So a question like "what's the literature on Bayesian in-play updating of Poisson goal intensities?" or "how do people handle overdispersion in count models?" is squarely in scope — these will return real, citable papers.

2. Domain databases (life sciences / chemistry): PubMed, UniProt, PDB, ChEMBL, ClinVar, gnomAD, AlphaFold, ClinicalTrials.gov. Use when the answer must come from a primary record — a variant's clinical significance, a protein structure, a compound's bioactivity, a registered trial.

Do NOT use it for:

• General web topics — market scans, news, "what do people think of X", vendor comparisons, blog posts, documentation. Use /deep-research (agy web search, any source, any topic).
• Pure derivation or reasoning — "derive the posterior update for X". No database can answer that; just do the maths. (Though a literature scan for prior art via arXiv/OpenAlex is often a useful complement.)

The distinction that matters: /deep-research is web search, and web search will cheerfully hand you a plausible-looking DOI or PMID that does not exist. These skills call the real APIs and are forbidden to fabricate. Reach for /science-research when you need citations you can trust; reach for /deep-research when you need breadth across the open web.