Agent skill · mims-harvard
tooluniverse-nih-funding-landscape
Analyze NIH grant portfolios and funding history using the OpenNIH FY1985-present corpus, then connect grants to investigators, institutions, publications, clinical trials, patents, targets, or drugs with ToolUniverse. Use for NIH grant discovery, topic or Institute/Center trends, PI and institution profiles, activity-code or mechanism analysis, funding growth and concentration, grant-writing landscape research, SBIR/STTR landscapes, research-policy analysis, expert discovery, funding-to-output translational impact studies, or public-facing NIH explainers for patients, advocates, local and national journalists, trainees, applicants, institutions, entrepreneurs, and taxpayers.
What it needs
About 11k tokens when loaded.
What this skill does
NIH Funding Landscape Build source-traceable NIH funding analyses with explicit scopes, count units, data coverage, and interpretation limits. Use OpenNIH for funding facts and other ToolUniverse sources only for downstream evidence they actually cover. Always read references/tool-reference.md before choosing tools or comparing totals. Read references/verified-cases.md when testing the skill, debugging an unexpected response, or adapting one of the verified case patterns. Read references/public-value-cases.md for a patient, family, advocate, journalist, trainee, applicant, taxpayer, policy, or other public-facing request. Public Value Routing Start from the reader's decision, not from the available endpoints: Reader Optimize the answer for Never imply --- --- --- Patient, family, advocate A topic-specific research map, recent activity, inspectable projects, and next contacts Clinical expertise, quality of care, treatment advice, or patient benefit from funding alone Journalist, taxpayer, policy analyst A reproducible headline number, its definition, its largest drivers, and its sensitivity to alternate queries That the largest number is the truest, a partial year is final, or spending caused outcomes Researcher, trainee, applicant Funded precedents, active mechanisms, institutions, and project language Application odds, reviewer preferences, mentorship quality, or K99-to-R00 conversion Institution or translational team Resolved peer portfolios and exact identifiers for output follow-up Raw-name totals as one entity or grant-output chronology as causality Local reporter or community A location-qualified portfolio joined through resolved institutions That an institution-name substring is a city/state geography query or that award location equals beneficiary location Entrepreneur Topic-specific R41/R42/R43/R44 awards, companies, and phase-labeled project activity Commercial success, current company status, addressable market, or Phase I-to-II conversion from annual awa …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills mims-harvard/tooluniverse-nih-funding-landscape