funding-search
Skill8 starsChanged 8 months agoMITView on GitHub
Search for new funding opportunities in data science, AI, computational science, and related fields announced within the last week. Covers federal agencies (NSF, NIH, DOE, DARPA, DOD, USDA, DOEd, ARPA-H, State Department, DHS) and major foundations (Sloan, Schmidt Sciences, Gates, Hewlett, Simons, Moore, Burroughs Wellcome, MacArthur, Mellon, Carnegie, Russell Sage, Templeton, Chan Zuckerberg Initiative). Use this skill whenever the user asks to find new grants, funding opportunities, RFAs, RFPs, NOFOs, FOAs, or solicitations relevant to a School of Data Science, or asks to check what new funding has been announced recently. Also trigger when the user says "funding search," "new grants," "grant scan," "what's new in funding," "check for new RFAs," or similar.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- t46/ra-skillstheir own version, first seen May 18, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- t46/ra-skills★ 16same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- brand-ymlSkill
- deslopSkill
- write-alt-textSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. About 0 are common, 16 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈16
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 32
Run web searches in three waves.
- Distinctive: line 38
Search for new solicitations from each of these agencies.
- Distinctive: line 59
Use web_fetch on promising results pages (e.g., grants.gov search results, NSF new funding page) to extract details.
- Distinctive: line 64
Search for new opportunities from foundations known to fund data science, AI, and computational research:
- Distinctive: line 86
Run broader searches to catch anything missed in Waves 1 and 2:
- Distinctive: line 98
After collecting candidate opportunities, filter for:
- Distinctive: line 100
Recency: Only include opportunities announced or posted within approximately the last 7 days.
- Distinctive: line 106
Deduplication: If the same opportunity appears in multiple searches, include it only once.
- Distinctive: line 107
New announcements only: Only include opportunities that were announced or posted within the last ~7 days.
- Distinctive: line 118
Funding amount: if available (per-award range or total program budget)
- Distinctive: line 120
Posted/announced date: if you can determine it
- Distinctive: line 122
Use this template for each entry:
- Distinctive: line 145
After listing all opportunities found, add a brief summary line stating how many new opportunities were found and the date range searched.
- Very specific: line 153
Always render results in the conversation first.
- Distinctive: line 161
If a URL leads to a page that has been taken down or is behind a login wall, note this.
- Distinctive: line 162
Do not fabricate opportunities.
- Distinctive: line 164
When in doubt about relevance, include the opportunity with a note about which SDS research areas it might fit.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Funding Opportunity Search
This skill performs a systematic web search for funding opportunities announced within the last ~7 days that are relevant to data science, artificial intelligence, computational science, statistics, and adjacent fields. The output is a formatted summary suitable for inclusion in a weekly research newsletter.
Context
The user is the Assistant Dean for Research at UVA's School of Data Science. Faculty research spans computational genomics, applied statistics, AI/ML, NLP, network science, computer vision, data ethics and policy, AI safety, biosecurity, digital twins, public health informatics, and responsible AI. Opportunities of interest include those funding research, training grants, infrastructure, workshops, and centers in these areas.
Search Strategy
Run web searches in three waves. Use today's date to anchor recency. For each search, include a time qualifier like "2026" or "this week" or "March 2026" (adjusted to the current date) to bias results toward recent announcements. Expect to run 10-20 searches total.
Wave 1: Federal Agency Announcements
Search for new solicitations from each of these agencies. Use queries like:
NSF new funding opportunity 2026orNSF dear colleague letter [current month] 2026NIH new RFA [current month] 2026orNIH notice of funding opportunity data scienceDOE funding opportunity announcement [current month] 2026DARPA broad agency announcement 2026ARPA-H funding opportunity 2026grants.gov new opportunities data science AI [current month] 2026USDA NIFA funding opportunity 2026NSF dear colleague letter 2026(DCLs often announce new priority areas)
Also search grants.gov directly for recent postings:
site:grants.gov artificial intelligence [current month] 2026site:grants.gov data science [current month] 2026
For NSF specifically, also check for new program solicitations:
site:nsf.gov new funding opportunity [current month] 2026site:nsf.gov program solicitation [current month] 2026
Use web_fetch on promising results pages (e.g., grants.gov search results, NSF new funding page) to extract details.
Wave 2: Foundations and Private Funders
Search for new opportunities from foundations known to fund data science, AI, and computational research:
Sloan Foundation new grant program 2026Schmidt Sciences funding opportunity 2026orSchmidt Futures RFP 2026Gates Foundation funding opportunity 2026Simons Foundation funding 2026Moore Foundation data science grant 2026Burroughs Wellcome Fund new program 2026Chan Zuckerberg Initiative funding 2026Hewlett Foundation grant opportunity 2026Templeton Foundation funding 2026MacArthur Foundation grant 2026Russell Sage Foundation RFP 2026Mellon Foundation grant 2026Carnegie Corporation grant 2026Google.org impact challenge 2026
Adjust the year and month to match the current date.
Wave 3: Aggregators and Broad Searches
Run broader searches to catch anything missed in Waves 1 and 2:
new funding opportunity artificial intelligence research [current month] 2026new grant data science research [current month] 2026new federal funding computational science 2026new RFP machine learning research 2026funding opportunity digital twins 2026funding opportunity AI safety 2026funding opportunity biosecurity bioinformatics 2026
Filtering
After collecting candidate opportunities, filter for:
- Recency: Only include opportunities announced or posted within approximately the last 7 days. If the posting date is unclear, include it but flag the uncertainty.
- Relevance: Include opportunities where a data science, AI, statistics, or computational science researcher could plausibly be PI or co-PI. Cast a reasonably wide net, but skip opportunities that are clearly outside scope (e.g., pure humanities with no computational angle, clinical trials with no data science component, equipment-only grants for wet labs).
- Deduplication: If the same opportunity appears in multiple searches, include it only once.
- New announcements only: Only include opportunities that were announced or posted within the last ~7 days. Do not include a "previously noted" or "still open" section for older opportunities. The goal is a clean list of what is new this week.
Output Format
Present results as a markdown list. For each opportunity, include:
- Funder and program name with a link to the solicitation
- One to three sentences describing what the program funds and why it may interest SDS faculty
- Funding amount if available (per-award range or total program budget)
- Deadline if available
- Posted/announced date if you can determine it
Use this template for each entry:
**[Program Name](URL)** (Funder)
Brief description of the opportunity and its relevance to data science faculty.
Amount: $X–$Y per award. Deadline: Month Day, Year.Example output:
Pathways to Enable Secure Open-Source Ecosystems (PESOSE) (NSF) Supports translation of open-source science and engineering research products into sustainable ecosystems. Relevant to SDS faculty working on open-source software tools for data analysis, ML frameworks, or reproducible research infrastructure. Amount: up to $750,000. Deadline: September 1, 2026.
Science of Trustworthy AI (Schmidt Sciences) Funds technical research to understand, predict, and control risks from frontier AI systems. Directly relevant to SDS faculty in AI safety, responsible AI, and ML robustness. Amount: varies. Deadline: May 17, 2026.
Closing the Report
After listing all opportunities found, add a brief summary line stating how many new opportunities were found and the date range searched. If a search wave returned nothing new, say so. Example:
Found 8 new funding opportunities posted between March 19–26, 2026. Federal agency searches returned 5 results; foundation searches returned 3. No new DOE or ARPA-H solicitations were identified this week.
Always render results in the conversation first. Then save the same content to a markdown
file at /mnt/user-data/outputs/funding-opportunities-YYYY-MM-DD.md (using today's date)
and present it to the user so they can download it.
Important Notes
- Prioritize accuracy. If you cannot confirm a deadline or amount from the source, say "deadline TBD" or "amount not specified" rather than guessing.
- If a URL leads to a page that has been taken down or is behind a login wall, note this.
- Do not fabricate opportunities. Every entry must come from a real search result with a verifiable URL.
- When in doubt about relevance, include the opportunity with a note about which SDS research areas it might fit.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.