agentsclimarketplace

Grant prospect researcher

Skill SkillMedev/skills/skills/grant-prospect-researcher

The open Skill Me catalog — every hosted skill as a portable, MIT-licensed SKILL.md

Install
npx -y skills add SkillMedev/skills --skill grant-prospect-researcher

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Finds and qualifies foundation funders for a nonprofit by fit-scoring prospects on mission alignment, typical grant size, geographic focus, and past-grantee similarity, reading the funder's 990 for real priorities and median grant size, and sizing the pipeline at 4-5x the annual grant goal. Use when a nonprofit leader says "find foundations that would fund us", "is this funder worth applying to", "how many grants do we need in the pipeline", or "what does this funder's 990 tell us". Do NOT use for B2B sales prospect lists - use prospect-list-builder instead - and do NOT use for startup investor research - use investor-targeting instead.

SKILL.md

8.4 KB, as published. Nobody here has run it

Grant Prospect Researcher

Small nonprofits lose most grants before a word of the proposal is written: they apply to funders who were never going to fund an organization of their size, in their geography, doing their work. Every poorly fit application burns two to four staff-weeks that a three-person team does not have. This skill qualifies funders before any writing starts, so the writing time goes only to prospects with a real 20-30 percent chance of winning. It is the first skill in the grants pipeline: qualified prospects flow to grant-loi-writer, and invitations from there flow to grant-proposal-writer.

Work the example organization throughout: Bright Futures Tutoring, a youth-education nonprofit with a $420,000 annual budget, 3 staff, serving 250 students, seeking a $75,000 foundation grant toward a $180,000 annual grant-revenue goal.

Operating procedure

Follow the steps in order. Pipeline sizing comes first because it tells you how many qualified prospects you need before you know whether the list is done.

Step 1: Set the grant goal and size the pipeline

Pipeline sizing rests on one practitioner number, defined here and cited by nonprofit-board-pack: well-fit prospects win at roughly 20-30 percent, so the pipeline of submitted asks must total 4-5x the grant goal.

Bright Futures math: goal $180,000. Pipeline target at 4.5x is $810,000 in qualified asks. At an average ask of $45,000, that means 16-20 qualified prospects. At a 20-30 percent win rate, expect 4-6 awards - which covers the goal. A pipeline covering less than 4x the goal is a plan to miss it.

Check capacity against the math: a 3-staff organization can realistically produce 1-2 LOIs per month plus 3-5 full proposals per year. If the pipeline needs more applications than staff can write, raise the average ask size rather than the application count.

Step 2: Build the raw list

Sources, cheapest first: the grantee lists (Schedule I or Part XV) of funders who fund your closest peer organizations; ProPublica Nonprofit Explorer full-text search of 990s for your program keywords and county; the local community foundation's directory; state nonprofit association funder lists; board members' personal knowledge of local foundations. Aim for 30-50 raw names to yield 16-20 qualified prospects.

Step 3: Run the 990-reading procedure on each plausible funder

A funder's website says what it wants to be; its 990-PF says what it actually pays for. Pull the two most recent filings (free on ProPublica Nonprofit Explorer) and read in this order:

  1. Part XV, grants paid. This is the ground truth. List every grantee and amount. Compute the median grant, not the mean - one flagship $500,000 grant makes the mean useless.
  2. Grantee similarity. Does any grantee look like you - similar budget size, similar program, same county or state? A funder with no grantee under $1 million in budget rarely starts with one.
  3. Stated guidelines versus actual grants. Real priorities are the grants-paid list. A funder whose website says "education" but whose grants are 80 percent hospital capital campaigns is a hospital funder.
  4. Part XV line 2: does it accept unsolicited applications? "Preselected organizations only" plus no board connection means disqualify, whatever the mission fit.
  5. Assets and payout. Private foundations must distribute roughly 5 percent of assets annually; assets times 0.05 approximates yearly giving capacity.
  6. Officers and trustees. Cross-check names against your board's network. A warm introduction changes the odds materially.
  7. Repeat grantees across the two filings. Many repeats signal a relationship funder that renews; plan for multi-year cultivation, not one-shot asks.

Step 4: Fit-score the prospect

Score five criteria 0-3 each, 15 points maximum:

  • Mission alignment: your program matches the grants-paid list (not the website language).
  • Grant-size fit: your ask falls within 50-150 percent of the funder's median grant. Outside that band, score 0-1.
  • Geographic fit: the funder has recent grantees in your county or state.
  • Grantee similarity: at least one recent grantee resembles you in budget and program.
  • Accessibility: accepts unsolicited LOIs, or you hold a genuine board connection.

Thresholds: 11-15 pursue, 8-10 watch (revisit when something changes), 7 or below disqualify.

Step 5: Apply disqualification discipline

Disqualify fast and in writing, one line of reason each. Automatic kills regardless of mission fit: no unsolicited applications and no connection; median grant below 50 percent of your minimum useful ask; no grantee in your state within three years. Concentration check: no single funder should carry more than 15-20 percent of your annual budget. Bright Futures' $75,000 ask is 18 percent of $420,000 - at the ceiling, acceptable once, but do not stack two funders at that weight.

Step 6: Tier, calendar, and hand off

Sort pursue-tier prospects by deadline, assign each an LOI month within staff capacity, and hand the top prospect to grant-loi-writer. Report pipeline coverage (total qualified asks divided by goal) to the board through nonprofit-board-pack.

Inputs to collect

Annual budget, grant-revenue goal, program area and population served, geography served, minimum useful ask and typical ask, current and past funders, board members' foundation connections, and staff capacity for applications per month (default 1-2 LOIs for a 3-person team). If any number is a guess, label it a guess in the prospect table and refine later.

Worked artifact: Bright Futures prospect-scoring table

GRANT PROSPECT SCORES - Bright Futures Tutoring
Goal $180,000 | Pipeline target $810,000 (4.5x) | Ask band $30k-$90k

Funder                        Mission Size Geo Similar Access TOTAL Verdict
Hearthstone Foundation           3     3    3     2      2     13   PURSUE
  990: median grant $60k; 4 youth-ed grantees in county; accepts LOIs.
  $75k ask = 125% of median - inside the 50-150% band.
National STEM Futures Fund       2     0    0     1      3      6   DISQUALIFY
  990: median grant $250k; zero grantees in state; funds $5M+ orgs.
Riverton Community Foundation    3     2    3     3      0     11→9 WATCH
  Strong fit but grants by trustee nomination only; no connection yet.
  Action: ask board for introductions to Riverton trustees.

Deliverable

A scored prospect table like the one above covering every raw-list name, pipeline coverage math (qualified asks vs 4-5x goal), a one-line reason for every disqualification, and a submission calendar matched to staff capacity, with the first prospect handed to grant-loi-writer.

Do NOT

  • Do not score a funder on its website language; the grants-paid list is the funder's real behavior.
  • Do not use the mean grant size; one outlier grant distorts it. Median only.
  • Do not keep "maybe someday" prospects in the pursue tier - pipeline coverage becomes fiction, and nonprofit-board-pack reports that fiction to the board.
  • Do not apply to a poor-fit funder because its deadline is convenient; a rushed application to the wrong funder costs the same staff-weeks as a strong one to the right funder.
  • Do not let one funder exceed 20 percent of the budget without a board-visible concentration note.

Quality bar

  • Every pursue-tier prospect has a 990-verified median grant and at least one named similar grantee.
  • Pipeline coverage is computed and shown, not asserted, and sits at 4-5x the goal.
  • Every disqualified funder carries a one-line reason.
  • The submission calendar fits inside stated staff capacity.

Escalation

When a prospect scores pursue, go to grant-loi-writer. When the pipeline table is ready for the board, feed the coverage numbers into nonprofit-board-pack. For government grants with compliance regimes (federal RFPs, single-audit thresholds), bring in a grants professional; this skill covers private foundation research.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.