Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Write a structured grant proposal or funding application for any grant type. Use when asked to write a grant proposal, funding application, research grant, charitable grant, or innovation fund application. Produces a complete proposal with project summary, rationale, methodology, impact, and budget narrative.
.claude/skills/mohitagw15856-grant-proposal/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 17% | 0% |
Produces structured grant proposals tailored to the funder priorities — the most common reason grants fail is writing about what you want to do rather than what the funder wants to fund.
Informative and memorable. Should convey the problem being solved and the approach.]
What you will do, why it matters, who will benefit, measurable outcomes. Every sentence earns its place.]
Funder test: does this problem align with funder] stated priorities? Make the connection explicit.
3-5 SMART objectives:
Phase 1: Name] (Months 1-X) What will happen, who will do it, what is produced]
Key activities:
What makes this approach innovative or effective: Why this over alternatives]
| Level | Description | Measure | |---|---|---| | Output | Tangible deliverable] | How counted] | | Short-term outcome | Immediate change] | How measured] | | Medium-term outcome | Behaviour change] | How measured] | | Long-term impact | Systemic change] | How evidenced] |
Direct beneficiaries: Who and how many] Sustainability: How work continues beyond grant period]
| Budget line | Amount | Justification | |---|---|---| | Staff costs | £amount] | Role, % FTE, duration, salary] | | Travel | £amount] | Specific journeys named] | | Equipment | £amount] | Itemised] | | Indirect costs | £amount] | X]% of direct — check policy] | | Total | £total] | |
Value for money: Cost per beneficiary. What could not be done without this grant]
Track record of similar projects, governance, financial management. Name previous grants and outputs — be specific]
| Risk | Likelihood | Impact | Mitigation | |---|---|---|---| | Risk] | H/M/L | H/M/L | Specific mitigation] |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→fail | 26,528 | 30,779 | +16% | 1 | 1 | 0% | 5,292 | 6,479 | +22% | 0 | 0 | — |
case-01 | fail→pass | 35,112 | 28,593 | -19% | 1 | 1 | 0% | 6,293 | 5,813 | -8% | 0 | 0 | — |
case-03 | fail→fail | 36,664 | 34,422 | -6% | 1 | 1 | 0% | 6,276 | 7,277 | +16% | 0 | 0 | — |
case-04 | pass→pass | 16,191 | 17,580 | +9% | 1 | 1 | 0% | 2,903 | 3,783 | +30% | 0 | 0 | — |
case-05 | pass→pass | 17,774 | 17,525 | -1% | 1 | 1 | 0% | 3,189 | 4,216 | +32% | 0 | 0 | — |
case-06 | pass→pass | 17,287 | 14,793 | -14% | 1 | 1 | 0% | 2,939 | 3,541 | +20% | 0 | 0 | — |
case-07 | pass→pass | 10,706 | 21,271 | +99% | 1 | 1 | 0% | 1,918 | 4,486 | +134% | 0 | 0 | — |
case-08 | fail→pass | 13,171 | 9,461 | -28% | 1 | 1 | 0% | 2,207 | 2,596 | +18% | 0 | 0 | — |
case-09 | pass→pass | 12,239 | 9,372 | -23% | 1 | 1 | 0% | 2,245 | 2,827 | +26% | 0 | 0 | — |
case-10 | pass→pass | 16,625 | 7,859 | -53% | 1 | 1 | 0% | 3,018 | 2,660 | -12% | 0 | 0 | — |
case-11 | fail→pass | 14,575 | 8,136 | -44% | 1 | 1 | 0% | 2,620 | 2,518 | -4% | 0 | 0 | — |
case-12 | fail→pass | 13,150 | 14,638 | +11% | 1 | 1 | 0% | 2,834 | 3,790 | +34% | 0 | 0 | — |
case-13 | fail→pass | 11,616 | 9,459 | -19% | 1 | 1 | 0% | 2,172 | 2,544 | +17% | 0 | 0 | — |
case-14 | fail→pass | 14,513 | 9,639 | -34% | 1 | 1 | 0% | 2,347 | 2,754 | +17% | 0 | 0 | — |
case-15 | pass→pass | 13,331 | 9,835 | -26% | 1 | 1 | 0% | 2,250 | 2,712 | +21% | 0 | 0 | — |
case-16 | fail→pass | 11,642 | 7,617 | -35% | 1 | 1 | 0% | 2,017 | 2,613 | +30% | 0 | 0 | — |
case-17 | fail→pass | 11,721 | 8,669 | -26% | 1 | 1 | 0% | 1,997 | 2,444 | +22% | 0 | 0 | — |
case-18 | fail→pass | 13,423 | 8,769 | -35% | 1 | 1 | 0% | 2,399 | 2,428 | +1% | 0 | 0 | — |
case-19 | pass→pass | 12,826 | 8,765 | -32% | 1 | 1 | 0% | 2,173 | 2,444 | +12% | 0 | 0 | — |
case-20 | pass→pass | 10,030 | 8,524 | -15% | 1 | 1 | 0% | 1,640 | 2,237 | +36% | 0 | 0 | — |
case-21 | fail→fail | 12,331 | 10,566 | -14% | 1 | 1 | 0% | 1,913 | 2,682 | +40% | 0 | 0 | — |
case-22 | fail→pass | 16,410 | 7,778 | -53% | 1 | 1 | 0% | 2,736 | 2,233 | -18% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.