grant-proposal-assistant

$npx mdskill add lyndonkl/claude/grant-proposal-assistant

Crafts competitive grant proposals using reviewer-perspective thinking.

  • Ensures clear hypotheses, compelling significance, and feasible approaches.
  • Integrates with NIH R01/R21/K, NSF, and foundation proposal systems.
  • Decides recommendations by applying study section evaluation criteria.
  • Delivers structured guidance for aims, significance, and innovation sections.

SKILL.md

.github/skills/grant-proposal-assistantView on GitHub ↗
---
name: grant-proposal-assistant
description: Guides creation and review of competitive grant proposals (NIH R01/R21/K, NSF, foundations) by applying reviewer-perspective thinking to ensure clear hypotheses, compelling significance, genuine innovation, and feasible approaches. Use when writing or reviewing grant proposals, crafting specific aims, drafting significance/innovation/approach sections, or when user mentions R01, R21, K-series, grant writing, proposal review, study section, or fundable hypothesis.
---

# Grant Proposal Assistant

## Table of Contents
- [Core Questions](#core-questions)
- [Workflow](#workflow)
- [Section Frameworks](#section-frameworks)
- [Reviewer Mindset](#reviewer-mindset)
- [Guardrails](#guardrails)
- [Quick Reference](#quick-reference)

**Related skills (not this one)**:
- Manuscripts: `scientific-manuscript-review`
- Fellowship personal statements: `career-document-architect`
- Letters of recommendation: `academic-letter-architect`

## Core Questions

Every grant proposal must convincingly answer these four questions:

**1. What is the central hypothesis?**
- Testable, specific, falsifiable
- Not just "we will study X" but "we hypothesize that X causes Y through mechanism Z"

**2. Why is the problem important NOW?**
- What gap exists in current knowledge?
- Why is this gap significant for the field/patients/society?
- Why is this the right time (new tools, preliminary data, shifting paradigm)?

**3. What makes the approach innovative?**
- What is genuinely new (concept, method, application)?
- How does this advance beyond incremental improvement?
- Innovation in approach AND/OR innovation in what will be learned

**4. Is the plan feasible and logical?**
- Can this team do this work in this timeframe with these resources?
- Do aims build logically without fatal dependencies?
- Are pitfalls anticipated with alternatives ready?

## Workflow

Copy this checklist and track your progress:

```
Grant Proposal Progress:
- [ ] Step 1: Identify grant mechanism and constraints
- [ ] Step 2: Core questions audit
- [ ] Step 3: Specific Aims review (1-page)
- [ ] Step 4: Significance section review
- [ ] Step 5: Innovation section review
- [ ] Step 6: Approach section review (per aim)
- [ ] Step 7: Reviewer alignment check
- [ ] Step 8: Compliance verification
```

**Step 1: Identify Grant Mechanism and Constraints**

Determine mechanism (R01, R21, K, NSF, Foundation). Note page limits, required sections, and review criteria. R01 = 12 pages; R21 = 6 pages; K = 12 pages + career development. See [resources/methodology.md](resources/methodology.md#grant-mechanisms) for mechanism-specific guidance.

**Step 2: Core Questions Audit**

Read entire proposal looking ONLY for answers to the four core questions. Mark where each is addressed (or missing). Flag unclear hypotheses, weak significance, or missing innovation. See [resources/methodology.md](resources/methodology.md#core-question-audit) for audit checklist.

**Step 3: Specific Aims Review**

Evaluate the 1-page Aims against the gold standard: Opening hook → Gap → Hypothesis → Aims (testable, independent, coherent) → Impact. This is the most important page. See [resources/template.md](resources/template.md#specific-aims-template) for structure.

**Step 4: Significance Section Review**

Check: What is the problem? Why does it matter? What will change if successful? Look for explicit gap statements and impact predictions. See [resources/methodology.md](resources/methodology.md#significance-checklist) for evaluation criteria.

**Step 5: Innovation Section Review**

Check: What is genuinely new? Be specific (not "innovative approach" but "first application of X to Y"). Innovation can be conceptual, methodological, or in expected outcomes. See [resources/methodology.md](resources/methodology.md#innovation-checklist) for evaluation criteria.

**Step 6: Approach Section Review**

For EACH aim: Rationale (why this aim?) → Strategy (how?) → Expected outcomes → Pitfalls → Alternatives. Check for adequate controls, statistical power, timeline realism. See [resources/template.md](resources/template.md#approach-per-aim) for per-aim structure.

**Step 7: Reviewer Alignment Check**

Read as a non-expert reviewer would. Can they understand significance without deep domain knowledge? Are impact statements prominent? Is the writing accessible? See [resources/methodology.md](resources/methodology.md#reviewer-perspective) for reviewer simulation.

**Step 8: Compliance Verification**

Check page limits, required sections, biosketch format, reference formatting. Verify all required components present. Validate using [resources/evaluators/rubric_grant_proposal.json](resources/evaluators/rubric_grant_proposal.json). **Minimum standard**: Average score ≥ 3.5.

## Section Frameworks

### Specific Aims Page (1 page)

**The most important page of your grant.**

**Structure:**
```
OPENING PARAGRAPH (4-6 sentences)
- Hook: Why this problem matters (significance)
- Gap: What's missing in current understanding
- Long-term goal: Your program of research
- Central hypothesis: Testable, specific
- Rationale: Why this hypothesis is reasonable (preliminary data)

AIM 1: [Verb phrase describing objective]
- Brief description (2-3 sentences)
- Expected outcome and interpretation
- Must be testable and achievable

AIM 2: [Verb phrase describing objective]
- Brief description (2-3 sentences)
- Expected outcome and interpretation
- Independent of Aim 1 (can proceed if Aim 1 fails)

AIM 3 (optional): [Verb phrase describing objective]
- Brief description (2-3 sentences)
- May integrate findings from Aims 1-2

CLOSING PARAGRAPH (2-3 sentences)
- Expected outcomes of the project
- Impact: How this advances the field
- Future directions this enables
```

### Significance Section

**Goal:** Convince reviewers the problem matters

**Key elements:**
1. **The Problem**: What clinical/scientific problem exists?
2. **Current State**: What's known, what's been tried?
3. **The Gap**: What critical question remains unanswered?
4. **Impact of Gap**: What's the cost of not knowing?
5. **If Successful**: What changes? Be specific.

**Red flags:**
- ❌ Generic statements ("cancer is bad")
- ❌ No clear gap statement
- ❌ Impact statements too vague ("will advance the field")
- ✅ Specific gap, specific impact, quantifiable where possible

### Innovation Section

**Goal:** Show this is not incremental

**Types of innovation:**
1. **Conceptual**: New framework, paradigm, or understanding
2. **Methodological**: New technique, approach, or model
3. **Application**: Known method applied to new problem
4. **Expected Outcomes**: Will generate novel insights

**Format:**
- Use bullet points for scannability
- Start each with "This project is innovative because..."
- Be specific, not vague

### Approach Section (Per Aim)

**Structure for each aim:**

```
AIM X: [Title]

RATIONALE (1 paragraph)
Why is this aim necessary? How does it address the hypothesis?

PRELIMINARY DATA (if applicable)
What have you already shown that supports feasibility?

STRATEGY (2-4 paragraphs)
- Experimental design
- Methods and procedures
- Controls (positive and negative)
- Statistical analysis plan

EXPECTED OUTCOMES
What results do you expect? How will you interpret them?

POTENTIAL PITFALLS AND ALTERNATIVES
What could go wrong? What's your backup plan?

TIMELINE/MILESTONES
When will this be completed? Dependencies on other aims?
```

## Reviewer Mindset

### How Study Sections Work

- Reviewers assigned based on expertise (but may not be YOUR exact field)
- Primary reviewers read carefully; secondary skim
- 3 reviewers score; others may not read deeply
- Scored on: Significance, Investigators, Innovation, Approach, Environment
- Overall Impact = "How important is this research?"

### What Reviewers Look For

**Good proposals make reviewers' jobs easy:**
- Clear hypothesis on page 1
- Explicit significance statements
- Obvious innovation points (bulleted)
- Logical aim flow
- Pitfalls acknowledged with alternatives

**Proposals get criticized for:**
- Vague hypotheses ("We will explore...")
- Missing controls
- Overly ambitious scope
- Aim dependencies (if Aim 1 fails, whole project fails)
- No preliminary data for risky approaches
- Unclear statistical plans

## Guardrails

1. **Testable hypothesis**: The hypothesis should be falsifiable, not just a goal
2. **Explicit gaps**: State what is unknown, not just what you will do
3. **Real innovation**: Be specific, not just "innovative approach"
4. **Independent aims**: The project should survive if one aim fails
5. **Feasibility evidence**: Include preliminary data for risky elements
6. **Power calculations**: Know sample sizes and why they are sufficient
7. **Pitfall acknowledgment**: Show anticipated problems and alternatives

**Common pitfalls:**
- ❌ **Fishing expedition**: "We will determine..." without hypothesis
- ❌ **Aim dependency**: Aim 2 impossible without Aim 1 success
- ❌ **Scope creep**: Too ambitious for budget/time
- ❌ **Missing controls**: Experiments without proper comparisons
- ❌ **Vague statistics**: "Data will be analyzed appropriately"
- ❌ **No alternatives**: Assuming everything will work

## Quick Reference

**Key resources:**
- **[resources/methodology.md](resources/methodology.md)**: Grant mechanisms, audit checklists, reviewer perspective
- **[resources/template.md](resources/template.md)**: Specific aims template, approach per-aim structure
- **[resources/evaluators/rubric_grant_proposal.json](resources/evaluators/rubric_grant_proposal.json)**: Quality scoring

**Page limits:**
| Mechanism | Research Strategy | Specific Aims |
|-----------|------------------|---------------|
| R01 | 12 pages | 1 page |
| R21 | 6 pages | 1 page |
| R03 | 6 pages | 1 page |
| K-series | 12 pages (+career) | 1 page |

**NIH scoring:**
- 1-3: Exceptional to Excellent (funded)
- 4-5: Very Good to Good (may fund)
- 6-7: Satisfactory to Fair (unlikely)
- 8-9: Marginal to Poor (not funded)

**Typical writing time:**
- Specific Aims (polished): 3-5 days
- Full R01 first draft: 4-6 weeks
- R21 first draft: 2-3 weeks
- Revision cycle: 1-2 weeks per round

**Inputs required:**
- Research idea with preliminary data
- Grant mechanism and deadline
- Institutional resources available

**Outputs produced:**
- Structured grant sections
- Commentary on strengths/weaknesses
- Reviewer-perspective critique

More from lyndonkl/claude

SkillDescription
abstraction-concrete-examplesBuilds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.
academic-letter-architectGuides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.
adr-architectureDocuments significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.
adverse-selection-priorProduces a Bayesian prior probability that an offered transaction is +EV for the recipient, given that the counterparty chose to propose it. Applies Akerlof market-for-lemons logic -- if they offered it, they believe it is +EV for them, so the prior that it is +EV for us is materially below 50%. Reusable across trade evaluation, waiver drops (another team dropping a player is also adverse selection), job-offer analysis, M&A, and any "someone offered me this" situation. Use when you receive an unsolicited trade/offer/proposal, analyzing incoming trade prior, evaluating why a counterparty proposed a deal, or when user mentions adverse selection, market for lemons, why did they offer this, incoming trade prior, they proposed it, Bayesian adjustment on received offer.
alignment-values-north-starCreates actionable alignment frameworks that give teams a shared North Star (direction), values (guardrails), and decision tenets (behavioral standards). Enables autonomous decision-making while maintaining organizational coherence. Use when starting new teams, scaling organizations, defining culture, establishing product vision, resolving misalignment, creating strategic clarity, or when user mentions North Star, team values, mission, principles, guardrails, decision framework, or cultural alignment.
analogy-weight-checkFor every analogy in a substacker draft, verifies it carries mechanical weight — the analogy does real work explaining the mechanism, not merely decorates it. Cross-references analogy-catalog.md for novelty (is this analogy reused from a prior post?) and domain fit (biology > organizational > sports preferred; physics/military disfavored). Use whenever an analogy appears in the draft. Trigger keywords: analogy weight, decorative, mechanical weight, reused analogy, catalog check, metaphor check.
answer-uncomfortable-questionTakes one strategic question about substacker ("should we launch paid?", "is this section dead?", "are we writing for the wrong audience?") and produces the mandatory evidence + reasoning + downside triad plus a recommendation. Used 3 times per Growth Strategist review. Trigger keywords: uncomfortable question, strategic question, evidence reasoning downside, triad.
attribute-performanceFor each substacker post that materially over- or under-performs the rolling baseline (|z| ≥ 1.0), produces a plain-English attribution paragraph with calibrated confidence (high / medium / low / unexplained). Considers subject-line effect, topic zeitgeist, external share, day-of-week, length effect, and audience-notes signals. Labels unexplained outliers explicitly rather than fabricating a story. Use after compute-baseline when outlier posts exist. Trigger keywords: attribution, why did this post work, outlier explanation, performance analysis.
auction-first-price-shadingComputes the optimal shaded bid for a first-price sealed-bid auction given a true private value, an estimate of the number of competing bidders N, and a value-distribution assumption. Implements the `(N-1)/N` equilibrium shading rule for uniform private values, adjusts for log-normal or empirical value distributions, layers a risk-aversion adjustment, and caps output against the bidder's remaining budget. Domain-neutral auction theory reusable across fantasy sports (baseball FAAB, NBA/NHL waiver auctions), prediction-market limit sizing, sealed procurement bids, and any blind-bid context. Use when user mentions "first-price auction bid", "sealed bid shading", "(N-1)/N", "FAAB bid amount", "auction shading", "optimal bid first-price", "bid for sealed-bid", "blind bid sizing", or when downstream logic needs a principled shade factor rather than an ad-hoc heuristic.
auction-winners-curse-haircutApplies a Bayesian haircut to a bid valuation for common-value auctions where winning is itself evidence the bidder over-estimated. Takes a raw valuation, a value-type classification (common_value / private_value / mixed), the number of informed bidders N, and a signal-dispersion estimate, and returns an adjusted valuation. Domain-neutral and reusable across fantasy FAAB, prediction markets, M&A bids, ad-auction budgets, and any generic bidding context. Use when user mentions "winner's curse", "common value auction", "valuation haircut", "adverse valuation", "Bayesian bid adjustment", or "over-paying in auction".