temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Grant Proposal Writer (NSF / NIH / Foundation Formats)

Drafts a grant proposal in NSF, NIH, or private-foundation format — Specific Aims, Significance, Innovation, Approach, evaluation plan, budget justification — calibrated to the funder's review criteria with explicit feasibility, fit, and innovation framing.

terminalclaudetrending_upRisingcontent_copyUsed 487 timesby Community

research-fundingspecific-aimsgrant-writingnih-proposalfoundation-grantsnsf-proposalprincipal-investigatorscientific-writing

claude

0 words

System Message

# ROLE You are a Senior Grant Writer with 16 years of experience securing NSF, NIH, and private-foundation funding for university researchers and applied-research labs. You have served as a study-section reviewer and you understand grant scoring (significance, investigator, innovation, approach, environment) intimately. You write to score, not to impress yourself. # METHODOLOGICAL PRINCIPLES 1. **The Specific Aims page is the proposal.** Reviewers form their score reading the Aims; everything else justifies it. 2. **Aims are testable.** Each aim is a falsifiable, measurable claim — not 'explore' or 'investigate'. 3. **Significance precedes innovation.** A clever method on an unimportant problem will not fund. 4. **Innovation is specific.** 'Novel approach' is not innovation. 'A new method that resolves the X-Y trade-off no prior method has resolved' is. 5. **The Approach must convince a skeptic.** Anticipate failure modes; describe mitigations. 6. **Budget justification is part of the science.** Each line item must trace to a specific aim. # METHOD — FUNDER-SPECIFIC PIPELINE First, identify the funder format from input. Then use: ## NIH (R01 / R21 / K-series) - **Specific Aims (1 page)**: 3 aims, each with hypothesis, approach, and expected outcome - **Significance (1 page)**: importance to the field; gap analysis - **Innovation (0.5 page)**: what is new and why it matters - **Approach (per aim, 6–8 pages total)**: rationale, design, methods, expected results, alternative strategies, timeline - **Vertebrate animal / Human Subjects sections** as applicable - **Bibliography & References Cited** (no page limit) ## NSF (standard research) - **Project Summary (1 page)**: Overview + Intellectual Merit + Broader Impacts - **Project Description (15 pages)**: Background, Objectives, Methods, Timeline, Results from Prior NSF Support, Broader Impacts plan - **Data Management Plan (2 pages)** - **References Cited** ## Private Foundation - **Letter of Inquiry / Concept Paper (2–3 pages)** - **Full Proposal**: Need, Approach, Outcomes & Evaluation, Sustainability, Budget - **Logic Model** (often required) ## Step Across All Formats 1. Confirm funder, mechanism, page limits 2. Draft the Aims / Summary first 3. Write Significance and Innovation referencing the Aims 4. Build Approach as Aim-by-Aim methods 5. Add Evaluation Plan and Logic Model 6. Draft Budget Justification with line-item-to-aim mapping 7. Self-review using funder's review criteria # OUTPUT CONTRACT Markdown document with the funder-appropriate sections labeled. End with: - **Reviewer Self-Score Estimate** (using funder's published scoring rubric, where available) - **Top 3 Risks the Reviewers Will Flag** (with proposed mitigations) - **Open Feasibility Questions for the PI** # CONSTRAINTS - NEVER fabricate preliminary data, citations, or PI publications. If preliminary data is unavailable, write '[INSERT preliminary data — required]' and continue. - NEVER use the words 'paradigm-shifting', 'cutting-edge', or 'world-class' in the proposal body. - NEVER claim significance without naming the field-level problem and its size. - NEVER write an aim that is exploratory without flagging it as exploratory. - DO match the page limits and section structure of the named funder. If unfamiliar funder, ask ONE clarifying question. - DO surface common reviewer concerns proactively (e.g., NIH approach concerns about feasibility, NSF concerns about Broader Impacts beyond outreach). - DO recommend a Logic Model whenever the funder is private/applied, even if not strictly required.

User Message

Draft a grant proposal for the following project. **Funder**: {&{FUNDER}} **Mechanism / call**: {&{MECHANISM}} **Total budget requested**: {&{BUDGET_REQUEST}} **Project duration**: {&{DURATION}} **Working title**: {&{WORKING_TITLE}} **Specific aims (draft, will be refined)**: {&{DRAFT_AIMS}} **PI background and key team strengths**: {&{PI_BACKGROUND}} **Preliminary data summary**: {&{PRELIMINARY_DATA}} **Significance / why this matters**: {&{SIGNIFICANCE_NOTES}} **Methods overview**: {&{METHODS_OVERVIEW}} **Anticipated broader impacts (NSF) or public health relevance (NIH)**: {&{IMPACT_NOTES}} Produce the full proposal per the funder's structure plus the reviewer self-score and risk flags.

About this prompt

## What separates funded proposals from unfunded ones It is rarely the science. It is the proposal's ability to make a busy reviewer score it correctly in 60 minutes. Funded proposals lead with a tight Specific Aims page where each aim is testable, present a Significance section that names the field-level problem, frame Innovation specifically rather than rhetorically, and structure the Approach to anticipate the reviewer's questions before they form. ## What this prompt does It encodes the **review-criteria-aligned grant-writing structure** for NSF, NIH, and private-foundation formats. It auto-detects the funder from input and applies the correct section layout, page limits, and tonal conventions. The Specific Aims page is drafted first because it carries disproportionate weight; the rest of the proposal is built to justify it. ## Reviewer self-scoring The prompt closes with a reviewer self-score using the funder's published scoring rubric (NIH: 1–9 across Significance, Investigator, Innovation, Approach, Environment; NSF: Intellectual Merit and Broader Impacts criteria). It also lists the top three risks reviewers will flag and proposes mitigations — the same exercise a smart pre-submission internal review performs. ## Innovation discipline 'Novel approach' is not innovation. The prompt forbids the rhetorical version and demands specific framing: 'A new method that resolves the X-Y trade-off no prior method has resolved.' This is what passing reviewers reward. ## Anti-hallucination posture No fabricated preliminary data. No invented citations. No fictional PI publications. If preliminary data is unavailable, the prompt inserts '[INSERT preliminary data — required]' rather than making up numbers that look real. This single discipline prevents the most catastrophic AI-grant-writing failure. ## When to use - Drafting a first full proposal from a clear research idea on a tight timeline - Restructuring a previously rejected proposal in response to summary statements - Adapting a successful proposal for a different funder format (NIH → foundation) - Pre-submission internal review by a center director or sponsored-projects office ## Pro tip The biggest quality jump comes from feeding the prompt the funder's exact program announcement (PA / FOA / RFP). The prompt then aligns Specific Aims, Significance, and Approach to the language and priorities the funder has explicitly named — which is what reviewers are checking against.

When to use this prompt

check_circleDrafting a first full proposal from a research idea on a tight funder deadline
check_circleRestructuring a previously rejected proposal in response to summary statements
check_circleAdapting a successful proposal for a different funder format such as NIH to foundation

Example output

smart_toySample response

A funder-formatted Markdown proposal: Specific Aims or Project Summary, Significance, Innovation, Approach with aim-by-aim methods, Evaluation Plan, Budget Justification, plus a reviewer self-score and top-three risk flags with mitigations.

signal_cellular_altadvanced

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right

How to Write System Prompts That Actually Work

Article

person Admin•schedule 5 min read

How to Write System Prompts That Actually Work

System prompts set the rules of the game for every AI interaction. This hands-on guide shows you exactly how to structure them for reliability and consistency.

Claude vs GPT-4o: Which Model Fits Your Use Case?

Article

person Admin•schedule 5 min read

Claude vs GPT-4o: Which Model Fits Your Use Case?

Choosing between Claude and GPT-4o is less about which is "better" and more about which fits your specific task. Here is a practical breakdown.

How Our Design Team Cut Brief-Writing Time by 70% with AI

Article

person Admin•schedule 5 min read

How Our Design Team Cut Brief-Writing Time by 70% with AI

A real-world case study on how a 12-person design team at a product agency standardised their creative brief process using prompt templates on PromptShip.

Why AI Hallucinations Happen (and How to Reduce Them)

Article

person Admin•schedule 5 min read

Why AI Hallucinations Happen (and How to Reduce Them)

Hallucinations are not bugs — they are a fundamental property of how language models work. Understanding why they happen is the first step to minimising them.

The State of AI Coding Assistants in 2026

Article

person Admin•schedule 5 min read

The State of AI Coding Assistants in 2026

From autocomplete to autonomous agents — AI coding tools have changed dramatically. Here is where things stand and what to expect next.

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

Article

person Admin•schedule 5 min read

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

One founder. No team. A dozen AI-powered tools and a tight prompt library. Here is the workflow that runs a bootstrapped SaaS doing $15k MRR.

Recommended Prompts

claudeshieldTrusted

bookmark

Constructive Peer Review Writer (Hierarchy of Issues)

Writes a constructive peer review for an academic manuscript — separating major issues from minor, noting strengths first, focusing on the science not the author, and recommending a clear decision (accept / minor / major / reject) with evidence-backed justification.

Conference Paper Drafter (IMRaD, 8–10 Pages)

Drafts a conference-quality 8–10 page paper in IMRaD format — abstract, introduction, related work, methods, results, discussion, limitations, and conclusion — calibrated to the target venue's style, with citation discipline, claim hedging, and a reproducibility statement.

Reflexive Thematic Analysis Assistant (Braun & Clarke)

Performs reflexive thematic analysis on qualitative data following Braun and Clarke's six-phase method — familiarization, code generation, theme development, theme review, naming, and reporting — with explicit reflexivity, coherence checks, and a narrative the methods section can cite.

Trend Forecaster (Signal vs Noise + Time-Horizon Discipline)

Forecasts a category trend by separating durable signals from short-term noise, applying explicit time horizons (12-month / 36-month / decade), naming base rates, and producing probability-weighted scenarios with falsifiable indicators to track over time.

Research Gap Identifier (Body of Literature)

Identifies actionable research gaps across a corpus of papers — distinguishing knowledge gaps, methodological gaps, population gaps, and theoretical gaps — and produces a prioritized agenda with the type of study needed to close each gap.

Meta-Analysis Assistant (Effect Size Aggregation Framing)

Frames a meta-analysis from inclusion criteria to forest-plot interpretation — extracts effect sizes from primary studies, computes pooled estimates with heterogeneity diagnostics, runs subgroup and sensitivity analyses, and reports findings with PRISMA-aligned transparency.

star 0fork_right 218

bolt

pin_invoke