Grant-Builder Skill
Purpose
This skill supports competitive proposal writing for:
- national R&D grants
- multi-institution consortia
- challenge proposals
- internal pilot funding
- translational medical AI project plans
- Korean government grants (산학협력 / 연구계획서 — MOHW 복지부, MOTIE 산자부, MSS 중기부, and regional industry-academia programs)
It is optimized for projects where clinical relevance, multi-site coordination, and executable milestones matter as much as technical novelty.
Korean Government Grant Mode (산학과제 / 연구계획서)
When the user requests a Korean industry-academia grant (산학과제) or research plan
(연구계획서), apply the adaptations below. Korean program terms are preserved in
parentheses because they are the literal form used on the funding agency's template.
Document Structure (three-attachment format)
Most Korean grants follow a standardized three-attachment format:
- Attachment 1 (첨부1, 기본정보): project title, participating institutions,
investigator CVs, publication / patent record.
- Attachment 2 (첨부2, 매칭확인서): per-institution cost-share confirmation,
typically finalized after a kickoff meeting between the institutions.
- Attachment 3 (첨부3, 연구계획서): the 10-page research plan — structure below.
Attachment 3 Standard Structure
1. Significance & Aims (약 2p)
- clinical problem with quantitative framing
- domestic + international trends (3–5 year literature / guideline window)
- differentiation of the proposed work
2. Research Content & Methods (약 4p)
- staged roadmap (Phase 1 – N with time ranges)
- pipeline schematic (mandatory when an AI pipeline is in scope)
- per-subproject institution and personnel assignment
3. Team Capability (약 1p)
- expertise + representative record (SCI papers, patents) per investigator
- cross-institution synergy (hospital = data / clinical; university = algorithm)
4. Expected Outcomes & Utilization (약 2p)
- quantitative targets: SCI papers, patents
- qualitative targets: clinical impact, standardization contribution
- linkage to follow-on larger grants (positioning as a seed)
5. Budget Plan (약 1p)
- RA salaries, computing equipment, consumables, academic activities, indirect costs
Writing Tips for Small-Scale Grants (< KRW 30 million)
- Write for a non-specialist reviewer — assume the evaluator is not in your subfield.
- Emphasize feasibility over technical novelty.
- Prioritize length / format compliance; exceeding the template incurs scoring penalties.
- Include preliminary data or pilot results whenever available.
- Keep quantitative targets conservative — undershooting a committed target is punished
more than overdelivering on a modest one.
Communication Rules
- Communicate with the user in their preferred language.
- Proposal prose should be in the language required by the target call.
- Avoid hype. Emphasize unmet need, feasibility, differentiation, and deliverables.
Core Outputs
Depending on the request, produce one or more of:
- project concept summary
Significance
Innovation
Approach
- specific aims
- work packages
- milestone table
- role split by institution
- evaluation framework
- reviewer-risk memo
Workflow
Phase 1: Decode the funding call
Extract:
- funding body
- call theme
- eligibility constraints
- deliverable expectations
- timeline
- evaluation criteria
If no call text is available, infer a generic academic-medical AI proposal structure and label assumptions.
Phase 2: Frame the problem
Define:
- clinical pain point
- current workflow limitation
- why existing AI or standard care is insufficient
- who benefits if the project succeeds
Gate: Present the problem framing (clinical pain point, gap, proposed solution) to the
user. Confirm before building proposal sections — a misframed problem produces an
unfundable proposal.
Phase 3: Build the proposal spine
Always articulate:
- problem
- gap
- proposed solution
- why this team can execute it
- measurable outputs
Phase 4: Convert to proposal sections
Significance
Must answer:
- why this matters clinically
- why this matters now
- why the proposed solution is worth funding
Innovation
Should focus on:
- what is genuinely different
- why the integration is new
- why the novelty is useful, not just technical
Approach
Should define:
- dataset and participating sites
- model or workflow components
- validation plan
- benchmark/comparator
- failure analysis
- risk mitigation
Phase 5: Execution plan
Generate:
- milestones by quarter or year
- institution-level responsibilities
- dependencies and handoffs
- required infrastructure
Default Structure
## Proposal Summary
Title: ...
Goal: ...
Clinical problem: ...
### Significance
...
### Innovation
...
### Approach
Aim 1. ...
Aim 2. ...
Aim 3. ...
### Milestones
- ...
### Consortium roles
- ...
### Major risks and mitigations
- ...
Evaluation Heuristics
Before finalizing, check:
- Is the clinical need explicit and credible?
- Is the novelty more than "we will use AI"?
- Are the aims linked to measurable outputs?
- Is the validation plan convincing?
- Is the multi-site structure realistic?
- Are compute, annotation, and regulatory needs acknowledged?
- Does each institution have a distinct role?
Common Weaknesses To Flag
- novelty described without clinical consequence
- vague benchmark or success criterion
- no external validation or deployment path
- too many aims for the timeline
- consortium members listed but not functionally integrated
- proposal sounds like a paper, not a funded program
Handoff Rules
- route to
search-lit to support significance and prior-art positioning
- route to
design-study if the evaluation framework is weak
- route to
write-paper only when the proposal requires publication-style narrative sections
What This Skill Does NOT Do
- It does not fabricate budget details
- It does not promise datasets, partners, or infrastructure not evidenced by the user
- It does not replace institutional administrative review
Anti-Hallucination
- Never fabricate references. All citations must be verified via
/search-lit with confirmed DOI or PMID. Mark unverified references as [UNVERIFIED - NEEDS MANUAL CHECK].
- Never invent clinical definitions, diagnostic criteria, or guideline recommendations. If uncertain, flag with
[VERIFY] and ask the user.
- Never fabricate numerical results — compliance percentages, scores, effect sizes, or sample sizes must come from actual data or analysis output.
- If a reporting guideline item, journal policy, or clinical standard is uncertain, state the uncertainty rather than guessing.
1---2name: grant-builder3description: >4 Grant and challenge proposal support for radiology and medical AI projects. Structures significance,5 innovation, approach, milestones, and consortium roles while keeping claims evidence-based and executable.6triggers: grant, proposal, aims page, grant proposal, significance, innovation, approach, milestones, 산학과제, 산학협력, 과제계획서, 연구계획서, 연구비 신청, 첨부37tools: Read, Write, Edit, Bash, Grep, Glob8model: inherit9metadata:10 source: https://skillmd.com/skills/aperivue/grant-builder11---1213# Grant-Builder Skill1415## Purpose1617This skill supports competitive proposal writing for:1819- national R&D grants20- multi-institution consortia21- challenge proposals22- internal pilot funding23- translational medical AI project plans24- **Korean government grants** (산학협력 / 연구계획서 — MOHW 복지부, MOTIE 산자부, MSS 중기부, and regional industry-academia programs)2526It is optimized for projects where clinical relevance, multi-site coordination, and executable milestones matter as much as technical novelty.2728---2930## Korean Government Grant Mode (산학과제 / 연구계획서)3132When the user requests a Korean industry-academia grant (산학과제) or research plan33(연구계획서), apply the adaptations below. Korean program terms are preserved in34parentheses because they are the literal form used on the funding agency's template.3536### Document Structure (three-attachment format)3738Most Korean grants follow a standardized three-attachment format:39- **Attachment 1 (첨부1, 기본정보)**: project title, participating institutions,40 investigator CVs, publication / patent record.41- **Attachment 2 (첨부2, 매칭확인서)**: per-institution cost-share confirmation,42 typically finalized after a kickoff meeting between the institutions.43- **Attachment 3 (첨부3, 연구계획서)**: the 10-page research plan — structure below.4445### Attachment 3 Standard Structure4647```481. Significance & Aims (약 2p)49 - clinical problem with quantitative framing50 - domestic + international trends (3–5 year literature / guideline window)51 - differentiation of the proposed work52532. Research Content & Methods (약 4p)54 - staged roadmap (Phase 1 – N with time ranges)55 - pipeline schematic (mandatory when an AI pipeline is in scope)56 - per-subproject institution and personnel assignment57583. Team Capability (약 1p)59 - expertise + representative record (SCI papers, patents) per investigator60 - cross-institution synergy (hospital = data / clinical; university = algorithm)61624. Expected Outcomes & Utilization (약 2p)63 - quantitative targets: SCI papers, patents64 - qualitative targets: clinical impact, standardization contribution65 - linkage to follow-on larger grants (positioning as a seed)66675. Budget Plan (약 1p)68 - RA salaries, computing equipment, consumables, academic activities, indirect costs69```7071### Writing Tips for Small-Scale Grants (< KRW 30 million)7273- Write for a non-specialist reviewer — assume the evaluator is not in your subfield.74- Emphasize feasibility over technical novelty.75- Prioritize length / format compliance; exceeding the template incurs scoring penalties.76- Include preliminary data or pilot results whenever available.77- Keep quantitative targets conservative — undershooting a committed target is punished78 more than overdelivering on a modest one.7980---8182## Communication Rules8384- Communicate with the user in their preferred language.85- Proposal prose should be in the language required by the target call.86- Avoid hype. Emphasize unmet need, feasibility, differentiation, and deliverables.8788---8990## Core Outputs9192Depending on the request, produce one or more of:9394- project concept summary95- `Significance`96- `Innovation`97- `Approach`98- specific aims99- work packages100- milestone table101- role split by institution102- evaluation framework103- reviewer-risk memo104105---106107## Workflow108109### Phase 1: Decode the funding call110111Extract:112- funding body113- call theme114- eligibility constraints115- deliverable expectations116- timeline117- evaluation criteria118119If no call text is available, infer a generic academic-medical AI proposal structure and label assumptions.120121### Phase 2: Frame the problem122123Define:124- clinical pain point125- current workflow limitation126- why existing AI or standard care is insufficient127- who benefits if the project succeeds128129**Gate:** Present the problem framing (clinical pain point, gap, proposed solution) to the130user. Confirm before building proposal sections — a misframed problem produces an131unfundable proposal.132133### Phase 3: Build the proposal spine134135Always articulate:136- problem137- gap138- proposed solution139- why this team can execute it140- measurable outputs141142### Phase 4: Convert to proposal sections143144#### Significance145146Must answer:147- why this matters clinically148- why this matters now149- why the proposed solution is worth funding150151#### Innovation152153Should focus on:154- what is genuinely different155- why the integration is new156- why the novelty is useful, not just technical157158#### Approach159160Should define:161- dataset and participating sites162- model or workflow components163- validation plan164- benchmark/comparator165- failure analysis166- risk mitigation167168### Phase 5: Execution plan169170Generate:171- milestones by quarter or year172- institution-level responsibilities173- dependencies and handoffs174- required infrastructure175176---177178## Default Structure179180```text181## Proposal Summary182Title: ...183Goal: ...184Clinical problem: ...185186### Significance187...188189### Innovation190...191192### Approach193Aim 1. ...194Aim 2. ...195Aim 3. ...196197### Milestones198- ...199200### Consortium roles201- ...202203### Major risks and mitigations204- ...205```206207---208209## Evaluation Heuristics210211Before finalizing, check:2122131. Is the clinical need explicit and credible?2142. Is the novelty more than "we will use AI"?2153. Are the aims linked to measurable outputs?2164. Is the validation plan convincing?2175. Is the multi-site structure realistic?2186. Are compute, annotation, and regulatory needs acknowledged?2197. Does each institution have a distinct role?220221---222223## Common Weaknesses To Flag224225- novelty described without clinical consequence226- vague benchmark or success criterion227- no external validation or deployment path228- too many aims for the timeline229- consortium members listed but not functionally integrated230- proposal sounds like a paper, not a funded program231232---233234## Handoff Rules235236- route to `search-lit` to support significance and prior-art positioning237- route to `design-study` if the evaluation framework is weak238- route to `write-paper` only when the proposal requires publication-style narrative sections239240---241242## What This Skill Does NOT Do243244- It does not fabricate budget details245- It does not promise datasets, partners, or infrastructure not evidenced by the user246- It does not replace institutional administrative review247248## Anti-Hallucination249250- **Never fabricate references.** All citations must be verified via `/search-lit` with confirmed DOI or PMID. Mark unverified references as `[UNVERIFIED - NEEDS MANUAL CHECK]`.251- **Never invent clinical definitions, diagnostic criteria, or guideline recommendations.** If uncertain, flag with `[VERIFY]` and ask the user.252- **Never fabricate numerical results** — compliance percentages, scores, effect sizes, or sample sizes must come from actual data or analysis output.253- If a reporting guideline item, journal policy, or clinical standard is uncertain, state the uncertainty rather than guessing.