grant-builder

Name: grant-builder
Author: Aperivue

41installs53forks

How to install grant-builder?

aperivue/medsci-skills/grant-builder

$npx -y skills add Aperivue/medsci-skills --skill grant-builder

Installs into the current project.

Summary

Grant and challenge proposal support for radiology and medical AI projects. Structures significance, innovation, approach, milestones, and consortium roles while keeping claims evidence-based and executable.

Files · 1

View on GitHub

SKILL.md

1	# Grant-Builder Skill
2
3	## Purpose
4
5	This skill supports competitive proposal writing for:
6
7	- national R&D grants
8	- multi-institution consortia
9	- challenge proposals
10	- internal pilot funding
11	- translational medical AI project plans
12	- Korean government grants (산학협력 / 연구계획서 — MOHW 복지부, MOTIE 산자부, MSS 중기부, and regional industry-academia programs)
13
14	It is optimized for projects where clinical relevance, multi-site coordination, and executable milestones matter as much as technical novelty.
15
16	---
17
18	## Korean Government Grant Mode (산학과제 / 연구계획서)
19
20	When the user requests a Korean industry-academia grant (산학과제) or research plan
21	(연구계획서), apply the adaptations below. Korean program terms are preserved in
22	parentheses because they are the literal form used on the funding agency's template.
23
24	### Document Structure (three-attachment format)
25
26	Most Korean grants follow a standardized three-attachment format:
27	- Attachment 1 (첨부1, 기본정보): project title, participating institutions,
28	investigator CVs, publication / patent record.
29	- Attachment 2 (첨부2, 매칭확인서): per-institution cost-share confirmation,
30	typically finalized after a kickoff meeting between the institutions.
31	- Attachment 3 (첨부3, 연구계획서): the 10-page research plan — structure below.
32
33	### Attachment 3 Standard Structure
34
35	```
36	1. Significance & Aims (약 2p)
37	- clinical problem with quantitative framing
38	- domestic + international trends (3–5 year literature / guideline window)
39	- differentiation of the proposed work
40
41	2. Research Content & Methods (약 4p)
42	- staged roadmap (Phase 1 – N with time ranges)
43	- pipeline schematic (mandatory when an AI pipeline is in scope)
44	- per-subproject institution and personnel assignment
45
46	3. Team Capability (약 1p)
47	- expertise + representative record (SCI papers, patents) per investigator
48	- cross-institution synergy (hospital = data / clinical; university = algorithm)
49
50	4. Expected Outcomes & Utilization (약 2p)
51	- quantitative targets: SCI papers, patents
52	- qualitative targets: clinical impact, standardization contribution
53	- linkage to follow-on larger grants (positioning as a seed)
54
55	5. Budget Plan (약 1p)
56	- RA salaries, computing equipment, consumables, academic activities, indirect costs
57	```
58
59	### Writing Tips for Small-Scale Grants (< KRW 30 million)
60
61	- Write for a non-specialist reviewer — assume the evaluator is not in your subfield.
62	- Emphasize feasibility over technical novelty.
63	- Prioritize length / format compliance; exceeding the template incurs scoring penalties.
64	- Include preliminary data or pilot results whenever available.
65	- Keep quantitative targets conservative — undershooting a committed target is punished
66	more than overdelivering on a modest one.
67
68	---
69
70	## Communication Rules
71
72	- Communicate with the user in their preferred language.
73	- Proposal prose should be in the language required by the target call.
74	- Avoid hype. Emphasize unmet need, feasibility, differentiation, and deliverables.
75
76	---
77
78	## Core Outputs
79
80	Depending on the request, produce one or more of:
81
82	- project concept summary
83	- `Significance`
84	- `Innovation`
85	- `Approach`
86	- specific aims
87	- work packages
88	- milestone table
89	- role split by institution
90	- evaluation framework
91	- reviewer-risk memo
92
93	---
94
95	## Workflow
96
97	### Phase 1: Decode the funding call
98
99	Extract:
100	- funding body
101	- call theme
102	- eligibility constraints
103	- deliverable expectations
104	- timeline
105	- evaluation criteria
106
107	If no call text is available, infer a generic academic-medical AI proposal structure and label assumptions.
108
109	### Phase 2: Frame the problem
110
111	Define:
112	- clinical pain point
113	- current workflow limitation
114	- why existing AI or standard care is insufficient
115	- who benefits if the project succeeds
116
117	Gate: Present the problem framing (clinical pain point, gap, proposed solution) to the
118	user. Confirm before building proposal sections — a misframed problem produces an
119	unfundable proposal.
120
121	### Phase 3: Build the proposal spine
122
123	Always articulate:
124	- problem
125	- gap
126	- proposed solution
127	- why this team can execute it
128	- measurable outputs
129
130	### Phase 4: Convert to proposal sections
131
132	#### Significance
133
134	Must answer:
135	- why this matters clinically
136	- why this matters now
137	- why the proposed solution is worth funding
138
139	#### Innovation
140
141	Should focus on:
142	- what is genuinely different
143	- why the integration is new
144	- why the novelty is useful, not just technical
145
146	#### Approach
147
148	Should define:
149	- dataset and participating sites
150	- model or workflow components
151	- validation plan
152	- benchmark/comparator
153	- failure analysis
154	- risk mitigation
155
156	### Phase 5: E

People who liked this also viewed

6 picks

Type

grant-builder

41installs53forks

View on GitHub

How to install grant-builder?

aperivue/medsci-skills/grant-builder

$npx -y skills add Aperivue/medsci-skills --skill grant-builder

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Grant-Builder Skill
2
3	## Purpose
4
5	This skill supports competitive proposal writing for:
6
7	- national R&D grants
8	- multi-institution consortia
9	- challenge proposals
10	- internal pilot funding
11	- translational medical AI project plans
12	- Korean government grants (산학협력 / 연구계획서 — MOHW 복지부, MOTIE 산자부, MSS 중기부, and regional industry-academia programs)
13
14	It is optimized for projects where clinical relevance, multi-site coordination, and executable milestones matter as much as technical novelty.
15
16	---
17
18	## Korean Government Grant Mode (산학과제 / 연구계획서)
19
20	When the user requests a Korean industry-academia grant (산학과제) or research plan
21	(연구계획서), apply the adaptations below. Korean program terms are preserved in
22	parentheses because they are the literal form used on the funding agency's template.
23
24	### Document Structure (three-attachment format)
25
26	Most Korean grants follow a standardized three-attachment format:
27	- Attachment 1 (첨부1, 기본정보): project title, participating institutions,
28	investigator CVs, publication / patent record.
29	- Attachment 2 (첨부2, 매칭확인서): per-institution cost-share confirmation,
30	typically finalized after a kickoff meeting between the institutions.
31	- Attachment 3 (첨부3, 연구계획서): the 10-page research plan — structure below.
32
33	### Attachment 3 Standard Structure
34
35	```
36	1. Significance & Aims (약 2p)
37	- clinical problem with quantitative framing
38	- domestic + international trends (3–5 year literature / guideline window)
39	- differentiation of the proposed work
40
41	2. Research Content & Methods (약 4p)
42	- staged roadmap (Phase 1 – N with time ranges)
43	- pipeline schematic (mandatory when an AI pipeline is in scope)
44	- per-subproject institution and personnel assignment
45
46	3. Team Capability (약 1p)
47	- expertise + representative record (SCI papers, patents) per investigator
48	- cross-institution synergy (hospital = data / clinical; university = algorithm)
49
50	4. Expected Outcomes & Utilization (약 2p)
51	- quantitative targets: SCI papers, patents
52	- qualitative targets: clinical impact, standardization contribution
53	- linkage to follow-on larger grants (positioning as a seed)
54
55	5. Budget Plan (약 1p)
56	- RA salaries, computing equipment, consumables, academic activities, indirect costs
57	```
58
59	### Writing Tips for Small-Scale Grants (< KRW 30 million)
60
61	- Write for a non-specialist reviewer — assume the evaluator is not in your subfield.
62	- Emphasize feasibility over technical novelty.
63	- Prioritize length / format compliance; exceeding the template incurs scoring penalties.
64	- Include preliminary data or pilot results whenever available.
65	- Keep quantitative targets conservative — undershooting a committed target is punished
66	more than overdelivering on a modest one.
67
68	---
69
70	## Communication Rules
71
72	- Communicate with the user in their preferred language.
73	- Proposal prose should be in the language required by the target call.
74	- Avoid hype. Emphasize unmet need, feasibility, differentiation, and deliverables.
75
76	---
77
78	## Core Outputs
79
80	Depending on the request, produce one or more of:
81
82	- project concept summary
83	- `Significance`
84	- `Innovation`
85	- `Approach`
86	- specific aims
87	- work packages
88	- milestone table
89	- role split by institution
90	- evaluation framework
91	- reviewer-risk memo
92
93	---
94
95	## Workflow
96
97	### Phase 1: Decode the funding call
98
99	Extract:
100	- funding body
101	- call theme
102	- eligibility constraints
103	- deliverable expectations
104	- timeline
105	- evaluation criteria
106
107	If no call text is available, infer a generic academic-medical AI proposal structure and label assumptions.
108
109	### Phase 2: Frame the problem
110
111	Define:
112	- clinical pain point
113	- current workflow limitation
114	- why existing AI or standard care is insufficient
115	- who benefits if the project succeeds
116
117	Gate: Present the problem framing (clinical pain point, gap, proposed solution) to the
118	user. Confirm before building proposal sections — a misframed problem produces an
119	unfundable proposal.
120
121	### Phase 3: Build the proposal spine
122
123	Always articulate:
124	- problem
125	- gap
126	- proposed solution
127	- why this team can execute it
128	- measurable outputs
129
130	### Phase 4: Convert to proposal sections
131
132	#### Significance
133
134	Must answer:
135	- why this matters clinically
136	- why this matters now
137	- why the proposed solution is worth funding
138
139	#### Innovation
140
141	Should focus on:
142	- what is genuinely different
143	- why the integration is new
144	- why the novelty is useful, not just technical
145
146	#### Approach
147
148	Should define:
149	- dataset and participating sites
150	- model or workflow components
151	- validation plan
152	- benchmark/comparator
153	- failure analysis
154	- risk mitigation
155
156	### Phase 5: E

People who liked this also viewed

6 picks

Type