Source: https://github.com/aipoch/medical-research-skills

Grant Proposal Assistant

A comprehensive tool for writing competitive grant proposals targeting NIH (R01/R21), NSF, and other major funding agencies.

Quick Check

Use this command to verify that the packaged script entry point can be parsed before deeper execution.

python -m py_compile scripts/main.py

Audit-Ready Commands

Use these concrete commands for validation. They are intentionally self-contained and avoid placeholder paths.

python -m py_compile scripts/main.py
python scripts/main.py --help
python scripts/main.py --section project_summary
python scripts/main.py --section project_summary --agency NIH

When to Use

• Use this skill when the task needs Grant proposal writing assistant for NIH (R01/R21), NSF and other mainstream.
• Use this skill for protocol design tasks that require explicit assumptions, bounded scope, and a reproducible output format.
• Use this skill when you need a documented fallback path for missing inputs, execution errors, or partial evidence.

Workflow

1. Confirm the user objective, required inputs, and non-negotiable constraints before doing detailed work.
2. Validate that the request matches the documented scope and stop early if the task would require unsupported assumptions.
3. Use the packaged script path or the documented reasoning path with only the inputs that are actually available.
4. Return a structured result that separates assumptions, deliverables, risks, and unresolved items.
5. If execution fails or inputs are incomplete, switch to the fallback path and state exactly what blocked full completion.

Capabilities

1. Section Templates: Standard templates for all major grant sections
2. Specific Aims Generator: Structured approach to crafting compelling Specific Aims pages
3. Budget Justification Helper: Equipment, personnel, and other cost justifications
4. Review & Critique: Self-assessment checklists for proposal quality

Usage

Command Line

# Generate Specific Aims template
python3 scripts/main.py --section aims --output my_aims.md

# Generate full proposal template
python3 scripts/main.py --section full --agency NIH --type R01 --output proposal.md

# Budget justification helper
python3 scripts/main.py --section budget --category personnel --output budget.md

# Review existing proposal
python3 scripts/main.py --review --input my_proposal.md

As Library

from scripts.main import GrantProposalAssistant

assistant = GrantProposalAssistant(agency="NIH", grant_type="R01")
template = assistant.generate_section("specific_aims")
budget = assistant.generate_budget_justification(category="equipment", items=[...])

Parameters

Parameter	Description	Options
--section	Section to generate	aims, significance, approach, budget, full
--agency	Funding agency	NIH, NSF, DOD, VA
--type	Grant mechanism	R01, R21, R03, SBIR, STTR
--category	Budget category	personnel, equipment, supplies, travel, other
--input	Input file for review	Path to existing proposal
--output	Output file path	Path for generated content

Technical Difficulty

Medium - Requires understanding of grant structure, funding agency requirements, and scientific writing best practices.

References

• references/NIH_R01_template.md - NIH R01 full proposal template
• references/NSF_template.md - NSF standard grant template
• references/budget_templates.xlsx - Budget templates by category
• references/review_checklist.md - Proposal quality checklist
• references/specific_aims_examples.md - Example Specific Aims pages

Best Practices

1. Start with Specific Aims: This 1-page summary drives the entire proposal
2. Follow Page Limits: NIH R01 Research Strategy = 12 pages, Specific Aims = 1 page
3. Use Significance-Innovation-Approach Structure: Standard for NIH applications
4. Justify Everything: Every budget item needs a clear justification
5. Review with Checklist: Use the built-in review tool before submission

Agency-Specific Notes

NIH R01/R21

• Page limits strictly enforced
• Significance, Innovation, Approach structure required
• Vertebrate animals and human subjects sections if applicable
• Resubmission strategy for A1 applications

NSF

• Project Summary (1 page) and Project Description (15 pages)
• Broader impacts criterion weighted equally with intellectual merit
• Data management plan required
• Facilities and resources section

Version

1.0.0 - Initial release with NIH and NSF support

Risk Assessment

Risk Indicator	Assessment	Level
Code Execution	Python/R scripts executed locally	Medium
Network Access	No external API calls	Low
File System Access	Read input files, write output files	Medium
Instruction Tampering	Standard prompt guidelines	Low
Data Exposure	Output files saved to workspace	Low

Security Checklist

• No hardcoded credentials or API keys
• No unauthorized file system access (../)
• Output does not expose sensitive information
• Prompt injection protections in place
• Input file paths validated (no ../ traversal)
• Output directory restricted to workspace
• Script execution in sandboxed environment
• Error messages sanitized (no stack traces exposed)
• Dependencies audited

Prerequisites

No additional Python packages required.

Evaluation Criteria

Success Metrics

• Successfully executes main functionality
• Output meets quality standards
• Handles edge cases gracefully
• Performance is acceptable

Test Cases

1. Basic Functionality: Standard input → Expected output
2. Edge Case: Invalid input → Graceful error handling
3. Performance: Large dataset → Acceptable processing time

Lifecycle Status

• Current Stage: Draft
• Next Review Date: 2026-03-06
• Known Issues: None
• Planned Improvements:
  • Performance optimization
  • Additional feature support

Output Requirements

Every final response should make these items explicit when they are relevant:

• Objective or requested deliverable
• Inputs used and assumptions introduced
• Workflow or decision path
• Core result, recommendation, or artifact
• Constraints, risks, caveats, or validation needs
• Unresolved items and next-step checks

Error Handling

• If required inputs are missing, state exactly which fields are missing and request only the minimum additional information.
• If the task goes outside the documented scope, stop instead of guessing or silently widening the assignment.
• If scripts/main.py fails, report the failure point, summarize what still can be completed safely, and provide a manual fallback.
• Do not fabricate files, citations, data, search results, or execution outcomes.

Input Validation

This skill accepts requests that match the documented purpose of grant-proposal-assistant and include enough context to complete the workflow safely.

Do not continue the workflow when the request is out of scope, missing a critical input, or would require unsupported assumptions. Instead respond:

grant-proposal-assistant only handles its documented workflow. Please provide the missing required inputs or switch to a more suitable skill.

Response Template

Use the following fixed structure for non-trivial requests:

1. Objective
2. Inputs Received
3. Assumptions
4. Workflow
5. Deliverable
6. Risks and Limits
7. Next Checks

If the request is simple, you may compress the structure, but still keep assumptions and limits explicit when they affect correctness.

When Not to Use

• Do not proceed when required input files, identifiers, parameters, or context are missing — ask the user to provide them first.
• Do not assume capabilities beyond this skill's declared scope when the user requests external operations or inferences.
• Do not proceed without user confirmation when overwriting existing results, executing high-cost batch operations, or expanding task scope.

Required Inputs

Field	Required	Format/Source	Example	If Missing
User task description	Yes	Text	Research question, writing goal, analysis objective	Stop and ask user to provide
Primary input material	Depends on task	Text, file path, ID, table, or literature	PMID, PDF, CSV, DOCX, keywords, etc.	Specify which material type is missing
Output preference	No	Text	Language, format, target journal, template	Use skill default format

Output Contract

• Primary output: Structured result or target file aligned with this skill's objective.
• Optional output: Intermediate check notes, issue list, supplementary suggestions, or generated file paths.
• Format requirement: Unless the user specifies otherwise, prefer stable, reviewable Markdown or JSON; if the skill's bundled script requires a fixed format, use that format.
• If partially complete: Must explicitly mark as PARTIAL and state which steps are completed and which remain.

Failure Handling

• Missing critical input: Explicitly state which fields, files, or identifiers are missing and pause.
• Script, template, or resource execution failure: Report the failing step, likely cause, and recovery suggestions — do not silently degrade.
• Partial completion only: Return the verified portion first, then list remaining blockers and suggested next steps.

User Checkpoints

• Before executing batch processing, overwriting files, long-running searches, or multi-stage generation, confirm scope and output format with the user.
• Before proceeding when a key judgment is ambiguous, evidence is insufficient, or the workflow is entering the next stage, confirm with the user.

Quick Validation

• Check that key scripts, templates, or reference file paths this skill depends on exist.
• Check that the final output contains the core fields, sections, or files specified for this task.
• Check that results clearly mark assumptions, limitations, and incomplete items.