research-grants – skill Dữ liệu & Khoa học cho agent AI

Research Grant Writing

Overview

Research grant writing is the process of developing competitive funding proposals for federal agencies and foundations. Master agency-specific requirements, review criteria, narrative structure, budget preparation, and compliance for NSF (National Science Foundation), NIH (National Institutes of Health), DOE (Department of Energy), DARPA (Defense Advanced Research Projects Agency), and Taiwan's NSTC (National Science and Technology Council) submissions.

Critical Principle: Grants are persuasive documents that must simultaneously demonstrate scientific rigor, innovation, feasibility, and broader impact. Each agency has distinct priorities, review criteria, formatting requirements, and strategic goals that must be addressed.

When to Use This Skill

This skill should be used when:

• Writing research proposals for NSF, NIH, DOE, DARPA, or NSTC programs
• Preparing project descriptions, specific aims, or technical narratives
• Developing broader impacts or significance statements
• Creating research timelines and milestone plans
• Preparing budget justifications and personnel allocation plans
• Responding to program solicitations or funding announcements
• Addressing reviewer comments in resubmissions
• Planning multi-institutional collaborative proposals
• Writing preliminary data or feasibility sections
• Preparing biosketches, CVs, or facilities descriptions

Establish the governing opportunity first

For each task, record agency, opportunity identifier and amendment, activity/project

type, due date/time zone, eligibility, submission stage, application form version,

limits, required attachments, review criteria and source URL/retrieval date. Check

current notices as well as the original solicitation. An archived call, funded award,

or budget announcement does not establish live funding availability. If the official

package is unavailable, provide a bounded drafting review and list unresolved rules.

Build a requirement -> source section -> draft location -> gap matrix before judging

compliance. Templates in assets/ are illustrative worksheets, not official forms.

Never invent data, citations, investigator records, partner commitments or approvals.

Inspect the final exported files; Markdown text does not establish page compliance.

For NIH, use this skill for requirements, critique, consistency checks and limited

editing of investigator-authored material. [NIH policy](https://grants.nih.gov/grants/policy/nihgps/HTML5/section_2/2.3.7_policies_affecting_applications.htm)

excludes applications or sections substantially developed by AI. Preserve applicant

ownership of substantive science and writing; review or disclosure alone does not

make substantial AI authorship compliant. Apply other agencies' current rules too.

Visual Enhancement (Optional)

Strong proposals often include 1–3 figures (timelines, workflow diagrams, preliminary data). Figures support review but are not a substitute for clear aims and methods.

When figures help:

• Research methodology and workflow diagrams
• Project timeline or Gantt charts
• Conceptual framework or system architecture (technical proposals)
• Experimental design flowcharts
• Broader impacts activity diagrams
• NSTC CM03 research architecture diagrams when they clarify the proposed methods

How to create figures:

• Preferred: Use the scientific-schematics skill (--doc-type grant) for AI-generated diagrams from a natural-language description
• Alternative: Build figures in your usual tools (matplotlib, Illustrator, PowerPoint, etc.)

Illustrative optional integration (CLI options checked; no paid generation tested in this refresh). Run from the repository root, with OPENROUTER_API_KEY set:

python skills/scientific-schematics/scripts/generate_schematic.py "project timeline with Year 1-3 milestones" -o figures/timeline.png --doc-type grant

Disclosure: AI schematic generation sends your prompt to [OpenRouter](https://openrouter.ai/) (a third-party API). Do not include unpublished sensitive details unless that transmission is appropriate for your project.

---

Agency-Specific Overview

NSF (National Science Foundation)

Mission: Promote the progress of science and advance national health, prosperity, and welfare

Key Features:

• Use the [current PAPPG index](https://www.nsf.gov/policies/pappg), effective supplements and solicitation; as reviewed, NSF 24-1 is supplemented by NSF 26-200 and 26-202
• Intellectual Merit + Broader Impacts both receive full consideration; no universal numerical weighting
• 15-page project description limit (most programs; includes Results from Prior NSF Support, max 5 pages)
• Education and societal benefit, with activities aligned to current NSF priorities and the solicitation
• Collaborative research encouraged
• Current SciENcv Common Forms, graduate/postdoc mentoring, and Research.gov DMSP tool requirements
• Merit review process with panel + ad hoc reviewers

NIH (National Institutes of Health)

Mission: Enhance health, lengthen life, and reduce illness and disability

Key Features:

• Standard R01: Specific Aims up to 1 page and Research Strategy up to 12; verify the NOFO
• Most RPGs use Importance, Rigor/Feasibility, and Expertise/Resources review factors; required narrative headings remain Significance, Innovation, Approach
• Preliminary evidence normally supports R01 feasibility; follow the mechanism-specific instructions
• Rigor and reproducibility; SciENcv Common Forms and NIH Supplement required under the 2026 implementation
• For eligible applications, modular budgets use $25,000 increments, up to $250,000 in direct costs per budget period, excluding consortium F&A; verify the NOFO and organization eligibility. See [NIH budget guidance](https://grants.nih.gov/grants/developing_budget.htm).
• NIH permits one resubmission (A1) of an unfunded application, within 37 months of the initial application due date when the NOFO permits resubmissions; see [resubmission policy](https://grants.nih.gov/grants-process/submit/submission-policies/resubmission-applications).

DOE (Department of Energy)

Mission: Ensure America's security and prosperity through energy, environmental, and nuclear challenges

Key Features:

• Focus on energy, climate, computational science, basic energy sciences
• Cost sharing and partnerships depend on the specific office, NOFO, and award instrument
• Emphasis on national laboratory collaboration
• Strong computational and experimental integration
• Energy innovation and commercialization pathways
• Distinguish SC, ARPA-E and current applied-energy offices; legacy EERE Exchange now identifies CMEI eXCHANGE

DARPA (Defense Advanced Research Projects Agency)

Mission: Make pivotal investments in breakthrough technologies for national security

Key Features:

• High-risk, high-reward transformative research
• Focus on "DARPA-hard" problems (what if true, who cares)
• Emphasis on prototypes, demonstrations, and transition paths
• Often requires multiple phases (feasibility, development, demonstration)
• Strong project management and milestone tracking
• Teaming and collaboration often required
• Varies dramatically by program manager and BAA (Broad Agency Announcement)

NSTC (National Science and Technology Council - Taiwan)

Mission: Advance scientific breakthrough, industrial application, and societal impact in Taiwan.

Key Features:

• CM03 Form: The core technical proposal format.
• Forms: Use the current call and division forms for Chinese/English abstracts and CM03.
• Innovation & Feasibility: Primary review focus.
• Preliminary Data: Highly critical for credibility.
• Research Architecture Diagram: Useful where appropriate; not a verified universal requirement.

Core Components of Research Proposals

Section-by-section guidance for every standard proposal component — specific aims,

significance, innovation, approach, preliminary data, timeline, budget and justification,

biosketch, facilities, data management and sharing, and broader impacts — with structure,

length targets, and worked language, is in

[references/core_components.md](references/core_components.md).

Review Criteria, Writing Principles, and Proposal Types

• [references/review_criteria.md](references/review_criteria.md): how NIH, NSF, DOE, and

DARPA score proposals, and what each criterion actually rewards.

• [references/writing_principles.md](references/writing_principles.md): what separates

funded proposals from competent ones — framing, specificity, reviewer psychology, and

readability.

• [references/proposal_types_and_resubmission.md](references/proposal_types_and_resubmission.md):

the common proposal types and how to handle a resubmission, including responding to

a summary statement.

Common Mistakes to Avoid

Conceptual Mistakes

1. Failing to Address Review Criteria:

… (nội dung đầy đủ có trong gói tải về)