Nsf Grant GuideSAFE
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库,覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文,并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.
Overview
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库,覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文,并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.
e1ba289846fdOBSERVED · 2026-10-08Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| openclaw | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: nsf-grant-guide
description: "Navigate NSF grant applications, program selection, and strategies"
metadata:
openclaw:
emoji: "💰"
category: "research"
subcategory: "funding"
keywords: ["NSF grant", "grant writing", "funding", "research proposal", "broader impacts", "NSF program"]
source: "wentor-research-plugins"
---
# NSF Grant Guide
A skill for navigating the National Science Foundation (NSF) grant application process. Covers program selection, proposal structure, the dual review criteria (Intellectual Merit and Broader Impacts), budget preparation, and strategies for improving funding success.
## NSF Proposal Structure
### Required Sections
```
1. Cover Sheet (generated by Research.gov/FastLane)
2. Project Summary (1 page max)
- Overview
- Intellectual Merit statement
- Broader Impacts statement
3. Project Description (15 pages max for most programs)
- Introduction and background
- Proposed research plan
- Broader impacts plan
- Timeline and milestones
4. References Cited (no page limit)
5. Budget and Budget Justification
6. Biographical Sketches (3 pages per PI/co-PI)
7. Current and Pending Support
8. Data Management Plan (2 pages max)
9. Facilities, Equipment, and Other Resources
10. Supplementary Documents (letters of collaboration, etc.)
```
### Project Summary Template
```
Project Summary (1 page, three separate sections):
Overview:
"This project will [what you will do] to address [problem].
We propose [approach/method] that will [expected outcome].
The work will be conducted over [duration] at [institution]."
Intellectual Merit:
"The intellectual merit of this project lies in [contribution
to knowledge]. Specifically, this work will advance understanding
of [topic] by [how]. The proposed approach is innovative because
[novelty]. The PI has expertise in [relevant qualifications]."
Broader Impacts:
"The broader impacts include [societal benefits]. Specifically,
the project will [education component, broadening participation,
infrastructure, dissemination, or societal benefit]. These
activities will benefit [who] by [how]."
```
## Intellectual Merit and Broader Impacts
### The Two Review Criteria
```python
def evaluate_merit_criteria() -> dict:
"""
NSF's two merit review criteria and their elements.
"""
return {
"intellectual_merit": {
"definition": (
"The potential to advance knowledge within and across "
"fields of science and engineering."
),
"elements_reviewers_consider": [
"What is the potential for the proposed activity to advance "
"knowledge and understanding within its own field or across fields?",
"To what extent does the proposed activity suggest and explore "
"creative, original, or potentially transformative concepts?",
"Is the plan for carrying out the proposed activities well-reasoned, "
"well-organized, and based on a sound rationale?",
"How well qualified is the individual, team, or organization to "
"conduct the proposed activities?",
"Are there adequate resources available?"
]
},
"broader_impacts": {
"definition": (
"The potential to benefit society and contribute to the "
"achievement of specific, desired societal outcomes."
),
"examples": [
"Training and mentoring students (especially underrepresented groups)",
"Curriculum development and educational outreach",
"Public engagement with science and technology",
"Partnerships with industry, government, or community organizations",
"Infrastructure for research and education",
"Broadening participation of underrepresented groups in STEM"
],
"common_mistake": (
"Do not treat broader impacts as an afterthought. "
"Reviewers and panels weight this criterion equally with "
"intellectual merit."
)
}
}
```
## Finding the Right Program
### Program Selection Strategy
```
1. Browse NSF Directorates and Divisions:
- BIO (Biological Sciences)
- CISE (Computer & Information Science & Engineering)
- ENG (Engineering)
- GEO (Geosciences)
- MPS (Mathematical & Physical Sciences)
- SBE (Social, Behavioral & Economic Sciences)
- EDU (STEM Education)
2. Use NSF Award Search (nsf.gov/awardsearch):
- Search by keyword to find funded projects similar to yours
- Note which program funded them
3. Read program solicitations carefully:
- Check eligibility requirements
- Note submission deadlines (some are annual, some rolling)
- Check page limits and special requirements
4. Contact the Program Director:
- Send a 1-page summary of your idea
- Ask if it fits the program scope
- This is expected and encouraged by NSF
```
## Budget Preparation
### Common Budget Categories
```
A. Senior Personnel:
- PI and co-PI salary and fringe benefits
- Summer months for academic-year faculty (typically 1-2 months)
B. Other Personnel:
- Graduate research assistants (stipend + tuition)
- Postdoctoral researchers
- Undergraduate students (REU supplements available)
- Technical staff
C. Fringe Benefits:
- Rates set by your institution's sponsored programs office
D. Equipment:
- Items over $5,000 (institution-specific threshold)
E. Travel:
- Domestic and international conference travel
- Fieldwork travel
F. Other Direct Costs:
- Materials and supplies
- Publication costs
- Participant support (stipends for workshop attendees)
- Subawards to collaborating institutions
G. Indirect Costs (F&A):
- Negotiated rate between your institution and the federal goTrust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
e1ba289846fdfull audit observations/trust-audit/skill/brycewang-stanford__nsf-grant-guide.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | e1ba289846fd | SAFE | B | 89 | first audit |
Questions
What does the Nsf Grant Guide skill do?
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库,覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文,并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.
Is Nsf Grant Guide safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Nsf Grant Guide access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Nsf Grant Guide work with?
Its documentation mentions openclaw. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (e1ba289846fd), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.