Research Grants
Writes competitive research proposals tailored to NSF, NIH, DOE, DARPA, and Taiwan NSTC review criteria, formats, and budget rules.
Content & WritingIntermediate★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026
What it does
Guides you through planning, drafting, and self-reviewing funding proposals with agency-specific rules baked in.
- Agency playbooks: NSF (Intellectual Merit + Broader Impacts, 15-page project description, PAPPG 24-1), NIH (1-page Specific Aims + 12-page Research Strategy; Significance/Innovation/Approach), DOE (energy, computational science, national-lab partnerships), DARPA (high-risk/high-reward, BAA response, transition paths), Taiwan NSTC (CM03 form, bilingual abstract, research architecture diagram)
- Section-level drafting: specific aims, significance, innovation, approach, preliminary data, timeline, budget and justification, biosketch, facilities, data management and sharing, broader impacts
- Failure-mode checklist: conceptual, writing, technical, formatting, and strategic mistakes to audit against before submission
- Five-phase workflow: from opportunity scouting 2–6 months out to submitting 48 hours early
- Optional figures: hooks into the
scientific-schematicsskill for timelines and workflow diagrams (requires OPENROUTER_API_KEY) - Templates: NSF project summary, NIH specific aims, budget justification
Who it's for
- Early-career researchers and postdocs writing their first federal proposal
- PIs preparing a resubmission and responding to a summary statement
- Researchers in Taiwan assembling an NSTC CM03 package
- Labs repositioning one idea across multiple agencies with different framings
- Research development and sponsored-programs staff supporting faculty
Examples
- NIH R01 aims page: "Draft a one-page Specific Aims for a gut-microbiome and metabolic disease R01 using a Significance–Gap–Aims arc" → a template-backed draft with measurable deliverables per aim.
- Strengthening NSF Broader Impacts: paste a weak draft and ask for a rewrite covering education, diversity, and societal benefit → concrete activities plus evaluation metrics.
- Pre-submission mock review: "Score this 15-page project description against NSF merit review criteria and flag formatting violations and over-scoping" → reviewer-style critique with a prioritized revision list.
· · · Install guide · · ·
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the skills/research-grants folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/research-grants/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/research-grants ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal (Terminal on macOS/Linux, Git Bash or WSL on Windows).
- Create the skills folder if needed:
mkdir -p ~/.claude/skills - Clone the repository:
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git - Copy just this skill:
cp -r scientific-agent-skills/skills/research-grants ~/.claude/skills/ - Confirm the
references/andassets/folders came along:ls ~/.claude/skills/research-grants - Restart Claude Code and try a prompt like "Draft an NIH R01 Specific Aims page for my project."
- (Optional) For generated figures, also install the
scientific-schematicsskill and setexport OPENROUTER_API_KEY=your_key. Avoid sending unpublished sensitive details to the third-party API.
View source on GitHub ↗License: MIT