Skip to content

K-Dense-AI/scientific-agent-skills / skills/research-grants

research-grants

Verified

Supports research proposal preparation and review for NSF, NIH, DOE, DARPA, and Taiwan NSTC, including opportunity-specific requirements, aims, review criteria, budgets, broader impacts, forms, and resubmissions. Use for investigator-authored grant development, compliance matrices, and proposal critiques.

assets/nih_specific_aims_template.md

View on GitHub
# NIH Specific Aims worksheet

Reviewed 2026-10-01. The standard NIH Specific Aims attachment is **up to one page**;
verify the [NOFO and page-limit table](https://grants.nih.gov/grants-process/write-application/how-to-apply-application-guide/page-limits).
This is a planning worksheet for investigator-authored content, not a complete
application or a required paragraph/aim count. NIH permits limited AI assistance,
but applications or sections substantially developed by AI are not eligible under
[its application policy](https://grants.nih.gov/grants/policy/nihgps/HTML5/section_2/2.3.7_policies_affecting_applications.htm).

## Problem, gap and importance

[What consequential scientific problem does the applicant seek to resolve?]
[What do cited studies establish, and what important question remains?]
[Why will resolving that question advance knowledge or health?]

Use verified current statistics only when they help the argument. Do not insert
canned disease-burden numbers or assert that a therapy does not exist without checking.

## Objective, rationale and organizing idea

[Long-term goal, if useful.]
[Specific objective achievable in this application.]
[Investigator's central hypothesis, research question, or development objective.]
[Actual preliminary evidence or published rationale, with limitations and provenance.]

Use placeholders for missing results. Do not turn hypothetical observations into
"our preliminary data" or imply that a named cohort or facility is available.

## Aim [number]: [Action and knowledge/result sought]

[Rationale for the aim.]
[Applicant's proposed design, principal comparison and analysis.]
[What different outcomes would establish.]
[Important dependency and feasible alternative if that dependency fails.]

Repeat only as the scientific scope requires. NIH does not mandate two, three or four
aims. A development or discovery project need not be forced into a causal-hypothesis
format. An aim is more informative when it states what will be learned than when it
merely lists a technique.

## Expected contribution

[Summarize the knowledge or capability the work could deliver.]
[Explain the next scientific step without promising clinical adoption, efficacy or a
future trial that the proposed evidence cannot establish.]

## Review and formatting

Check whether an informed reader can identify the gap, importance, objective, approach
and feasibility. For applicable RPGs, those support NIH's Importance and Rigor/Feasibility
factors; expertise/resources must also be adequate. Keep the substantive science the
applicant's own and verify all citations, data, resources and commitments.

Follow [NIH attachment formatting](https://www.grants.nih.gov/grants-process/write-application/how-to-apply-application-guide/format-attachments):
at least half-inch margins, ordinarily at least 11-point body text, at most six lines
per vertical inch and 15 characters per horizontal inch. Graphic text may be smaller
if legible at actual size. Export and inspect the PDF; this worksheet itself is longer
than a finished aims page and is not evidence of page compliance.
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall