alterlab-research-grants — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited alterlab-research-grants (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
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.
This skill should be used when:
Well-chosen figures strengthen a proposal: a Gantt chart clarifies the timeline, a conceptual framework orients reviewers, and a workflow diagram makes methodology legible at a glance. Figures are optional — add them only where they genuinely improve clarity, and never pad a proposal with decorative graphics.
If a diagram or figure would aid comprehension, invoke the alterlab-scientific-schematics skill (diagrams/schematics) or the alterlab-generate-image skill (images). Figures are optional — add them only where they improve clarity.
Where figures typically earn their space in a proposal:
| Agency | Core structure | Primary review focus |
|---|---|---|
| NSF | 15-page project description; 1-page project summary | Intellectual Merit + Broader Impacts (equal weight) |
| NIH | 1-page Specific Aims + 12-page Research Strategy (R01) | Significance, Investigators, Innovation, Approach, Environment |
| DOE | Project narrative; often cost-sharing | Technical merit, mission relevance, often national-lab collaboration |
| DARPA | Technical volume by phase; BAA-driven | DARPA-hard impact (Heilmeier Catechism), transition paths |
| NSTC (Taiwan) | CM03 form; bilingual abstract; architecture diagram | Innovation, Feasibility, PI Capability, Value |
Full agency profiles, complete review criteria, and award-mechanism catalogs (NSF CAREER/RAPID/EAGER; NIH R01/R21/R35/F-series/K-series; DOE Office of Science/ARPA-E/EERE; DARPA YFA/offices) are in references/agency_profiles.md. For binding requirements and formatting, use the per-agency guides: references/nsf_guidelines.md, references/nih_guidelines.md, references/doe_guidelines.md, references/darpa_guidelines.md, references/nstc_guidelines.md.
A competitive proposal assembles these ten components. Detailed purpose, length, essential elements, and writing strategy for each — plus discipline-specific method guidance — are in references/proposal_components.md.
references/specific_aims_guide.md).references/broader_impacts.md).references/research_methods.md).references/timeline_planning.md).references/team_building.md).references/budget_preparation.md).These cross-cutting topics are consolidated in references/writing_and_workflow.md:
persuasion arc; active voice and precise language; figure design; balancing innovation against risk; internal coherence (budget/timeline/team/aims must align).
references/resubmission_strategies.md).submission (submit 24-48 h early; never wait for the deadline).
Load these as needed; the body above already cites each one at its point of use.
references/agency_profiles.md — agency profiles, review criteria, award-mechanism catalogs (NSF/NIH/DOE/DARPA/NSTC)references/proposal_components.md — the ten core proposal components, with discipline-specific method guidancereferences/writing_and_workflow.md — writing principles, common mistakes, and the 5-phase development workflowreferences/nsf_guidelines.md, nih_guidelines.md, doe_guidelines.md, darpa_guidelines.md, nstc_guidelines.mdreferences/broader_impacts.md, specific_aims_guide.md, research_methods.md, budget_preparation.md, timeline_planning.md, team_building.md, resubmission_strategies.mdassets/nsf_project_summary_template.md: NSF project summary structureassets/nih_specific_aims_template.md: NIH specific aims page templateassets/budget_justification_template.md: Budget justification structurereferences/ (nsf_guidelines.md, nih_guidelines.md, doe_guidelines.md, darpa_guidelines.md, nstc_guidelines.md) and references/team_building.md.This skill ships no helper scripts; handle these tasks directly:
references/ (e.g. references/nsf_guidelines.md, references/nih_guidelines.md).references/budget_preparation.md and the assets/budget_justification_template.md structure.references/timeline_planning.md.Final Note: Grant writing is both an art and a science. Success requires not only excellent research ideas but also clear communication, strategic positioning, and meticulous attention to detail. Start early, seek feedback, and remember that even the best researchers face rejection—persistence and revision are key to funding success.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.