grant-writing
Skill2 starsChanged 30 days agoMITView on GitHub
Plan, draft, or review grant and fellowship applications. Exclude manuscript work and career materials outside a funding application.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- lengrufeng2008/dsh-skill-librarytheir own version, first seen Nov 15, 2026
- sbfnk/skillstheir own version, first seen Nov 8, 2026
- BuildHarbor/sciagent-skillstheir own version, first seen Nov 1, 2026
- jjfroehlich/agent-skills-for-academic-researchword for word, first seen Oct 17, 2026
- poemswe/co-researchertheir own version, first seen Oct 13, 2026
- borgr/erc-reviewtheir own version, first seen Sep 11, 2026
Used with
Projects with it also use literature-review.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
JDerekLomasSkillliterature-review
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
Also in 3 projects that use this
Other versions10 projects use a version of this.
Word for word · 1
- jjfroehlich/agent-skills-for-academic-research★ 2100% same
Edited · 0
None found.
Wrote their own version · 9
- poemswe/co-researcher★ 139same name
- xjtulyc/awesome-rosetta-skills★ 34same name
- BuildHarbor/sciagent-skills★ 1same name
- Pratikrishi97/sciagent-skills★ 1same name
- borgr/erc-review★ 0same name
- fabioc-aloha/alex-cognitive-architecture★ 0same name
- lengrufeng2008/dsh-skill-library★ 0same name
- poorvith-mp/skills-writing★ 0same name
- sbfnk/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- career-developmentSkill
- data-visualization-and-figuresSkill
- life-science-research-handbookSkill
- literature-reading-and-synthesisSkill
- mentoring-management-and-lab-cultureSkill
- publishing-and-peer-reviewSkill
- research-strategy-and-project-designSkill
- scientific-communicationSkill
- scientific-feedbackSkill
- scientific-writingSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Use this skill for grant or fellowship applications, specific aims pages, research strategies, project summaries, …
- Distinctive: line 30
Run the full funder-fit, compliance, schedule, and internal-review preflight only for whole-application planning or submission readiness.
- Distinctive: line 66
Do figures, headings, topic sentences, and emphasis let a busy reviewer recover the proposal logic?
- Distinctive: line 81
Check the current call when a compliance question could change the requested work.
- Distinctive: line 83
Avoid generic encouragement unless it is attached to a specific revision action.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Grant Writing
Purpose
Help users turn a funding opportunity and proposal draft into an assessable application: a clear purpose, interpretable proposed work and truthful evidence of fit, capability and resources.
Use this skill when
Use this skill for grant or fellowship applications, specific aims pages, research strategies, project summaries, significance/innovation/approach sections, feasibility and risk reviews, budget-deliverability checks, resubmission planning, and interview preparation for funding mechanisms.
Do not use this skill when
- The task is about manuscript peer review responses.
- The task is about journal cover letters or article submission, not funding.
- The task is general scientific prose editing without a funding context.
- The task is about career materials unless they are part of a funding application.
Core workflow
- Scope the preflight to the deliverable. For whole applications, planning, or readiness judgments, identify the funder, mechanism, required sections, review criteria, audience breadth, deadline, available proposal text, review-team availability, and time left for critique. For a local edit, inspect the supplied text and constraints and identify only missing information that could change that edit.
- Run the full funder-fit, compliance, schedule, and internal-review preflight only for whole-application planning or submission readiness. For local edits, use the supplied constraints and flag only a consequential compliance uncertainty.
- For narrative or structural work, make the objective, premise, payoff, approach, and applicant fit visible. For local prose edits, preserve meaning and supplied constraints.
- Review significance, innovation, aims, feasibility, budget, risks, and alternatives only where they bear on the requested section or readiness judgment.
- Return prioritized edits, not generic encouragement: what to move, cut, relabel, evidence, reframe, or verify against the call.
- Preserve completed, proposed, conditional and unknown states, including pilot findings, access, institutional support and award authority. A clear rewrite cannot supply missing controls or commitments. Inspect the actual document before certifying its visual readability; a written plan is not an executed assessment, submission or agreement.
Reference routing
- Open
references/funder-fit-and-compliance.mdwhen scope, eligibility, instructions, templates, assessor criteria, or submission readiness matter. - Open
references/grant-narrative.mdwhen the central story, objective, premise, section order, or proposal coherence is weak. - Open
references/specific-aims.mdwhen aims, dependencies, overview figures, approach blocks, or aim-level feasibility are central. - Open
references/significance-innovation-approach.mdwhen significance, innovation, impact, DEI, ambition, or approach rationale need work. - Open
references/reviewer-perspective.mdwhen the draft needs panel readability, skim tests, non-specialist framing, reader feedback, or interview preparation. - Open
references/budget-and-feasibility.mdwhen budget, preliminary data, applicant capacity, risk, alternatives, or future-work integrity are at issue. - Open
references/award-start-and-conditions.mdwhen an application decision or planned handoff raises award conditions, authorization, or readiness to begin. Keep financial and legal decisions with the responsible institution. - Open
references/handbook-access.mdwhen a fuller explanation or worked example would help with the current task.
Output formats
Select only the format that fits the requested deliverable; these are patterns, not mandatory response sections.
- Proposal triage memo with funder-fit, reviewer-risk, and next edits.
- Specific aims revision plan.
- Section-level rewrite guidance for significance, innovation, or approach.
- Feasibility and risk audit.
- Readiness checklist with pass/fail items, review timeline, and fixes.
- Template or table for premise, aims, budget, risk-return, or reviewer doubts.
Quick checklist
Apply only the checks relevant to the requested scope and artifact. Inspect supplied context first; treat identify or clarify as analysis when the answer is already available, and ask only for missing information that could change the result.
- Is the opportunity a real fit, and are current instructions reflected in the draft?
- Can a reviewer find the objective, premise, significance, innovation, approach, and feasibility evidence quickly?
- Are aims understandable and their dependencies assessable for this scheme and development stage, with appropriate evidence, qualification milestones, or decision gates?
- Are risks named with alternatives, rather than hidden?
- Do figures, headings, topic sentences, and emphasis let a busy reviewer recover the proposal logic?
Common pitfalls
- Polishing an out-of-scope or noncompliant proposal.
- Burying the objective under background.
- Blurring significance, innovation, and approach into one enthusiasm section.
- Treating preliminary data, CV, budget, impact, or DEI as boilerplate rather than scoring evidence.
- Calling execution gaps "high risk" without a credible development or access plan.
- Adding pilot findings, secured access, or institutional commitments that the user has not supplied.
Quality bar
- Ground advice in the user's funder, mechanism, review criteria, and draft text when available.
- Translate reviewer expectations into concrete edits or checks.
- Check the current call when a compliance question could change the requested work; a local wording edit does not require a full call review.
- Distinguish completed evidence, planned work, unresolved feasibility, selection, spending authority, and technical readiness. A rewrite must preserve their status.
- Avoid generic encouragement unless it is attached to a specific revision action.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

