%202.png)
Grant and Funding Proposal Development
Write to the call's assessment criteria, argue feasibility and impact instead of asserting them, and plan around a base rate most applicants are never told.
Free. Works on Claude, ChatGPT, Gemini or any assistant that accepts a skill file.
What this skill does
The method, encoded.
Most funding applications are written as descriptions of a project and assessed as answers to a set of criteria. The gap between those two things is where most avoidable failures live. Reviewers score item by item, often under time pressure, and often across a mixed panel where the person grading your application is not from your subfield. An application that never states its question in a form a non-specialist can grasp, or that leaves feasibility to be inferred from a publication list, loses points the research deserved.
This skill starts where the assessment does. It builds a criteria map from the call before a word is written, so that every scored item has a location, evidence and an owner, and so that effort is weighted the way the marks are. It tests funder fit honestly, distinguishing a project that serves a priority from one dressed to look as if it does, which reviewers detect and penalise. It makes you write the research question three times, including once in plain language, because that version is a test rather than a simplification.
It then does the work applicants usually skip: feasibility argued from prior delivery, confirmed access, pilot data and a schedule that accounts for approvals; a work plan with real dependencies and real slack; a risk register that includes the risk you actually worry about, including that the hypothesis is wrong; a team justified by role rather than reputation; a budget every line of which traces to an activity; and an impact plan with named beneficiaries, an articulated pathway, and activities that are scheduled and costed.
It is also honest that most applications are unsuccessful, that this is a base rate rather than a verdict, and how to plan around it.
Best used for
- Writing a full application against an open call
- Deciding whether a project genuinely fits a funder's priorities
- Building a feasible work plan, milestone schedule and risk register
- Justifying a team by role rather than by reputation
- Structuring a budget justification that traces to the work plan
- Writing an impact section that is a plan rather than an aspiration
- Rebuilding an application after rejection
Typical inputs
What you give it.
The full call document, including assessment criteria and hard rules, A research idea at the level of a question, aim and approach, The team's actual track record, supplied by the people concerned, Optional funder strategy, priorities and previously funded projects, Optional feedback and scores from a previous unsuccessful application, Collaborator and partner commitments, agreed or in negotiation, Costing information from the institution's finance function, Optional pilot or preliminary data
Typical outputs
What you get back.
Criteria map with weight, location, evidence and owner per criterion, Hard-rules checklist covering eligibility, limits, sections and deadlines, Funder fit statement naming the priorities served and how, Case for support with the research question stated for specialist and lay readers, Work plan with dependencies, milestones and slack, Risk register including the scientific risk, Team justification mapping capability to work package and committed time, Budget mapped line by line to the work plan, with a structural justification, Impact plan with beneficiaries, pathway, costed activities and indicators, Data management, ethics and governance sections, Resubmission statement and portfolio plan
Method coverage
What the skill works through.
- Why applications are written to projects and assessed against criteria
- Reading the call and building the criteria map
- Testing funder fit, and the difference between fitting and pretending to fit
- Stating the research question for a mixed panel
- The case for support: objectives that are outcomes, methods that are argued
- Feasibility, and using track record as evidence rather than credential
- Work plans, dependencies, milestones and slack
- Risk registers that include the risk you actually worry about
- Justifying the team by role
- Building a budget from the work plan and reading it back
- Impact as a plan: beneficiaries, pathway, activities, indicators
- Data management, ethics and governance
- Resubmission and using reviewer comments
- Base rates, portfolios and planning around rejection
Download
Free skill. One file.
Enter your email once. Every skill you download after that takes a single click.
How to install
Add the skill file and the five kernel protocols to a Claude Project, a ChatGPT Project, a Gemini Gem, or paste them at the top of any assistant conversation. Then give it your real research material, not a description of it.
Download skillQuestions
Common questions.
How do I write a research grant application?
Start from the assessment criteria, not from the project. Extract them with their weights, build a table showing where each will be addressed and what evidence supports it, and allocate your effort in proportion to the marks. Applicants routinely spend most of their time on the section they enjoy and least on the section carrying a third of the score.
How do I know if my project fits a funder?
Test whether the funder's priority is visible in your objectives and work plan, not just in your opening and closing paragraphs. If removing the priority would leave the project unchanged, you are pretending to fit, and reviewers who care about that priority will see it. Partial fit stated honestly is a stronger position than an unconvincing claim to serve the whole remit.
What makes a strong case for support?
Objectives that are outcomes rather than activities, a small number of them; methods argued against the alternative the reviewer is already thinking of; significance that survives being stated in plain language; and every assessment criterion findable without searching. Signposting helps: a reviewer scoring against a scheme is grateful for it.
How do I write a lay summary or plain-language section?
Write the research question three times: for a specialist, for a colleague outside your subfield, and in two or three sentences for an intelligent reader with no background, saying what is not known, why that matters, and what the project would establish. The plain version is a test rather than a simplification: if the significance evaporates when stated plainly, the panel would have found that too.
What should a research risk register contain?
The risks you actually face: recruitment shortfall, access withdrawn, a key person leaving, delayed approvals, dependency on an external partner, and the possibility that the central hypothesis is wrong. Each with an honest likelihood and impact, and a specific mitigation that is already in the plan. Naming the scientific risk and showing the project still yields something is one of the strongest signals in an application.
How do I write a pathways to impact section?
Name who specifically benefits and what they would do differently; articulate what has to happen between a finding and that change, including who must be persuaded and in what form; schedule and cost the activities that make those steps happen; and give indicators proportionate to a research project. Engagement that starts during the project is far more credible than a dissemination phase at the end. Where the realistic impact is academic, say so.
How detailed should a grant budget justification be?
Every line should map to a work package, and every work package should have the resources it needs; check both directions, because the second catches a plan the budget cannot deliver. Justify necessity and scale rather than restating the figures. Under-costing is a feasibility risk, not a virtue, and reviewers score it as one. Get real figures from whoever owns them rather than estimating.
My grant was rejected. Should I resubmit?
It depends which of three things happened. Scored well and missed the funding line: resubmit with modest strengthening. Scored poorly on a criterion you can fix: rebuild that section. Scored poorly on fit or significance: the project needs a different funder or a rethink. Applicants reliably misread which case they are in. Check the scheme's resubmission rules first, since they vary.
What is a normal success rate for research funding?
Most competitive schemes fund a minority of applications, frequently well under a third and sometimes far less, so an unsuccessful application is the modal outcome for good research written up well. Check the published rate for your scheme rather than assuming. The practical consequence is that the sensible unit of planning is a portfolio and a schedule, not a single submission: identify two or three plausible calls, build reusable components, stage the work so a smaller award can establish feasibility for a larger one, and protect the time to write the next application.
The skill chain
Works well with.
Research where people already are.
Analyse it where you already work.
Yazi helps researchers conduct surveys, AI interviews and longitudinal research directly through WhatsApp.
