Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Grant Proposal Drafter Pro

    1

    Turn a nonprofit's mission, program details, and budget into a complete grant proposal draft in which every unverified fact is marked for review.

    $2.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    About this skill

    Turn a nonprofit's mission, program details, and budget into a complete grant proposal draft in which every unverified fact is marked for review.

    For drafting a grant proposal or funding application, writing one section such as a statement of need, budget narrative, or evaluation plan, or checking whether a specific funder fits before investing time. The placeholders are the product as much as the prose: you can see exactly what to confirm before anything reaches a funder.

    Why it matters: A smooth draft with made up facts is a failure, and funders check arithmetic and penalize overpromising. This skill keeps a draft honest: every unsupplied fact becomes a bracketed placeholder, every budget figure is reconciled by script, and a poor funder fit gets a plain Do not apply verdict before you invest more time.

    What it does:

    • Normalizes an org profile in any form, pasted text, bullet list, or attached document, and lists all missing fields once, in one message, instead of asking one question at a time.
    • Derives an inputs to activities to outputs to outcomes logic model from the program description, and shows it for confirmation or correction before drafting any section.
    • Drafts five sections in order: executive summary, statement of need, program description, budget narrative, evaluation plan, using funder ready plain language with no hype, no jargon, and no guaranteed outcomes.
    • Rewrites overpromising claims as measurable, honest claims, and tells you why.
    • Builds the budget narrative from supplied figures only, runs the reconciliation script, and stops on any failed reconciliation, showing the flags to resolve before finishing.
    • Scores funder fit with a rubric as soon as a funder and enough profile information are available. If the fit is poor, it says so plainly with reasons. A clear fail at intake, such as wrong geography, is raised then, with a choice to continue anyway.
    • Runs the placeholder script on the full draft and delivers the draft together with a checklist of every placeholder sorted by section. Nothing should go to a funder until every item is confirmed.

    Honest limits:

    • Never invent a number, date, statistic, citation, outcome, name, or legal status. If you did not supply it, it becomes a bracketed placeholder. This rule beats fluency, length, and the wish to produce a polished draft.
    • Simple arithmetic on supplied figures is allowed, but it must be correct and must agree with the budget check script.
    • It does not submit applications or interact with funder portals.
    • It does not guarantee or predict funding outcomes.
    • It does not verify facts, statistics, or legal status. It marks them for you to verify.
    • It does not write a letter of intent in version 1. If asked, it says so, offers to draft the executive summary as a starting point, and keeps going.
    • No budget figures at all means the other four sections are drafted, and the budget narrative is marked BLOCKED: needs budget figures, with the figures needed listed.
    • A vague mission, such as we help people, is not drafted from fluff. It asks who you serve, what changes for them, and how you know, in the same message as the missing fields list.

    Requirements: An agent environment that can read an org profile and write markdown, with the bundled scripts runnable for budget reconciliation and placeholder listing. No funder portal access needed.

    Example prompt: Draft a grant proposal for our nonprofit from this mission, program description, and budget, and mark every fact I have not supplied for review.

    What is in the package: SKILL.md, LICENSE, references including section templates, examples, and scripts for budget checking and placeholder listing.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 23 days ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed23 days ago

    What's inside

    Frequently Asked Questions

    Turn a nonprofit's mission, program details, and budget into a complete grant proposal draft in which every unverified fact is marked for review.

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use Grant Proposal Drafter Pro on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.

    New in Writing & Content