Grant Writing Master
Turn your research plan into a clear, evidence-grounded grant application.
Draft, revise, translate and review grant text against the selected funder, year, evidence and form. Includes dated KAKENHI profiles and programme-specific AMED guidance, with tools for profile selection and field counting. Preserves the facts and uncertainty in your research while making the argument easier to follow.
$5.00 one-off
Preview — package delivery is not available yet
- Version
- 7.0.0-public.2
- Curated
- 2026-09-25
- Package
- 161 KiB unpacked
- License
- MIT
An agent that can read local Markdown files; Python 3.10+ for the selector and counter.
License and attribution clarified on 25 September 2026; the MIT grants are preserved. Runtime and example bytes are unchanged. Scientific demonstrations and native-host checks retain their 24 September scope. Individually prepared under the owner's publication authorization. Demonstrations are AI-assisted and self-reviewed; no independent human review of the final generated artifacts is claimed. Updates require an explicit release decision.
The standalone package supports writing from supplied evidence. New evidence retrieval and native Word/PDF assembly require separate capabilities. Native document fidelity and portal submission are not certified.
Evidence
Research brief in → revised grant section out
demonstrationA synthetic brief supplies an association, a null pilot comparison and a proposed experiment. The revision makes the question and test explicit, preserves p = 0.20, and removes invented causal certainty and approvals. The brief, draft, output and change notes are all inspectable.
Prepared and self-reviewed with the public skill. This is one prose demonstration; it is not a funded application or a blinded quality benchmark.
Read the example on this page
Before · synthetic draft
Our three cultures prove that marker A controls response B. Treatment C is equivalent to control because p = 0.20. We will validate this mechanism by perturbing marker A, and our approved facilities guarantee success.
After · revised paragraph
Whether marker A contributes causally to response B remains unresolved. In three independent cell cultures, marker A was associated with response B; these observations do not establish causation. A separate pilot comparison of treatment C with control did not detect a difference (p = 0.20), which does not establish equivalence. We will perturb marker A and measure response B against a matched control. Replication, sample-size justification, facility access and applicable ethics requirements remain to be established before the proposed work proceeds.
Select the right funder, year and form
measuredEight routing cases passed, including explicit selection, missing context, conflicting form, future-year lookup and incomplete AMED context. An AMED programme frame is not a verified application template. Selecting a profile does not certify its rules or the completed application.
Count the field using the right unit
measuredThe same field has different character, word and byte counts. These local measurements preserve the input, including line endings; the actual form's counting rule decides which limit applies.
Keep uncertainty visible across languages
demonstrationThe English and Japanese versions preserve the three independent cultures, association rather than causation, a null result rather than equivalence, and a future perturbation rather than a completed experiment. Unresolved sample-size justification, access and ethics remain visible. This is an AI self-review; independent bilingual review is not claimed.
What was checked for this edition
measuredSix Python test methods passed, covering eight routing cases plus catalog and counting checks. Three CLI limit-boundary checks and Codex discovery/selector execution also passed. These checks are separate from scientific quality, native document fidelity and funding outcomes.
What's in the package
34 files · 161 KiB unpacked · standard Agent Skills layout
Requirements
- An agent that can read local Markdown files; Python 3.10+ for the selector and counter.
- The applicable official call, year and exact form. Stored profiles were sourced on 7 September 2026 and do not certify current eligibility or rules.
- Supplied research facts for prose work. New literature retrieval can use the separate Biomedical Literature Evidence skill or equivalent tools; a grant-specific acceptance adapter is not bundled.
- Separate document/PDF tools and the actual style donor for native forms; spreadsheet tools for workbooks. These are optional for the standalone prose and counting functions.
Install — by agent
Package delivery is not available yet. These instructions describe installation once you have the ZIP. The compatibility table records the actual test date, environment and scope for each agent.
Install for your agent
Installation overview. Follow the steps for your agent and check the compatibility table for the tested scope.
- 1.
Obtain the versioned ZIP
Preview listing: checkout and package delivery are not enabled.
Preview — package delivery is not available yet
The steps below describe installation once you have the ZIP. Checkout and downloads are not enabled.
- 2.
Extract into a new project skill directory
Linux shell. The archive contains SKILL.md at its root. Refuse an existing destination to protect local edits.
bashtest ! -e .agents/skills/grant-write-master && mkdir -p .agents/skills/grant-write-master && unzip grant-write-master-7.0.0-public.2.zip -d .agents/skills/grant-write-master - 3.
Start a new session and check the installed files
verified on Codex CLI 0.154.0, 2026-09-24. Linux only. Read the public version and scope; ran the grant selector / biomedical CLI help. This is a discovery and CLI smoke test, not end-to-end scientific validation.
bashcodex exec 'Read the installed $grant-write-master skill. State its version and limits, then run: PYTHONDONTWRITEBYTECODE=1 python3 .agents/skills/grant-write-master/scripts/profile_select.py --funder JSPS --scheme B --year 2027 --language en'
Agent compatibility
| Agent | Status | Method | Notes |
|---|---|---|---|
| Codex CLI 0.154.0 | Verified2026-09-24 | Project-local .agents/skills discovery from extracted ZIP | Linux only. Read the public version and scope; ran the grant selector / biomedical CLI help. This is a discovery and CLI smoke test, not end-to-end scientific validation. |
| Claude Code Not tested | Untested | Standard SKILL.md layout | No native invocation of this public edition was tested. |
| Antigravity Not tested | Untested | Explicit file-reading pointer | No native invocation of this public edition was tested. |
| Other agents Not tested | Untested | Explicit file-reading pointer | Requires file access and an appropriate Python runtime. Biomedical retrieval requires POSIX file locking; native Windows is unsupported. |
License and reuse
MIT permits commercial use, modification, redistribution and resale with notices retained. Official forms, source publications and separately installed tools retain their own terms.
The displayed price does not change the license. Terms apply to the identified edition; earlier grants and third-party rights are preserved.
Provenance & integrity
Prepared from the owner-supplied Codex Skills Bundle dated 11 September 2026. Original bundles are preserved; private calibration metadata and Python caches were excluded. This edition was prepared and checked with AI assistance under the owner's publication authorization.
SHA-256 of grant-write-master-7.0.0-public.2.zip — verify your download against this hash:
cba4848c9d1c5ee00e31bac308a8da45253e54e4b43fd7d081b4fe12275fd5bd