/grant-proposal — Research Grant Proposal Scaffolder

Compose a funder-shaped grant proposal draft from primitives you already have: an /interview-me research spec supplies the science, /data-management-plan supplies the DMP, /capture-environment supplies the facilities/computational statement, and /lit-review supplies the prior-work framing. This skill structures and stitches — it does not submit anywhere, and it does not invent identification strategy where a spec is absent.

Core principle: A proposal is a coherence artifact. Aims, methods, budget, timeline, and broader impacts must agree with each other and with the underlying research spec. The skill's main value-add over a blank template is the Phase 3 coherence pass (aims ↔ methods ↔ budget ↔ timeline).

When to use

• Drafting an NSF / NIH / ERC / foundation proposal from an existing research idea.
• Turning an /interview-me spec (or a /preregister PAP) into a fundable narrative.
• Assembling the boilerplate-but-required pieces (DMP, facilities, data-sharing) so the human writes only the science.
• During resubmission, re-scaffolding aims after a reviewer "revise and resubmit" round.

When NOT to use

• You need the science itself invented — run /interview-me first; this skill refuses to fabricate an identification strategy.
• The sponsor is a clinical-trial funder requiring its own protocol template (out of scope; use the sponsor's native forms).
• You want a finished, submittable PDF — this writes Markdown sections + a checklist; final assembly into the sponsor's format is yours.