Grant Proposal

wanshuiyin/auto-claude-code-research-in-sleep

Takes research ideas and turns them into structured grant proposals for major funding agencies. Handles KAKENHI, NSF, NSFC, ERC, DFG, SNSF, ARC, NWO with correct section orders and review criteria for each. Chains together literature survey, novelty checking, and multi-round GPT-based review before output. Sits parallel to the experiment pipeline: you can either go straight to implementation or write the grant first and implement after funding. The style-ref option lets you mirror structural patterns from a successful past proposal without copying prose. Output defaults to markdown but supports LaTeX templates. Waits for confirmation at each checkpoint because grant writing needs PI judgment at every stage.

skills.sh installs: 590
GitHub stars: 18.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add wanshuiyin/auto-claude-code-research-in-sleep --skill grant-proposal --agent claude-code

Installs into .claude/skills of the current project.

Files

Grant Proposal: From Research Ideas to Fundable Application

Before each reviewer slot, follow Selectable Reviewers: resolve invocation → .aris/reviewer.json → Claude Code default (Codex MCP) with reviewer_route.py through the canonical helper resolver, preserving this slot's tier, fresh contexts, source/image inputs and deterministic gates. Codex examples/pins below apply only to backend=codex; other routes use their own first-call/reply contract. Save the route and actual returned identity; unavailable selections are REVIEW_UNAVAILABLE. Classify acceptance from actual families/completion/scope. Forward invocation reviewer/model/effort overrides to reviewer-bearing children. Generation workers are unchanged.

Draft a grant proposal based on: $ARGUMENTS