Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNSF (Switzerland), ARC (Australia), NWO (Netherlands), and generic formats. Use when user says "write grant", "grant propos

Grant Proposal: From Research Ideas to Fundable Application Draft a grant proposal based on: $ARGUMENTS Overview This skill turns validated research ideas into a structured, reviewer ready grant proposal. It chains sub skills into a grant specific pipeline: This is a parallel branch, not part of the linear Workflow 1→1.5→2→3 pipeline. After /idea discovery produces validated ideas, the user can either: Go to /experiment bridge → /auto review loop → /paper writing (implement & publish) Go to /grant proposal (write funding application first, then implement after funding) Grant proposals argue for future work (feasibility + potential), not completed work (results + claims). This skill handles the unique requirements of grant writing: narrative arc design, reviewer facing structure, budget justification, timeline planning, and agency specific formatting. Constants GRANT TYPE = KAKENHI — Default grant type. Supported: KAKENHI , NSF , NSFC , ERC , DFG , SNSF , ARC , NWO , GENERIC . Override via argument (e.g., /grant proposal "topic — NSF" ). GRANT SUBTYPE = auto — Sub type within the grant agency. Examples: KAKENHI Start up / Wakate / Kiban B ; NSFC Youth / Excellent Youth / Distinguished / Overseas / Key ; NSF CAREER / CRII / Standard . Auto detected from argument or defaults to the most common sub type. REVIEWER MODEL = gpt 6 astra — Model used via Codex MCP for proposal review. Must be an OpenAI model (e.g., gpt 6 astra , o3 , gpt 4o ). OUTPUT FORMAT = markdown — Output format. Supported: markdown , latex . LaTeX uses grant specific templates when available. MAX REVIEW ROUNDS = 2 — Maximum external review revise cycles before finalizing. OUTPUT DIR = grant proposal/ — Directory for generated proposal files. LANGUAGE = auto — Output language. Auto detected from grant type: KAKENHI→Japanese, NSF→English, NSFC→Chinese, ERC→English, DFG→English (or German), SNSF→English, ARC→English, NWO→English. Override explicitly if needed. AUTO PROCEED = false — At each checkpoint, always wait for explicit user confirmation before proceeding. Grant proposals require PI specific judgment at every stage. Set true only if user explicitly requests fully autonomous mode. 💡 These are defaults. Override by telling the skill, e.g., /grant proposal "topic — NSF CAREER, latex output" or /grant proposal "topic — NSFC Youth, language: English" . Optional: Style reference ( — style ref: <source , opt in) Lets the PI steer the proposal's structural layout (section order tendency, paragraph length, figure density, citation style) toward a successful past proposal or paper they'd like to mirror. Default OFF — when the user does not pass — style ref , do nothing differently from before. Only when — style ref: <source appears in $ARGUMENTS , run the helper FIRST, before drafting: Sources accepted: local TeX dir / file, local PDF, arXiv id, http(s) URL. Overleaf URLs/IDs are rejected — clone the project locally first and pass the local path. Strict rules (full contract in tools/extract paper style.py docstring): Use style profile.md to align paragraph length tendency, figure budget, and citation density. Grant type mandated section order (KAKENHI 研究目的 → 研究計画・方法 → 準備状況, NSF Intellectual Merit → Broader Impacts, etc.) always takes precedence — the agency template wins, the style ref only refines secondary structure. Never copy proposal prose, claims, vision statements, or budget items from anything reachable through the cache. The reference might be someone else's funded proposal; reproducing language risks plagiarism. Never pass — style ref (or the cache contents) to the GPT 6 Astra reviewer sub agent when it scores the draft — the proposal must be judged on its own merits. Grant Type Specifications KAKENHI (Japan — JSPS) Field Detail Sections 研究目的 (Research Objective), 研究計画・方法 (Plan & Methods), 準備状況 (Preparation Status), 人権の保護 (Ethics, if applicable) Sub types 基盤研究 A/B/C (Kiban), 若手研究 (Wakate), 研究活動スタート支援 (Start up), 国際共同研究 (International), 学術変革領域 (Transformative), 挑戦的研究 (Challenging), DC1/DC2 (doctoral) Language Japanese (English technical terms acceptable) Review criteria 学術的重要性 (academic significance), 独創性 (originality), 研究計画の妥当性 (plan feasibility), 研究遂行能力 (PI capability) Cultural norms Explicit yearly milestones (Year 1 / Year 2), budget justification integrated into plan, emphasize 社会的意義 (societal significance), concrete expected outputs (papers, datasets), reference KAKEN database for related funded projects NSF (US) Field Detail Sections Project Summary (1p), Project Description (15p max), References Cited, Biographical Sketch, Budget Justification, Data Management Plan Sub types Standard Grant, CAREER (early career), CRII (research initiation), RAPID, EAGER Language English Review criteria Intellectual Merit, Broader Impacts Cultural norms Aim based structure (Aim 1/2/3), preliminary data strongly expected, broader impacts must be concrete and specific (not generic "benefit society"), Results from Prior Support section NSFC (China — 国家自然科学基金) Field Detail Sections 立项依据 (Rationale & Significance), 研究内容 (Content), 研究目标 (Objectives), 研究方案 (Plan & Methods), 可行性分析 (Feasibility), 创新性 (Innovation Points), 预期成果 (Expected Outcomes), 研究基础 (PI Foundation & Track Record) Sub types 面上项目 (General Program) — emphasis on scientific problem and research accumulation; 青年基金 (Young Scientists Fund) — age ≤35, emphasis on independence and growth potential; 优秀青年基金/优青 (Excellent Young Scientists) — age ≤38, emphasis on outstanding achievements; 杰出青年基金/杰青 (Distinguished Young Scientists) — age ≤45, emphasis on international leading level; 海外优青 (Overseas Excellent Young Scientists) — emphasis on overseas experience and return contribution plan; 重点项目 (Key Program) — emphasis on systematic in depth research Language Chinese Review criteria 科学意义 (scientific significance), 创新性 (innovation), 可行性 (feasibility), 研究队伍 (team qualification) Cultural norms Heavy emphasis on 国际前沿 (international frontier) positioning, detailed feasibility analysis, explicit citation of applicant's prior publications, 研究基础 section is critical for demonstrating PI capability ERC (EU — European Research Council) Field Detail Sections Extended Synopsis (5p), Scientific Proposal Part B2 (15p) Sub types Starting Grant (2 7 years post PhD), Consolidator Grant (7 12 years), Advanced Grant (established leaders) Language English Review criteria Ground breaking nature, Methodology, PI track record Cultural norms Emphasis on "high risk/high gain", methodology table with WP/deliverables/milestones, Gantt chart expected, strong PI narrative DFG (Germany — Deutsche Forschungsgemeinschaft) Field Detail Sections State of the Art, Objectives, Work Programme, Bibliography, CV Language English or German Review criteria Scientific quality, Originality, Feasibility, PI qualification SNSF (Switzerland — Swiss National Science Foundation) Field Detail Sections Summary, Research Plan, Timetable, Budget Language English Review criteria Scientific relevance, Originality, Feasibility, Track record ARC (Australia — Australian Research Council) Field Detail Sections Project Description, Feasibility, Benefit, Budget Language English Review criteria Research quality, Feasibility, Benefit to Australia NWO (Netherlands — Dutch Research Council) Field Detail Sections Summary, Proposed Research, Knowledge Utilisation Language English Review criteria Scientific quality, Innovative character, Knowledge utilisation GENERIC For any grant not listed above. User provides section names, page limits, and review criteria via argument: State Persistence (Compact Recovery) Grant proposal drafting is a long task that may trigger context compaction. Persist state to grant proposal/GRANT STATE.json after each phase: Write this file at the end of every phase. On invocation, check for this file: If absent or status: "completed" → fresh start If status: "in progress" and within 24h → resume from saved phase (read GRANT PROPOSAL.md and GRANT REVIEW.md to restore context) If older than 24h → fresh start (stale state) On completion, set "status": "completed" . Workflow Phase 0: Input Parsing & Context Gathering Parse $ARGUMENTS to extract: 1. Research direction/idea — may reference existing files or be a freeform description 2. Grant type — detect from keywords (e.g., "科研費"→KAKENHI, "NSF"→NSF, "国自然"→NSFC, "基金"→NSFC) 3. Grant sub type — detect from keywords (e.g., "Start up", "若手", "青年", "CAREER", "优青", "海外优青") 4. Overrides — output format, language, review rounds Then gather context from the project directory: 1. Read idea stage/IDEA REPORT.md if it exists (from /idea discovery ); fall back to ./IDEA REPORT.md if not found 2. Read refine logs/FINAL PROPOSAL.md if it exists (from /research refine ) 3. Read refine logs/EXPERIMENT PLAN.md if it exists (from /experiment plan ) 4. Read review stage/AUTO REVIEW.md if it exists (from /auto review loop — prior review feedback is gold for grants); fall back to ./AUTO REVIEW.md if not found 5. Read NARRATIVE REPORT.md or STORY.md if they exist 6. Read any existing literature notes or survey documents 7. Scan for the user's publication list (e.g., publications.md , cv.md , bio.md , CV.pdf ) 8. Check for grant proposal/GRANT STATE.json (resume from prior interrupted run) If insufficient context exists: No research idea at all → suggest running /idea discovery first No literature survey → will invoke /research lit inline in Phase 1 No publication list → leave PI qualification section with [TODO: Add publications] placeholders Has review stage/AUTO REVIEW.md → extract reviewer feedback and use it to strengthen the feasibility narrative Phase 1: Literature & Landscape Positioning Invoke /research lit to ground the proposal in real literature, then search for competing funded projects: What this does: Reuse existing surveys if /research lit was already run and notes exist Otherwise invoke /research lit for multi source literature search (arXiv, Scholar, Zotero, local PDFs) Search for funded projects in the same area via WebSearch: KAKENHI → KAKEN database (https://kaken.nii.ac.jp/) NSF → NSF Award Search (https://www.nsf.gov/awardsearch/) NSFC → NSFC funded projects Other agencies → general web search Identify competing groups and their recent publications Run /novelty check on the proposed research direction to verify the gap is real: Build the gap statement — the single most important sentence in the proposal: 🚦 Checkpoint: Present the landscape summary and gap statement to the user: ⛔ STOP HERE and wait for user response. Do NOT auto proceed unless AUTO PROCEED=true was explicitly set by the user. Options for the user: Reply "go" or "ok" → proceed to Phase 2 with current positioning Reply with adjustments (e.g., "focus more on X", "the gap should emphasize Y") → refine and re present Reply "stop" → end the skill, save current progress to grant proposal/DRAFT NOTES.md State : Write GRANT STATE.json with phase: 1 and the gap statement. Phase 2: Narrative Structure & Aims Design Design the proposal's logical architecture before writing any prose. 2.1 Define Specific Aims (2 4) Each aim must satisfy: Independently valuable — if one aim fails, others still produce publishable results Logically connected — Aim 1 enables Aim 2, Aim 2 informs Aim 3 Concrete deliverables — each aim

grant-proposal