Grant Proposal

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:

/research-lit → /novelty-check → [structure design] → [draft] → /research-review → [revise] → GRANT_PROPOSAL.md
  (survey)      (verify gap)     (aims + matrix)     (prose)    (panel review)     (fix)      (done!)

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)

                    ┌→ /experiment-bridge → /auto-review-loop → /paper-writing  (publish track)
/idea-discovery ────┤
                    └→ /grant-proposal → [get funded] → /experiment-bridge → ...  (funding track)

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-5.5 — Model used via Codex MCP for proposal review. Must be an OpenAI model (e.g., gpt-5.5, o3, gpt-4o).
• OUTPUT_FORMAT = markdown — Output format. Supported: markdown, latex. LaTeX uses grant-specific templates when available.
• MAXREVIEWROUNDS = 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: , 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: appears in $ARGUMENTS, run the helper FIRST, before drafting:

# Resolve $STYLE_HELPER via the canonical strict-safe chain (see
# shared-references/integration-contract.md §2). Policy A — gate:
# unresolved helper means --style-ref cannot be satisfied, so abort.
cd "$(git rev-parse --show-toplevel 2>/dev/null || pwd)" || exit 1
if [ -z "${ARIS_REPO:-}" ] && [ -f .aris/installed-skills.txt ]; then
    ARIS_REPO=$(awk -F'\t' '$1=="repo_root"{print $2; exit}' .aris/installed-skills.txt 2>/dev/null) || true
fi
STYLE_HELPER=".aris/tools/extract_paper_style.py"
[ -f "$STYLE_HELPER" ] || STYLE_HELPER="tools/extract_paper_style.py"
[ -f "$STYLE_HELPER" ] || { [ -n "${ARIS_REPO:-}" ] && STYLE_HELPER="$ARIS_REPO/tools/extract_paper_style.py"; }
[ -f "$STYLE_HELPER" ] || {
  echo "ERROR: extract_paper_style.py not resolved at .aris/tools/, tools/, or \$ARIS_REPO/tools/." >&2
  echo "       Fix: rerun bash tools/install_aris.sh, export ARIS_REPO, or copy the helper to tools/." >&2
  echo "       --style-ref cannot be satisfied; aborting." >&2
  exit 1
}
STYLE_STATUS=0
CACHE=$(python3 "$STYLE_HELPER" --source "") || STYLE_STATUS=$?
case "$STYLE_STATUS" in
  0) ;;                                       # use $CACHE/style_profile.md as structural guidance
  2) echo "warning: style-ref skipped (missing optional dep)" >&2 ;;
  3) echo "error: --style-ref source failed; aborting proposal" >&2 ; exit 1 ;;
  *) echo "error: helper failed unexpectedly; aborting proposal" >&2 ; exit 1 ;;
esac

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-5.5 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:

/grant-proposal "topic — GENERIC, sections: Background|Methods|Impact, language: English"

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:

{
  "phase": 2,
  "grant_type": "KAKENHI",
  "grant_subtype": "Start-up",
  "language": "Japanese",
  "codex_thread_id": "019cfcf4-...",
  "gap_statement": "...",
  "aims_count": 3,
  "status": "in_progress",
  "timestamp": "2026-03-18T15:00:00"
}

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:

/research-lit "$ARGUMENTS"

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:

`` /novelty-check "[proposed gap statement]" ``

• Build the gap statement — the single most important sentence in the proposal:

`` "Despite progress in [X], [specific gap] remains unaddressed because [reason]. This proposal addresses this by [approach], which will [expected impact]." ``

🚦 Checkpoint: Present the landscape summary and gap statement to the user:

📚 Literature & landscape analysis complete:
- [key findings from literature]
- [competing funded projects found]
- Gap statement: "[the gap statement]"

Does this accurately capture the positioning? Should I adjust before designing the proposal structure?

⛔ 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 maps to specific outputs (papers, datasets, tools, benchmarks)
• Feasible within budget and timeline

2.2 Build Claims-Aims-Evidence Matrix

| Aim | Key Claim | Preliminary Evidence | Proposed Validation | Risk Level | Deliverable |
|-----|-----------|---------------------|--------------------|-----------:|-------------|
| Aim 1 | [claim] | [pilot data, prior work] | [experiments] | LOW | [paper, dataset] |
| Aim 2 | [claim] | [theoretical basis] | [experiments] | MEDIUM | [paper, tool] |

2.3 Design the Narrative Arc

Grant proposals follow a fundamentally different arc from papers:

Problem → Why Now → What We Propose → Why It Will Work → What We Will Deliver
         (not: Problem → Method → Results → Implications)

• Problem: What gap exists and why it matters (scientific + societal)
• Why Now: What recent developments make this the right time (new data, new methods, new need)
• What We Propose:

…

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: wanshuiyin
• Source: wanshuiyin/Auto-claude-code-research-in-sleep
• License: MIT

Install and usage instructions live in the source repository linked above.