k2f-grant-proposal
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseK2F Grant Proposal — AI-Native Aesthetic Design
K2F 基金申请书——AI 原生美学设计
Purpose
目的
Teach agents to blueprint fundable grant narratives before layout: a falsifiable hypothesis, explicit gaps, independent aims, reviewer-scannable hierarchy, and honest feasibility—without inventing data or drowning reviewers in prose.
教会 Agent 在排版前规划具备获资助可行性的基金申请叙事:可证伪的假设、明确的空白、相互独立的目标、便于评审快速扫描的层级结构,以及诚实的可行性评估——既不虚构数据,也不让评审淹没在冗长文字中。
Built on K2F
基于 K2F 构建
This skill produces grant packages as documents. Follow the k2f skill for authoring: unpack or init a workspace, edit the semantic tree, run pack/verify, then export. K2F keeps agents on meaning (section roles, aims, evidence)—not pixel coordinates—while the engine compiles layout, typography, and theme into consistent output across PDF, DOCX, and other formats.
.K2FBefore you build, install the core skill: .
npx skills add suzheng/k2f --skill k2f此 skill 会将资助申请材料包生成为 文档。编写时请遵循 k2f skill:解包(unpack)或初始化(init)工作区,编辑语义树,运行 pack/verify,然后导出。K2F 让 Agent 专注于含义(章节角色、目标、证据),而非像素坐标;同时由引擎编译布局、字体排印和主题,在 PDF、DOCX 及其他格式中生成一致的输出。
.K2F构建前,请安装核心 skill:。
npx skills add suzheng/k2f --skill k2fWhen to Use
适用场景
- Drafting or restructuring NIH, NSF, ERC, or foundation proposals from notes or prior work.
- Rebuilding a weak Specific Aims page before the full research strategy.
- Aligning content depth and visual hierarchy to mechanism limits and review rubrics.
- 根据笔记或前期工作起草或重构 NIH、NSF、ERC 或基金会申请书。
- 在编写完整研究策略前,重建薄弱的 Specific Aims 页面。
- 根据资助机制限制和评审量表,调整内容深度与视觉层级。
Workflow
工作流
Step 1. Generate the content_and_design.md
第 1 步:生成 content_and_design.md
Single blueprint for semantic content and aesthetic intent. Structure it with labeled blocks the k2f skill can map to pages later.
Sub-steps
-
Mechanism lock — Agency, solicitation ID, mechanism, page limits, required sections, scoring criteria (NIH: Significance, Innovation, Approach, Investigators, Environment; NSF: Intellectual Merit, Broader Impacts). Drop optional material that exceeds limits.
-
Four-question audit — Answer in prose using user-supplied evidence only:
- Central hypothesis: testable, falsifiable (not “we will study X”).
- Why now: gap, urgency, new tools or data.
- Innovation: conceptual, methodological, application, or novel outcomes—each with specifics.
- Feasibility: team, timeline, resources, aim independence, pitfalls with Plan B.
-
Specific Aims architecture — One page, ~400–550 words. Narrative arc: hook → gap → long-term goal → hypothesis → 2–3 verb-led aims (testable, largely independent) → impact close. Per aim: 2–3 sentences, expected outcome, no fatal dependency on prior aim success.
-
Strategy outline — Significance (problem, state of field, gap, cost of not knowing, if-successful impact). Innovation as scannable bullets (“This project is innovative because…”). Approach per aim: rationale → strategy/controls/stats → expected outcomes → pitfalls/alternatives → milestones. Assign word budgets from page limits (~450 words per full strategy page); note where figures replace paragraphs (preliminary data, workflow, timeline).
-
Design intent — Document tone, hierarchy, density, palette for the engine:
- Tone: formal, evidence-led; a non-expert primary reviewer grasps significance on page 1.
- Hierarchy: Aims page = strongest contrast and largest headings; strategy H1s conclusion-driven (“Gap in X limits Y”) not generic labels.
- Density: bullet-led Innovation; Approach subheads per aim; no paragraphs over ~6 lines.
- Palette: calm academic (navy/slate body, one accent for aim numbers and key metrics); WCAG AA; no decorative clutter on the Aims page.
Rules & constraints
- Golden thread: problem → hypothesis → aims → approach → impact; cut interesting tangents.
- Aims independence: partial success must remain fundable; merge aims that share one point of failure.
- Honesty gate: mark missing preliminary data; never fabricate citations, pilot results, or budget figures.
- Agency fit: mirror funder vocabulary and review dimensions in outline order.
Common failure modes
- Fishing expedition without falsifiable hypothesis → rewrite as if/then with measurable endpoints.
- Methods-before-problem Aims page → reorder hook → gap → hypothesis first.
- “Innovative approach” without novelty → one bullet per concrete first/novel/application.
- Scope creep → fewer aims or narrower mechanism; align word budgets.
- Aim 2 impossible if Aim 1 fails → redesign independence or alternatives.
- Dense Aims essay → enforce aim cards, bullets, and word cap in the design doc.
Quality checklist
- Hypothesis on Aims page matches Approach.
- Each aim has pitfalls + alternatives; no single point of failure across aims.
- Significance states gap and cost of not knowing.
- Innovation bullets name concrete novelty, not superlatives.
- Word budgets sum under mechanism limits.
- All evidence traceable to user inputs.
这是用于表达语义内容和美学意图的统一蓝图。使用带标签的区块进行组织,以便 k2f skill 之后将其映射到具体页面。
子步骤
-
机制锁定 — 资助机构、征集编号、机制、页数限制、必需章节、评分标准(NIH:Significance、Innovation、Approach、Investigators、Environment;NSF:Intellectual Merit、Broader Impacts)。删除超出限制的可选内容。
-
四问审计 — 仅依据用户提供的证据,以叙述性文字回答:
- 核心假设:可检验且可证伪(不能只是“我们将研究 X”)。
- 为何是现在:研究空白、紧迫性、新工具或新数据。
- 创新性:概念、方法、应用或新颖成果——每项都需具体说明。
- 可行性:团队、时间线、资源、目标独立性、潜在问题及 Plan B。
-
Specific Aims 架构 — 一页,约 400–550 词。叙事弧线:引入点 → 空白 → 长期目标 → 假设 → 2–3 个以行动动词引导的目标(可检验,且在很大程度上相互独立)→ 影响力收尾。每个目标包含 2–3 句话和预期结果,且不能对前序目标的成功产生致命依赖。
-
研究策略大纲 — Significance(意义):问题、领域现状、研究空白、不知道答案的代价、成功后的影响。Innovation(创新性)采用便于扫描的项目符号(“本项目具有创新性,因为……”)。每个目标的 Approach(方法):依据 → 策略/对照/统计 → 预期结果 → 潜在问题/替代方案 → 里程碑。根据页数限制分配字数预算(每个完整研究策略页约 450 词);注明哪些位置用图代替段落(初步数据、工作流、时间线)。
-
设计意图 — 为引擎记录语气、层级、信息密度和配色:
- 语气:正式、以证据为导向;非专业的主要评审也能在第 1 页把握 Significance。
- 层级:Aims 页面采用最强对比和最大标题;研究策略的 H1 以结论为导向(“X 中的空白限制了 Y”),而不是泛化标签。
- 密度:Innovation 以项目符号为主;Approach 按目标设置小标题;段落不超过约 6 行。
- 配色:沉静的学术风(正文用海军蓝/石板灰,目标编号和关键指标使用一种强调色);符合 WCAG AA;Aims 页面不添加装饰性冗余。
规则与约束
- 主线:问题 → 假设 → 目标 → 方法 → 影响;删减有趣但偏离主题的内容。
- 目标独立性:部分成功仍须具备获资助的可能性;合并共享同一故障点的目标。
- 诚信门槛:标记缺失的初步数据;绝不虚构引用、试点结果或预算数字。
- 资助机构契合度:按照大纲顺序使用资助方的术语和评审维度。
常见失败模式
- 没有可证伪假设的“大撒网式”探索(fishing expedition)→ 改写为 if/then 形式,并设置可衡量的终点。
- 方法先于问题的 Aims 页面 → 重新排序为引入点 → 空白 → 假设优先。
- 只有“Innovative approach”却没有新颖性 → 每项具体的首创、新颖内容或应用设置一个项目符号。
- 范围蔓延 → 减少目标或收窄机制;使字数预算保持一致。
- Aim 1 失败时 Aim 2 不可能实现 → 重新设计独立性或替代方案。
- 密集的 Aims 长文 → 在设计文档中强制使用目标卡片、项目符号和字数上限。
质量检查清单
- Aims 页面中的假设与 Approach 一致。
- 每个目标都有潜在问题和替代方案;所有目标之间不存在单一故障点。
- Significance 说明研究空白及不知道答案的代价。
- Innovation 项目符号指出具体新颖点,而非最高级表述。
- 字数预算之和不超过资助机制限制。
- 所有证据均可追溯至用户输入。
Step 2. Use the content_and_design.md and k2f skill to generate a K2F file and export to an appropriate file format.
第 2 步:使用 content_and_design.md 和 k2f skill 生成 K2F 文件并导出为适当格式
Follow k2f to instantiate pages from the blueprint, apply roles from design intent, verify, and export the agency-ready deliverable.
按照 k2f 的流程,从蓝图实例化页面,应用设计意图中的角色,进行验证,并导出可直接提交给资助机构的交付物。