← Back to Skills Marketplace
jirboy

Fund Proposal Assistant

by JIRBOY · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
66
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install fund-proposal-assistant
Description
基金申请写作专家 - 协助撰写国自然等科研项目申请书,提供模板、润色和形式审查
README (SKILL.md)

基金申请写作专家 Skill

🎯 一句话定义

为国自然(面上/青年/重点研发)等科研项目申请书提供全流程写作支持,从选题到提交。


📥 如何调用 (How to use me)

触发语句:

  • "激活基金技能"
  • "帮我写立项依据"
  • "检查基金申请书"
  • "生成技术路线图"
  • "润色创新点"

需要提供的信息:

  1. 必需: 申请类型(面上/青年/重点研发)、当前任务(写作/检查/润色)
  2. 可选: 学科领域、已有材料、DDL时间

🔄 执行逻辑 (What I do)

Step 1: 任务识别

判断用户需求:

  • 📝 写作 → 进入 Step 2A
  • 🔍 检查 → 进入 Step 2B
  • 润色 → 进入 Step 2C
  • 📊 图表 → 进入 Step 2D

Step 2A: 写作流程

  1. 确认章节(立项依据/研究内容/方案/创新点/基础)
  2. 调用对应模板
  3. 根据用户提供的信息填充
  4. 生成初稿 + 写作建议

Step 2B: 形式检查流程

  1. 执行检查清单
  2. 标记问题(P0/P1/P2)
  3. 生成修改建议
  4. 输出检查报告

Step 2C: 润色流程

  1. 分析原文问题
  2. 语言润色(学术表达)
  3. 逻辑优化
  4. 提供修改对比

Step 2D: 图表流程

  1. 理解技术逻辑
  2. 设计图表结构
  3. 生成Python/MATLAB代码或描述
  4. 提供美化建议

📋 检查清单

P0 - 必须修改(影响提交)

  • 申请代码正确(E0505/E050501等)
  • 研究期限合理(2026.01-2029.12)
  • 申请金额符合指南
  • 人员信息完整准确
  • 无超项问题
  • 摘要400字以内

P1 - 重要修改(影响评审)

  • 立项依据逻辑清晰
  • 科学问题明确(2-3个)
  • 研究内容具体可行(3-4条)
  • 创新点表述准确(2-3点)
  • 技术路线图清晰
  • 参考文献格式统一

P2 - 优化建议(提升质量)

  • 语言表达精炼
  • 图表质量提升
  • 错别字检查
  • 格式细节统一

📝 写作模板库

模板1: 立项依据(5段式结构)

第1段:工程背景

[重大工程背景]是我国[行业]发展的重要方向,
[具体结构/构件]的[安全性/可靠性/性能]直接关系到[工程安全]。
然而,[当前存在的问题]...(50-80字)

第2-3段:研究现状

针对上述问题,国内外学者开展了大量研究。
在[方面A],[学者A]提出了...,但仍存在[局限性1]。
在[方面B],...(分层评述,每段一个方面)

第4段:Gaps总结

综上所述,现有研究在以下方面仍需深入:
(1) [Gap 1:理论层面]...
(2) [Gap 2:方法层面]...
(3) [Gap 3:应用层面]...(2-3点即可)

第5段:切入点+意义

针对上述关键科学问题,本项目拟从[角度]出发,
采用[方法],开展[研究内容],以期[预期成果]。
本项目的开展将在理论上[贡献1],在方法上[贡献2],
为[工程应用]提供支撑。

模板2: 研究内容(3-4条)

结构:

针对[科学问题1],开展[研究内容1],预期获得[成果1]。

针对[科学问题2],开展[研究内容2],预期获得[成果2]。

针对[科学问题3],开展[研究内容3],预期获得[成果3]。

各研究内容间的逻辑关系:[承上启下的说明]

模板3: 创新点表述

公式:

"与现有[方法/理论]相比,本项目的创新在于:"

理论创新:

"将[因素X]纳入[理论框架],建立[新模型],揭示[机理]..."

方法创新:

"提出[方法名称],通过[技术手段],解决[关键问题]..."

应用创新:

"将[方法]应用于[新场景],验证其[性能],为[工程问题]提供新思路..."

模板4: 摘要(400字以内)

结构:

[研究背景](1句)
[科学问题](1句)
[研究内容](2-3句,分点)
[关键方法](1句)
[预期成果](1句)
[科学意义](1句)

📊 技术路线图生成

流程图结构

┌─────────────────────────────────────────────────────────┐
│                    总体研究思路                          │
├─────────────────────────────────────────────────────────┤
│  科学问题1 ──→ 研究内容1 ──→ 方法1 ──→ 预期成果1        │
│       ↓           ↓            ↓            ↓          │
│  科学问题2 ──→ 研究内容2 ──→ 方法2 ──→ 预期成果2        │
│       ↓           ↓            ↓            ↓          │
│  科学问题3 ──→ 研究内容3 ──→ 方法3 ──→ 预期成果3        │
└─────────────────────────────────────────────────────────┘

实现方式:

  • Python: matplotlib/networkx
  • 在线工具: ProcessOn, draw.io
  • PowerPoint/Visio

🔧 自动化工具

每日检查脚本

脚本位置: fund-proposal-assistant/daily_check.py

功能:

  • 自动生成带日期的Word文档版本
  • 生成每日检查清单(根据倒计时动态调整重点)
  • 记录修改历史

使用方法:

cd fund-proposal-assistant
python daily_check.py

输出:

  • 检查报告:fund-check-reports/check_report_YYYYMMDD.md
  • Word版本:fund-daily-versions/NSFC_面上项目_2026_纪金豹_YYYYMMDD.docx

检查重点随倒计时变化:

倒计时 检查重点
D-6 整体框架、格式统一
D-5 立项依据深化
D-4 研究内容打磨
D-3 创新点与基础
D-2 格式与参考文献
D-1 最终冲刺
D-Day 提交确认

💡 使用示例

示例1: 协助立项依据

用户: "帮我写振动台控制相关的立项依据"

我:
**建议框架:**

第1段(背景):
重大工程结构的抗震安全性是土木工程核心关切。振动台试验
是评估地震响应的最直接手段,但受台面尺寸限制难以足尺试验。
振动台子结构试验通过物理-数值混合模拟,为解决这一难题
提供了新思路,但边界条件精确模拟等关键问题仍待研究。

第2段(现状):
现有研究在[时滞补偿]方面... 在[多自由度协调]方面...

第3段(Gaps):
(1) 现有方法未考虑[非线性耦合效应]
(2) 缺乏[自适应控制策略]...

[继续提供第4-5段...]

示例2: 形式检查

用户: "检查我的基金申请书"

我:
## 基金申请书形式检查报告

### 🔴 P0级问题(必须修改)
| 位置 | 问题 | 建议 |
|------|------|------|
| 摘要 | 425字,超25字 | 精简至400字以内 |
| 研究期限 | 写成了2025-2028 | 修改为2026.01-2029.12 |

### 🟡 P1级问题(重要修改)
| 位置 | 问题 | 建议 |
|------|------|------|
| 立项依据 | 科学问题不明确 | 单独成段明确列出2-3个科学问题 |
| 创新点 | 表述空泛 | 具体说明"新"在哪里 |

[继续输出...]

技能版本: v2.1
更新日期: 2026-03-04
更新说明: 合并 fund-daily-check,添加每日检查脚本,完善功能模块

Usage Guidance
This skill appears to do what it says (templates, checks, and an automation script), but exercise caution before running the included daily_check.py: it contains hardcoded Windows paths (Y:\ and D:\...), a fixed deadline in early March 2026, and personalized names — likely tailored to a specific user. If you plan to use the script, (1) review the code line-by-line, (2) edit OUTPUT_DIR/FUND_DOC_DIR/REPORT_DIR to safe locations you control, (3) back up any documents it may copy/overwrite, (4) run it in a sandbox or VM (especially if your OS is not Windows), and (5) consider removing or replacing personal identifiers. If you will allow an agent to run skills autonomously, deny execution until you have verified the script's paths and behavior. These oddities are explainable by sloppy packaging/personalization but should be fixed before widespread use.
Capability Analysis
Type: OpenClaw Skill Name: fund-proposal-assistant Version: 1.0.0 The skill bundle is a legitimate assistant for academic grant proposal writing and review. The included Python script (daily_check.py) performs local file management tasks such as versioning Word documents and generating Markdown reports using standard libraries (os, shutil). No network activity, data exfiltration, or malicious execution patterns were detected, and the instructions in SKILL.md are strictly aligned with the stated purpose.
Capability Assessment
Purpose & Capability
The SKILL.md describes writing, checking, templates and a 'daily_check.py' script — these capabilities align with a fund-proposal assistant. However, the included script is tightly tailored to a specific user's environment (hardcoded Windows paths, username references such as '豹老大', 'SuperMike', '纪金豹'), which is disproportionate for a generic public skill.
Instruction Scope
The runtime instructions and templates stay on-topic, but the shipped Python script will read and copy local .docx files using absolute paths (FUND_DOC_DIR = 'Y:\', OUTPUT_DIR and REPORT_DIR on D:\). The SKILL.md does not declare these paths or ask for confirmation, and the script may attempt file I/O on the host if executed by an agent. No network/exfiltration code is present, but the file-system access is unexpected for an instruction-only skill.
Install Mechanism
No install spec; the skill is instruction-only with a code file. This is lower risk than remote downloads or package installs.
Credentials
No environment variables, credentials, or external endpoints are requested. Good. But the script implicitly assumes Windows drive letters and particular local folders, which may expose or overwrite local documents if run without modification.
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform privileges or modify other skills. Autonomous model invocation is allowed by default but is not combined with other high-risk flags.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install fund-proposal-assistant
  3. After installation, invoke the skill by name or use /fund-proposal-assistant
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of "基金申请写作专家", providing end-to-end support for major research fund proposals (e.g., NSFC surface/young/key projects). - Includes full workflow: topic selection, writing support, form check, language polishing, and technical diagram generation. - Offers structured writing templates for common sections (立项依据, 研究内容, 创新点, 摘要). - Built-in checklist for critical form requirements (分为P0/P1/P2级) with actionable suggestions. - Automated tools: integrated daily check script for versioning and tracking proposal progress tailored to countdown days. - Easy activation via trigger phrases (e.g., “帮我写立项依据”, “检查基金申请书”).
Metadata
Slug fund-proposal-assistant
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Fund Proposal Assistant?

基金申请写作专家 - 协助撰写国自然等科研项目申请书,提供模板、润色和形式审查. It is an AI Agent Skill for Claude Code / OpenClaw, with 66 downloads so far.

How do I install Fund Proposal Assistant?

Run "/install fund-proposal-assistant" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Fund Proposal Assistant free?

Yes, Fund Proposal Assistant is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Fund Proposal Assistant support?

Fund Proposal Assistant is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Fund Proposal Assistant?

It is built and maintained by JIRBOY (@jirboy); the current version is v1.0.0.

💬 Comments