Academic Press Release Writing

v1.0.0

学术新闻稿撰写专业工具。包含规范的五段式写作结构、全流程工作步骤、常见问题解决方案和效率提升技巧。**当以下情况时使用此 Skill**:(1) 需要撰写学术机构、科研团队的新闻通稿/宣传稿;(2) 需要将学术论文、科研成果转化为面向公众的科普性新闻稿;(3) 用户提到"学术新闻稿"、"科研宣传稿"、"论文新闻稿...

0· 156·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for 438061781/academic-press-release-writing.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Academic Press Release Writing" (438061781/academic-press-release-writing) from ClawHub.
Skill page: https://clawhub.ai/438061781/academic-press-release-writing
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install academic-press-release-writing

ClawHub CLI

Package manager switcher

npx clawhub@latest install academic-press-release-writing
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (academic press‑release writing) match the included SKILL.md, checklist, and template. The detailed requirements (five‑paragraph structure, image extraction from paper PDFs, Markdown + Word outputs) are aligned with the stated purpose.
Instruction Scope
Instructions are specific and stay within the stated purpose, including a precise Python example to extract figures and an automated workflow to produce Markdown and a .docx. Two points to note: (1) the SKILL.md references running 'python scripts/extract_figures.py' but the repository does not include that script — the agent would need to create or obtain it; (2) the skill expects the agent to read user‑supplied PDF files and write Word/Markdown files (which is expected for this purpose). There are no instructions to read unrelated system files or to transmit data to external endpoints.
Install Mechanism
This is an instruction‑only skill with no install spec (lowest install risk). However, the provided extraction code relies on the PyMuPDF 'fitz' library and an external script name; those dependencies are not declared or bundled, so the agent would need the Python environment and packages available or to install them at runtime.
Credentials
No environment variables, credentials, or config paths are required. The skill does not request unrelated secrets or broad credential access; it only operates on user-provided material (PDFs) and produces local output files.
Persistence & Privilege
The skill does not request 'always: true' or other elevated persistence. It does instruct writing local files (Markdown/.docx) and extracting images, which is appropriate for its stated purpose and scoped to its own outputs.
Assessment
This skill appears coherent and focused on turning academic papers into press releases and extracting figures from PDFs. Before installing or running it, consider: (1) The SKILL.md assumes you can run Python code and the PyMuPDF (fitz) library and refers to a script ('scripts/extract_figures.py') that is not included — confirm whether your environment already has these or whether the agent will attempt to download/install code. (2) The skill reads user‑supplied PDFs and writes Markdown/.docx files and extracted images — avoid using unpublished or confidential PDFs unless you trust the execution environment. (3) Verify any automated actions (creating files, running scripts) with the agent before allowing them, and confirm that no extracted images are uploaded externally. (4) If you want stricter control, require the skill to run only when explicitly invoked (disable autonomous invocation) or ask the skill author for the missing extraction script and a declared dependency list (e.g., PyMuPDF) before use.

Like a lobster shell, security has layers — review code before you run it.

latestvk976gx23grzkswqskqy88gkk5d834wpg
156downloads
0stars
1versions
Updated 1mo ago
v1.0.0
MIT-0

学术新闻稿撰写专业技能

一、核心结构要求(严格遵循五段式结构)

1. 01 导读部分

  • 开头:用1-2句话点明研究领域的重要意义+研究突破
  • 核心成果:简明扼要介绍研究团队、核心技术、关键突破、性能指标
  • 论文信息:明确说明发表期刊、论文标题、第一作者、通讯作者信息
  • 字数控制:300-400字,语言通俗易懂,突出新闻性

2. 02 研究背景部分

  • 领域现状:介绍相关技术的发展现状和主流技术路径
  • 存在问题:清晰阐述现有技术的瓶颈和未解决的核心挑战
  • 研究意义:点出该研究解决了什么痛点问题,有什么应用价值
  • 字数控制:300-400字,逻辑清晰,层层递进

3. 03 创新研究部分

  • 技术方案:详细介绍研究团队的核心技术路径、实验装置、创新点
  • 关键结果:分点说明实验取得的核心结果、性能参数、技术优势
  • 图表说明:每个重要图表都要有详细的图注说明,清晰描述图表展示的内容和结论
  • 字数控制:800-1000字,技术表述准确,避免过于晦涩的专业术语

4. 04 总结与展望部分

  • 成果总结:总结研究的核心贡献、理论价值、技术优势
  • 应用前景:展望该技术未来的应用领域、产业化潜力
  • 未来方向:简要说明后续研究的发展方向
  • 字数控制:300-400字,积极客观,避免夸大

5. 05 封面图部分

  • 只需标注"图源Fig.X"即可

二、内容写作要求

1. 准确性要求

  • 所有技术术语、参数、单位、人名、机构名必须准确无误
  • 实验结果、性能指标必须严格对应原文内容,不得编造或夸大
  • 作者信息、期刊信息、论文标题必须完全准确

2. 可读性要求

  • 避免直接翻译原文的复杂长句,用通俗易懂的中文表述
  • 专业术语首次出现时附带英文全称和缩写
  • 逻辑清晰,段落分明,每段聚焦一个核心内容

3. 新闻性要求

  • 突出研究的"首次"、"突破"、"创新"等亮点
  • 采用倒金字塔结构,最重要的信息放在最前面
  • 避免过于学术化的表述,兼顾专业性和可读性

三、格式规范要求

1. 标题格式

  • 主标题:中英文对照,英文在前,中文在后,居中
  • 作者信息:单独一行,"论文作者:XXX"格式
  • 撰稿人:单独一行,"新闻稿撰稿:两江编辑部"格式
  • 章节标题:"0X 标题"格式,加粗,单独占行

2. 正文格式

  • 字体:中文宋体,英文Times New Roman
  • 字号:正文12pt,行间距1.5倍
  • 段落首行缩进2个中文字符
  • 图表说明:"图X(见原文中的Fig. X):XXXX"格式,单独分段
  • 正文内容中不要出现字数统计、符合要求等说明性文字

3. 引用规范

  • 原文内容引用标注"(见Abstract/Introduction/Results/Discussion)"
  • 专业术语首次出现标注英文全称和缩写

四、字数控制标准

  • 总字数:2000-2500字
  • 各部分字数比例:导读(15%)、背景(15%)、创新研究(50%)、总结展望(20%)
  • 偏差范围:±10%以内

五、图片处理要求(关键!)

1. 图片选择标准

选择3张核心图片:

  • 图1: 概念示意图(原文Fig.1)- 展示技术原理和装置
  • 图2: 实验结果图(原文Fig.4)- 展示核心实验数据
  • 图3: 应用方案图(原文Fig.5)- 展示未来应用前景

2. PDF图片提取标准流程

必须使用以下精确流程提取图片

import fitz

# 步骤1: 打开PDF
doc = fitz.open(pdf_path)
page = doc[page_num]

# 步骤2: 分析PDF结构,找到caption位置
blocks = page.get_text("blocks")
for block in blocks:
    x0, y0, x1, y1, text, block_no, block_type = block
    if f"Fig. {fig_num}" in text:
        print(f"Caption位置: y={y0:.0f}-{y1:.0f}")

# 步骤3: 精确定位caption
text_instances = page.search_for(f"Fig. {fig_num}")
caption_y = text_instances[0].y0

# 步骤4: 根据caption位置确定图形边界
if caption_y > page.rect.height * 0.5:
    # caption在底部,图形在上方
    y_start, y_end = 100, caption_y - 10
else:
    # caption在顶部,图形在下方
    y_start, y_end = caption_y + 50, page.rect.height - 50

# 步骤5: 精确裁剪
rect = fitz.Rect(50, y_start, page.rect.width - 50, y_end)
pix = page.get_pixmap(matrix=fitz.Matrix(2, 2), clip=rect)
pix.save(f"fig{fig_num}.png")

3. 图片质量验证清单

提取后必须验证:

  • 完整性: 包含所有子图(a,b,c,d...)
  • 干净度: 没有混入caption文字(不以"Fig. X"开头)
  • 纯净度: 没有混入正文段落
  • 清晰度: 坐标轴、标签、图例完整可读

4. 常见PDF布局参考

Figure页码Caption位置图形区域
Fig.1第2页y=666 (底部)y=350-660
Fig.4第6页y=400 (顶部)y=100-395
Fig.5第7页y=326 (底部)y=100-320

5. 自动化工具

使用已创建的提取脚本:

python scripts/extract_figures.py <pdf_path> <fig_num> [output_path]

六、输出要求

  • 首先输出Markdown格式内容
  • 自动提取PDF图片并插入Word文档(.docx)
  • 图片必须干净、完整、无caption
  • 不需要生成PDF

触发关键词

"写学术新闻稿"、"生成科研宣传稿"、"论文新闻稿"、"成果宣传"

使用流程

  1. 接收用户需求:了解论文/成果、研究团队、宣传重点
  2. 按照以上规范撰写内容
  3. 内容审核:专业术语、引用、数据准确性
  4. 生成Markdown内容
  5. 自动转换为Word文档
  6. 发送给用户

常见问题处理

  • 专业术语解释:对专业术语进行通俗解释
  • 数据核对:确保数据准确无误
  • 格式调整:根据用户需求调整输出格式

Comments

Loading comments...