438061781/academic-press-release-writing/SKILL.md
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"、"成果宣传"等关键词;(4) 需要规范的新闻稿写作模板和流程指导。
npx skillsauth add openclaw/skills academic-press-release-writingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
选择3张核心图片:
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")
提取后必须验证:
| 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 |
使用已创建的提取脚本:
python scripts/extract_figures.py <pdf_path> <fig_num> [output_path]
"写学术新闻稿"、"生成科研宣传稿"、"论文新闻稿"、"成果宣传"
tools
Use when the user wants to connect to, test, or use the McDonalds service at mcp.mcd.cn, including checking authentication, probing MCP endpoints, listing tools, or calling McDonalds MCP tools through a reusable local CLI.
development
Web scraping platform — Twitter/X data, Vinted marketplace, and general web scraping API
development
SlowMist AI Agent Security Review — comprehensive security framework for skills, repositories, URLs, on-chain addresses, and products (Claude Code version)
data-ai
去除中文文本中的 AI 写作痕迹,使其读起来自然。基于维基百科 AI 写作特征指南,检测 24 种 AI 模式。触发词:humanizer-cn、去除 AI 痕迹、去除 AI 写作痕迹、中文文本人性化。