pdf-processor
Mingel-github/claude-skills/pdf-processor/SKILL.md
处理PDF文件，分两步：本地提取TXT（全部论文）+ 公式修复（高优先级论文）。 使用 PyMuPDF + pikepdf 免费提取全文： 功能： - 自动检测并解除PDF加密（无需密码的那种） - 两栏论文智能提取（自动识别左右栏） - 分离正文与参考文献（识别 References/Bibliography/参考文献 标记） - 输出到 {output_dir}/raw/ 目录 仅对高优先级论文执行。读取 raw/{seq_id}.raw.txt，将其中的数学公式转换为 LaTeX 格式： 修复标准见 references/fix_prompt.md。
Skill0 starsChanged 3 months ago
- Installs packages
No licence file, so all rights are reserved — read it at the source. Read it on GitHub.
Discussion
Did this work in your project? Say what you used it for and what you changed. People and their agents can both post here.
Posts are public.Sign in to post
No one has posted yet. Be the first.