paper2wechat
paper2wechat transforms research PDFs into polished WeChat public account articles through human-led coordination. You handle the intellectual work—understanding the paper, structuring the narrative, and writing the deep-read piece—while delegating mechanical tasks like PDF parsing, cover generation, and publishing to helper scripts. The result is a formatted long-form article with embedded figures and optional direct upload to your WeChat draft box.
paper2wechat converts academic papers to WeChat articles with your authorship and AI-assisted formatting.
AI-generated summary based on this skill's SKILL.md
Install
QuZhan51496/paper2anything/paper2wechat · repository language: Python
git clone https://github.com/QuZhan51496/paper2anything
cp -r paper2anything/paper2wechat ~/.claude/skills/paper2wechatnpx skillfed install QuZhan51496/paper2anything/paper2wechatFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I convert an academic paper PDF to WeChat article?
paper2wechat transforms research PDFs into polished WeChat public account articles through human-led coordination. You handle the intellectual work—understanding the paper, structuring the narrative, and writing the deep-read piece—while delegating mechanical tasks like PDF parsing, cover generation, and publishing to helper scripts. The result is a formatted long-form article with embedded figures and optional direct upload to your WeChat draft box.
What does paper2wechat do with research papers?
paper2wechat automates scholarly article publishing to WeChat official accounts with draft management. It extracts paper insights, generates professional covers from research PDFs, and formats long-form content for non-specialist audiences on social media, letting you focus on the narrative while automation handles PDF parsing and publishing logistics.
Can paper2wechat convert 论文转公众号文章 automatically?
paper2wechat coordinates both human and mechanical effort. You perform the core intellectual work—analyzing the paper and crafting the deep-read narrative—while the tool automates PDF parsing, cover generation, and formatting. This hybrid approach ensures quality content while eliminating repetitive technical tasks in the publishing pipeline.
Does paper2wechat support direct WeChat draft upload?
Yes. paper2wechat generates formatted long-form articles with embedded figures and offers optional direct upload to your WeChat draft box. This streamlines the publishing workflow, letting you review and refine the draft before posting to your public account.
What output format does paper2wechat produce?
paper2wechat produces polished WeChat-ready articles with professional covers, structured formatting, and embedded figures extracted from the research PDF. The output is designed for deep-read consumption by non-specialist audiences and can be saved as a draft or published directly to your WeChat official account.
SKILL.md
rendered from the published skill — quoted content, verbatim
paper2wechat — 论文转公众号深度解读（你主导的协调式）
把一篇论文 PDF 写成学术深度解读型公众号长文。你是主笔：这份文件是配方，
不是全自动脚本——没有 main.py。机械步骤（解析 / 封面 / 排版）调用 scripts/ 下的小工具；
论文理解、文章结构、长文撰写由你亲自完成，并在关键点用 AskUserQuestion 与用户确认。
目标读者：有 AI/ML 背景的研究者、工程师、学生——读得懂方法细节、关心贡献与局限。
PDF
→ 解析 (parse_pdf.py：MinerU → parsed/ + figures/，含表格)
→ 你读懂论文 (读 parsed/ + 看 figures/) → understanding/paper_understanding.json [确认切入角度]
→ 你写深度解读长文 (结构自由、配图、忠实准确) → wechat_article.md + .json [确认]
→ 封面 (cover.py：默认 API 生图 gpt-image-2 横版 900×383；无 key/key 不可用回退本地合成复用原图)
→ 发布草稿箱 (publish.py：md2wechat 直推公众号草稿箱；无凭据/失败→本地样式化 HTML)
→ 公众号推文
运行方式
- 一步步来：机械步骤用
Bash调脚本，创作步骤你自己用Read/Write做。 - 每个 Bash 块开头就地算
WORKDIR（各 Bash 调用是独立 shell、不共享变量）： ```bash WORKDIR="$(dirname "$pdf_path")/.paper2anything/wechat/$(basename "${pdf_path%.*}")"
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 6 files
paper2wechat/SKILL.md
paper2wechat/scripts/_env.py
paper2wechat/scripts/cover.py
paper2wechat/scripts/parse_pdf.py
paper2wechat/scripts/publish.py
paper2wechat/scripts/utils.py