skills/paper-parse/SKILL.md
对用户提供的任何学术论文(PDF附件或URL)进行双模式深度研读。当用户请求分析、研读、解读或总结一篇学术论文时,使用此技能。一次性生成两份报告:Part A 面向研究者的深度专业解析,Part B 面向快速理解的核心逻辑与价值提炼。
npx skillsauth add acefrost511/workmemory paper-parseInstall 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.
对任何学术论文进行专业深度解析,一次性产出两种不同深度的报告。
论文研读分四步执行:
使用 pdftotext 命令或 file 工具的 read 动作提取论文全文。对于URL来源的论文,先尝试下载PDF再提取。必须覆盖从摘要到参考文献的所有内容。对于包含重要图表的论文,使用 file 工具的 view 动作查看关键图表页面,并将图表信息保存到文本文件中。
创建临时分析文件 temp_analysis.md,提取并组织以下要素:
此步骤不可跳过,它是保证最终报告质量的思考过程。
创建最终交付文件,文件名格式为 [论文简称]_研读报告.md。
撰写 Part A 前,先读取模板:/home/ubuntu/skills/paper-parse/references/part-a-template.md
撰写 Part B 前,先读取模板:/home/ubuntu/skills/paper-parse/references/part-b-template.md
使用 message 工具交付最终报告文件。消息文本中简要概括论文的核心创新、关键发现和理论价值,引导用户查看附件。
--- 分隔# [论文标题] 双模式研读报告
---
## Part A: 深度专业学术速读报告
(遵循 part-a-template.md 结构生成的完整内容)
---
## Part B: 核心逻辑链与根本价值提炼
(遵循 part-b-template.md 结构生成的完整内容)
development
Create, edit, analyze spreadsheets (.xlsx, .xlsm, .csv). Formulas, formatting, data analysis.
testing
Self-improving agent system that analyzes conversation quality, identifies improvement opportunities, and continuously optimizes response strategies.
tools
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
documentation
Turn a chosen AI topic into a public-account writing package: collect evidence from X/Twitter and other sources, extract high-value comments, and produce title options + structured outline written into Obsidian. Use when user asks for topic-based research and article prep.