菜单
View paper content at different detail levels. L1 (metadata), L2 (abstract), L3 (paper-level conclusion card), L4 (full text). Use when the user wants to read a paper, see its abstract, L3 takeaway, or full content.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Vinnish-A/AutoR --skill show命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | show |
| description | View paper content at different detail levels. L1 (metadata), L2 (abstract), L3 (paper-level conclusion card), L4 (full text). Use when the user wants to read a paper, see its abstract, L3 takeaway, or full content. |
View the content of a specified paper in a layered structure. Supports four levels: L1 (metadata), L2 (abstract), L3 (paper-level conclusion card), and L4 (full text).
Parse user input and extract:
data/papers/)If the user is unsure of the paper ID, use /search first to locate the target paper.
Run the view command:
autor show "<paper-id>" --layer <N>
| Level | Content | Notes |
|---|---|---|
| L1 | Metadata | title, authors, year, journal, doi |
| L2 | Abstract | abstract |
| L3 | Paper-level conclusion card | takeaway, key findings, quantitative signals, limitations, and provenance when available |
| L4 | Full text | complete Markdown |
User says: "Show me the abstract of Smith-2023-TransformerSurvey."
→ Run show "Smith-2023-TransformerSurvey" --layer 2
User says: "Give me the full text of Zhang-2024-LLM."
→ Run show "Zhang-2024-LLM" --layer 4
User says: "What is the conclusion of this paper?" (paper ID already in context)
→ Run show "<paper-id>" --layer 3