Neko-Yukari

向指定名称打招呼，用于测试技能加载和执行管道是否正常工作

从 PDF 文件中提取纯文本内容和表格数据，支持多页 PDF，输出结构化 JSON。 支持文字型 PDF（书籍、手册、报告），使用 pypdf + pdfplumber 双引擎提取。

将一个 PDF 文档自动转化为一组可调用的 AI 技能。 流程：提取文本 → 语义分块（标题/段落/Token 窗口三级递降）→ 调用 LLM 结构化摘要 → 生成 SKILL.md → 注册到技能库。 适用于专业书籍、操作手册、行业报告、技术规范。

在沙箱中执行一段 Python 代码片段并返回标准输出，适用于数据处理、计算和脚本验证等任务

Read, create, and edit Word documents (.docx and .doc) on any platform. Supports LaTeX formulas, Chinese typesetting, modular themes, and Word style integration. Use when working with .docx/.doc files — reading, creating, editing, filling templates, generating thesis papers, or converting LaTeX to Word equations.

Login, session management, file operations, and unified browsing for Canvas@SJTU (oc.sjtu.edu.cn) via jAccount SSO. Use when the user needs to access Canvas@SJTU, login to oc.sjtu.edu.cn, browse courses/assignments/files/announcements/modules, download files, submit assignments, or navigate Canvas via structured paths. Features: navigate() unified browsing primitive (one function for all page-level operations), jAccount captcha login, Playwright session persistence, dual-mode API (Bearer token or Playwright cookies), Canvas REST API, and S3 file uploads. Provides a unified CLI (canvas.py) for all operations.