stable-jarvis

Use when a researcher is choosing, framing, refining, or stress-testing a research question, hypothesis, thesis topic, project idea, grant direction, paper angle, or stalled research direction.

精读文献。快速泛读请用paper-quick-read。

泛读：快速概览Zotero库中的文献，单轮LLM生成摘要级Markdown报告，并上传为Zotero Note。深度精读请用paper-deep-reader。

Intelligently organize and categorize Markdown notes within an Obsidian vault. This skill leverages Obsidian MCP tools to analyze the vault's current folder structure and note content, ensuring new or misplaced notes are moved to their most contextually appropriate locations (e.g., PARA, Zettelkasten, or custom taxonomies).

Discover recent arXiv papers matching a research profile and generate Obsidian-compatible Markdown notes. Use this skill when the user wants to find new papers, refresh their literature inbox, or search arXiv based on their interests.

Autonomously scans specific directories (00, 10, 20, 30) in an Obsidian vault, analyzes note content, and intelligently merges AI-generated YAML frontmatter (tags, summary, aliases) into the notes.

Distills a raw, text-based discussion (e.g., meeting notes, user-AI conversations in Markdown) into one or more structured, permanent 'evergreen' knowledge notes.

Convert any file to Markdown using Microsoft MarkItDown. Use this skill whenever the user needs to extract text from PDFs, Word documents, Excel spreadsheets, PowerPoints, EPUBs, images, audio, HTML pages, CSV, JSON, XML, ZIP archives, Jupyter notebooks, Outlook .msg files, or any other document format. Also use it when the user asks to "convert to markdown", "extract text from", "read this file as text", or mentions specific file formats they want turned into readable markdown. This skill runs in the conda jarvis environment with markitdown v0.1.6b2.

Perform three-way cross-validation of a research paper by comparing the original paper text (via Zotero), official code implementation (via Git), and personal Obsidian notes. Use this skill whenever the user wants to "audit a paper", "verify paper claims against code", "cross-check notes with implementation", "triangulate paper + code + notes", "find discrepancies between paper and code", or mentions wanting a deep, structured comparison of a paper's claims against its implementation and their own notes. Also trigger when the user asks to "analyze this paper thoroughly" with code available, or when they want to systematically reconcile what the paper says, what the code does, and what their notes claim.

Write technical documentation, guides, blog posts, tutorials, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

Directly convert Notion pages to Obsidian-friendly Markdown using MCP fetch and local processing. Use this skill when you need to migrate specific Notion pages identified by URL or ID into the local Obsidian vault, ensuring LaTeX normalization, image localization, and property-to-frontmatter mapping.

Automatically generates a 1-page weekly progress report PPTX based on Obsidian daily notes. Trigger this skill on Saturdays. It (1) Identifies the date range from last Saturday to this Saturday, (2) Reads daily notes from '50 Archive/Daily Notes/' and extracts only research (科研) and project (项目) related content, (3) Fills exactly ONE slide with '本周进展' and '下周计划', (4) Never touches the slide master or header area (name lives in the master), and (5) Saves to '00 Inbox/UserName_YYYY_MMDD_MMDD_week_report.pptx'.