Initialize or align repository-level AI collaboration scaffolding with AGENT.md, a delegating CLAUDE.md compatibility stub, and .agent/. Use when a user asks to bootstrap a new repository, onboard an existing repository, migrate Claude conventions, create project memory/workspace directories, or standardize where stable collaboration preferences versus changing progress and paths are recorded.
Curate a daily (or date-range) personalized paper digest from arXiv + HuggingFace. Fetches new & cross-listed papers, reads their abstracts, matches them against the user's preference topics (Agent / World Model / post-training / ...), and writes a grouped-by-topic Markdown digest with per-paper summaries. Self-contained: needs only python3 + the optional `hf` CLI, no other skill or external script. TRIGGER ONLY on an explicit request to run/generate/update the digest, e.g. "跑一下 paper-suggestions", "生成今天的论文日报", or when invoked by a scheduled/automated task. DO NOT auto-trigger. This skill is meant to run on a schedule (a daily cron/loop set up separately) OR on explicit demand — never run it proactively just because papers, arXiv, or research topics are mentioned in conversation. When unsure, ask before running. DO NOT TRIGGER when: user wants a raw keyword search, to read one specific paper's full text, to read a local paper folder, or to import papers into Zotero (those are separate skills) — and never as a
Turn a local Markdown file into a Feishu (Lark) Docx cloud document and push the link to a user via a private bot DM. Uses a Feishu self-built app (tenant_access_token) with the Drive import API and the im/v1 message API. TRIGGER when: user wants to send/push a Markdown file to Feishu/Lark as a cloud document, create a 飞书云文档 from local content, DM a doc link to themselves or someone via a Feishu bot, or publish a report/digest (e.g. a paper digest) into Feishu Docs. DO NOT TRIGGER when: user wants to drive a coding agent from Feishu (that is a different inbound bridge), or wants a generic Feishu API integration unrelated to importing docs or sending messages.
Convert PDF files to Markdown using pymupdf4llm. TRIGGER when: user asks to convert a PDF to markdown, extract text from PDF, or read/parse a PDF into markdown format. DO NOT TRIGGER when: user just wants to read an existing paper.md or work with already-converted files.
Extract, browse, and download figures from arXiv papers using their HTML rendering. Use this skill whenever the user wants to get figures/images/diagrams from an arXiv paper, extract paper illustrations, download paper visuals, grab charts or plots from a paper, or reference a specific figure from an arXiv paper for use in slides, blog posts, or documents. Also trigger when the user mentions an arXiv ID (like 2406.11434) in the context of needing images, visuals, or figures from that paper — even if they don't say "figure" explicitly (e.g., "get me the architecture diagram from 2406.11434", "I need the results chart from this paper"). This skill handles the full pipeline: fetching the paper's HTML, parsing all figure environments with their captions, letting the user choose which to download, and saving them with a structured captions.json metadata file.
Read and work with local academic paper folders exported by ZoFiles from Zotero. TRIGGER when: user asks to read/summarize/cite/review/compare a paper that is already downloaded locally, references a local paper folder or path, works with paper.md/paper.bib/kimi.md files, browses the local paper library by topic, or asks to update/refresh the paper library directory structure. DO NOT TRIGGER when: user asks to search for papers online, find new papers, look up papers on a topic online, browse HuggingFace daily papers, or read a paper by arXiv ID without a local copy (use read-paper-online skill).
Import arXiv papers into Zotero with duplicate detection and batch support. TRIGGER when: user asks to import papers, add arxiv papers to zotero, batch import papers, check for duplicate papers in zotero, mentions importing by arXiv ID, or wants to list Zotero collections. DO NOT TRIGGER when: user is working on ZoFiles plugin code, exporting papers, or general Zotero questions.
Search, browse, and read academic papers online using HuggingFace Papers API and arxiv2md. TRIGGER when: user asks to search for papers online, find recent papers, look up papers on a topic, search arXiv/HuggingFace for papers, check what's new in a research area, browse HuggingFace daily papers, get detailed info about a specific paper (authors, abstract, keywords, github), read a paper's full text by arXiv ID online, or download a paper as markdown. DO NOT TRIGGER when: user wants to read a local paper folder or paper already downloaded locally (use read-paper-local skill), import papers into Zotero (use zotero-connector skill), or convert a local PDF (use pdf-to-markdown skill).