Loading...
Loading...
Found 8 Skills
Download, split, and deeply read academic PDFs for teaching preparation or research. Works with Cowork to split PDFs into 4-page chunks, read in batches, and produce structured reading notes on research methodology and contributions.
Paper Reader for Non-Academics. It takes a research paper and extracts actionable ideas for personal use. Focuses on comprehension rather than academic critique. Activate when users share an arXiv link, paper URL, PDF, or request to analyze a research paper. Trigger words: 'read paper', 'analyze paper', 'paper', or when users share an academic paper.
Read an academic paper together in three passes of increasing depth — a bird's-eye profile, an interactive close reading, and a line-by-line derivation or reproduction — using this directory as a reading workspace that remembers you and your papers across sessions. Give it PDF paths or a title, arXiv ID, or DOI.
Use this skill when the user requests to "read paper", "analyze paper", "summarize paper", "read a paper", "analyze literature", "help me look at this paper", "paper notes", or provides a PDF file that appears to be an academic paper. It is specialized for CV/DL papers. It also supports Zotero integration: "read this paper...", "quickly look at this paper...", "critically analyze this paper...", "read XXX from Zotero", "batch read papers under the VLA category in Zotero" **Important Trigger Phrases**: "read XXX", "read this one", "help me read" → must call this skill
Guides research ideation through a 5-step goal-driven workflow: define long-term goal, build literature tree (novelty + challenge-insight), select a problem (well-established solution check), design a solution (cross-domain transfer + decomposition), validate and iterate. Also covers structured paper reading (3 depth levels). Use when: user wants to find a research direction, brainstorm ideas, build field vision, do a literature review, evaluate idea novelty, or read papers systematically. Do NOT use for comparing/ranking existing ideas (use idea-tournament) or planning a paper (use paper-planning).
Reverse Paper Reading Method: Given a paper, recursively identify the previous papers it critiques and improves on (max 5 layers), then find the latest research progress published after it, and tell the evolution history of the relevant problem forward from the source. Centered on problems, explain the problems identified by each paper and their solution innovations in a Feynman-style manner. Use when user shares a paper and wants to understand its intellectual lineage, citation chain, problem evolution, or says 'reverse reading', 'paper traceability', 'paper context', 'paper river', 'paper connects', 'trace back', 'the ins and outs of this paper', 'paper evolution'. Also trigger when user wants to understand how a research problem evolved across multiple papers.
Help a reader understand, evaluate, and use research papers, especially in science, engineering, mathematics, and computing. Use for a paper walkthrough, an unfamiliar method or result, a relevance assessment, or a comparison of papers. Adapt to the reader's knowledge and purpose, explain the core argument from first principles, and connect claims to evidence. Accept files, links, identifiers, or excerpts; a PDF upload is not required.
Read one supplied paper closely enough to reconstruct how its authors actually got there, rather than restating what the abstract claims. Use for 精读论文, 讲透这篇论文, 把这篇读懂, 作者为什么这么设计, 这个公式怎么推出来的, paper x-ray, and deep single-paper comprehension before building on, reviewing, presenting, or citing that paper. Recovers the real starting point and the bet the authors placed, separates load-bearing design from decoration, grounds each key formula in a worked micro-example with concrete numbers, and checks how far the evidence actually reaches, including where the authors are confident and where the paper does not report something. Delivers a structured Markdown long-read by default. Not a summary, not a translation, not a peer review.