4 published skills
- ▌ Lit Search · luwill bundleRuns an exhaustive time-windowed literature search over a research topic and delivers a quality-tiered DOI list plus a matching formatted reference list, with measurable recall (gold-set recall, PRISMA counts, citation-closure saturation). Use for systematic reviews / SLR, 开题报告, 挑战赛调研, or any "把某方向近 N 年文献检索全/理一遍/梳理一遍/查全" request. Builds the corpus — not for reading or summarizing the papers themselves, and not for writing the review text. Not for casual "find me a few papers" lookups.
- ▌ Scholar Slides · luwill bundleUse when the user wants a research paper, arXiv/DOI link, or research topic turned into academic slides — journal club / lab meeting (组会汇报), thesis defense (答辩幻灯片), conference or job talk (学术报告), poster, or grant pitch — or shares a paper and asks to "make slides / 做成 PPT / 讲一下这篇论文", especially when equations, numbers, figures, and citations must stay accurate and editable. NOT for marketing/pitch decks with no scholarly source, and NOT for writing the paper itself.
- ▌ Paper Slide Deck · luwill bundleUse when the user wants visually striking, shareable slide-deck IMAGES from any content — an article, blog post, topic, or paper — where look-and-feel matters more than editable precision (风格化幻灯/小红书配图/公众号配图/视觉化海报), optimized for reading and social sharing rather than live presentation. Offers 17 T2I aesthetic styles (watercolor, sketch-notes, pixel-art, editorial, chalkboard, etc.); each slide is an AI-generated image (Gemini/Nano Banana), so the look is distinctive but text/math/data are baked into the image (not editable). NOT for a faithful academic talk where equations, numbers, tables, and citations must stay exact, editable, and projector-ready (组会/答辩/thesis defense/conference/results-heavy talks) — for that use scholar-slides instead, since text-to-image will garble math and data.
- ▌ Medical Imaging Review · luwill bundleUse when the user asks to plan, conduct, document, synthesize, or draft a medical imaging AI narrative review or method survey, scoping review, or systematic review with qualitative synthesis, including protocol design, literature search, screening, extraction, risk-of-bias appraisal, or evidence synthesis. Do not use this skill to perform a meta-analysis or umbrella review; route those requests to a specialized evidence-synthesis methods workflow.