unumbrela

Given a research direction (e.g. "generated image detection", "对比学习", "neural machine translation"), research the literature and produce a NON-LINEAR development genealogy: a terminal ASCII tree (built from `--` connectors and text) plus a narrative tracing who proposed what, against which problem, what built on what, and which lines ran in parallel — from the founding work up to the latest. Use when the user wants to understand how a field evolved, not just a flat list or a theme-organized survey.

Use this skill when the user wants to create or improve a figure/chart for an academic paper or presentation (图表制图/论文绘图/画对比图/结果图/出版级图表), including writing matplotlib/seaborn/TikZ code for experiment results.

Use this skill when the user gives a paper (arXiv ID, DOI, title, or arXiv/OpenAlex URL) and wants a citation — BibTeX, GB/T 7714, APA, or a .bib file (生成引文/导出 BibTeX/参考文献格式). Works without any API key.

Use this skill when the user asks to find, search, or survey academic papers on a topic (查论文/找文献/调研某方向的论文), wants recent or highly-cited work in a research area, or asks "有哪些论文做了 X". Works without any API key.

Given a research direction (e.g. "generated image detection", "对比学习", "neural machine translation"), research the literature and produce a NON-LINEAR development genealogy: a terminal ASCII tree (built from `--` connectors and text) plus a narrative tracing who proposed what, against which problem, what built on what, and which lines ran in parallel — from the founding work up to the latest. Use when the user wants to understand how a field evolved, not just a flat list or a theme-organized survey.

Build publication-quality ILLUSTRATED scientific figures that pair real rendered content (molecular / atomistic structures loaded from .xyz / .npz / RuNNer / ase) with a consistent drawio narrative frame — for papers, slides, posters, or advisor briefings. Use when the user wants a figure that is more than a plain flowchart: labeled multi-panel comparisons, a system / architecture figure with embedded structure renders, a results figure with native bar charts or tables, a difficulty ladder, a timeline / roadmap, or any "图文并茂 / illustrated explainer" where boxes should be replaced by real elements. It renders shaded-sphere atomistic images (camera projection, CPK colors, bonds, precise atom-anchored overlays) and composes them with a curated palette / title / pill / table / bar toolkit that keeps a whole figure set uniform and renders CJK reliably. Triggers: "画一张图", "配图", "图文并茂", "illustrated figure", "structure figure", "render a molecule / crystal / slab", "architecture figure with a structure", "advisor / p

Create Distill-quality interactive, detailed, clear figures for articles/posts in any domain — linked diagrams (graph/matrix/text with synced highlighting), step/scrub/animation, editable-input-driven, and statistical panels with brushing. Use when the user wants a rich interactive visualization, an explorable explanation, a "Distill-style" or publication-quality figure, or to embed an interactive chart/diagram into writing. Ships a zero-build d3 v7 component library plus an automated render→screenshot→self-critique loop so figures come out high-quality reliably.