AI Agent Skills

在多个界面展示同一提示词，再剪辑生成结果，适合用真实案例说明 Agent 的使用场景。

将产品界面放入暗色摄影棚中的设备画面，围绕真实界面安排滚动、关键操作与品牌收尾。

把代码差异、易读摘要与能力场景组成说明短片，帮助无需阅读代码的受众理解变更成果。

Split Frame Portfolio 是 Skillry 提供的网页与界面技能。原站标注的任务与风格包括 Build Website Page · Build Portfolio Site · Minimalist · Monochrome · Photo Forward。可先查看案例，再根据创作需求选择。

Starlit Deck 是 Skillry 提供的演示文稿技能。原站标注的任务与风格包括 Create Presentation。可先查看案例，再根据创作需求选择。

Capability-Keynote Launch Film 是 Skillry 提供的视频技能。原站标注的任务与风格包括 Create Explainer Video · Create Social Brand Video · Fixed Pacing Grid · High Colour Presence · Light Home Dark Departure。可先查看案例，再根据创作需求选择。

Format-Shift Argument Film 是 Skillry 提供的视频技能。原站标注的任务与风格包括 Create Explainer Video · Create Social Brand Video · Compact 8px Geometry · Near Black Monolith · Radial Spotlight Glow。可先查看案例，再根据创作需求选择。

CreatorMotion · Status Focus Sidebar 是 Skillry 提供的视频技能。原站标注的任务与风格包括 Create Broll Animation · Minimalist · Editorial · Typographic。可先查看案例，再根据创作需求选择。

The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.

Assess business quality, economic moats, management, competitive positioning, and durable value creation.

Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN,…

Run a literature review using paper search and primary-source synthesis. Use when the user asks for a lit review, paper survey, state of the art, or academic landscape s…

Search and read research papers. The main agent calls alphaXiv, OpenAlex, and bioRxiv discovery primitives, ranks the combined candidates, and chooses sources for focuse…

Use when the user wants a structured, saturating literature survey on a question — not a one-shot summary, but an evidence/contradiction matrix (sources × claims) built…

Review UI code for web interface guidelines, UX quality, accessibility, and interaction design best practices.

Translate Figma designs into production-ready UI code with close visual fidelity and component-level detail.