Explora publicaciones de X revisadas sobre Skills, las personas que las comparten y los proyectos que mencionan.
El recuento incluye solo publicaciones sobre Skills recopiladas y revisadas. Un día vacío significa que aquí no se ha recopilado ninguna. Fechas en UTC.
47 publicaciones recopiladas
Hasan Shoaib releases Squint, a Skill that steers AI UI generation away from default “AI slop” toward tighter visual taste so agents spend less time being corrected on design.
tvytlx recommends Zea1shama (Garinmckayl)'s Skill for: 安利 Anima：把生物学问题变成可交互等距结构图，并敢于标注证据强弱. The poster is a recommender, not the author.
Shubhang Rajput introduces design-superskills, a six-skill design workflow covering reference capture, research synthesis, first drafts, Figma organization, design annotations, and developer handoff while keeping creative decisions with the designer.
vista8 recommends wheresryan22's Skill for: 学习 Anatomy skill 的验收/数据/画面元素控制规则并融合到自有 skill. The poster is a recommender, not the author.
mylifcc recommends wheresryan22's Skill for: 把抽象技术概念变成可交互等距机械图解（Anatomy）. The poster is a recommender, not the author.
Cathryn notes that Diagram Design has passed 50k GitHub stars. The Skill turns repository or product descriptions into branded single-file HTML diagrams instead of default Mermaid output.
sundyme recommends wheresryan22's Skill for: 一句话描述概念，Claude 做成可交互等角透视机械动画（Anatomy）. The poster is a recommender, not the author.
An imagegen Skill brings APIMart image generation into Claude. Its creator built it for workflows that need higher-resolution images.
Marco highlights /render, his text-to-3D Skill using build123d and a browser viewer where models can be inspected and edited.
majiang-photo-story turns a real photo into a white-background poster with sparse black-line characters and a story drawn from the subject. In a quote of her own release post, the creator explains preserving the photographed object, extending the scene into the whitespace, and checking caption wording separately from lettering.
HiAPI demonstrates a consistent game asset pack built from one game idea, including characters, tiles, UI, backgrounds, music, narration and a trailer. In the same thread, the author shares the open-source Skill for generating the pack and building a playable prototype in Claude Code or Codex.
Qiaomu shares qiaomu-codex-imagegen, a Skill with MCP and CLI routes for calling Codex's built-in image generation from another agent.
A recommendation of ip-as-logo for rounded square mascot images with simple silhouettes and a solid background. The workflow proposes design directions before generating a set of independent candidates.
The vgpu Skill guides Blender modeling, baking and asset validation for web projects, alongside version-matched WebGPU documentation.
Peng Chujin releases LiveCanvas, quoting his own Live image demo. The Skill researches a topic, plans a cover and storyboard, then renders an animated information card with Remotion and packages Apple Live Photo resources in a supported macOS environment.
恒星sun recommends Logo Design and highlights its concept checkpoint: study references, create SVG options and check small-size and one-color behavior, then wait for a direction choice before building icons and guidelines. The linked Skill is by kaankiziltug.
pengchujin introduces LiveCanvas, a Skill that turns a prompt into a Live Photo with a designed cover and animation. The linked project uses Remotion to create information cards from images, scenes, timelines and optional charts, with previews and paired Live Photo resources.
Mobile Prototype helps review an app’s screens and user flow before native development. The creator introduces the open-source Skill for Claude Code and Codex; prototype format depends on the installed revision.
Explore distinct UI directions, compare prototypes side by side, then refine the chosen design with desktop and mobile checks.
Dreameryanyan shares mono-color and mentions receiving remixes from users. The linked Skill creates original editorial images using one or two inks, neutral paper, halftone imagery and deliberate typography; image generation requires a compatible tool.