Rising stars
vox stayl animation
Arabic documentary paper-collage animation engine. Always asks for the Engine Source Material PDF first, then runs 10 gated states: niche, ten ideas, duration, Arabic script, ElevenLabs voiceover, beats, per-beat English image prompts with Arabic labels, universal video prompt, thumbnails.

AI Core Coaching Supervision
Using *Directly to the Core: A Revolutionary Approach to the Path of Coaching Excellence* as the sole evaluation standard, this Skill reviews a coaching session recording, transcript, or notes and turns it into structured supervision notes. The notes include an overall assessment, a phase-by-phase review (beginning, middle, and end), identification of 22 themes, the top three improvement suggestions, a case follow-up plan, and overall improvement areas. The output language follows the input language (English session → English review; Chinese session → Chinese review). The result is saved as a YouMind document.

Slideshow Narration Video
Turn a presentation topic—or your existing script, materials, or Slides—into an editable 16:9 video with Chinese narration for each slide. The Skill first plans the main narrative and asks you to confirm the outline and preview, then generates the slide visuals, writes and synthesizes Chinese narration for each slide, and assembles an editable video with one slide visual and one narration segment per page. Subtitles are enabled by default. The visual style, voice, slide count, and tone adapt to the topic, audience, and platform.

SwiftUI Expert Companion
An elite engineering companion for SwiftUI developers. It covers the full range of day-to-day SwiftUI work: analyzing and debugging issues, making architectural decisions, designing view composition and state management, building new features, reviewing and optimizing existing code, and applying modern SwiftUI best practices (Swift 6 concurrency, the Observation framework, NavigationStack), performance, accessibility, and Apple Human Interface Guidelines. It adapts its depth to the task: a concise fix for small problems, and a full engineering report (diagnosis, architectural rationale, code, trade-offs, self-check) for complex ones. It always aims to return compiling, up-to-date, production-ready SwiftUI code, and responds in the user's language.

Elite UI Design Studio
An elite UI design specialist for web, mobile, and desktop. It reviews and improves existing interfaces, builds executable UI code, produces compact design systems and specs, and generates visual concept mockups, all at a high level of craft, usability, and accessibility. Every output is designed to be distinctive rather than generic, with strong hierarchy, a coherent visual system, responsive layouts, and full state coverage. It enforces a strict token-economy discipline: it delivers the artifact directly with no preamble, no restating, and no filler. Output language follows the user's language.

Image Watermark Remover
After you upload or reference an image, this Skill automatically identifies watermarks in the image, including text, URLs, logos, semitransparent overlays, and repeated tiled marks. It seamlessly fills them with a background that matches the surrounding area while keeping everything else unchanged—the subject, composition, color tone, and aspect ratio. It is suitable for situations where source images contain platform watermarks, copyright marks, or semitransparent overlays and you need a clean version. Supports single or multiple images.

Podcast Content Studio
Turn raw audio, transcripts, written notes, slides, or episode materials into a complete podcast content package ready for production, editing, publishing, and distribution. It is especially suited to long-form interviews and narrative shows, and can carefully handle sensitive topics such as psychology, forensic psychology, personality disorders, trauma, and true crime while preserving context and balancing accuracy, empathy, and publication risks. From organizing source materials, revising transcripts, and mapping content to chapter markers, opening hooks, guest bios, memorable quotes, episode summaries, resource links, and social accounts, it helps you build content assets that are easy to use in production. It also adapts copy for different publishing channels, producing descriptions, promotional posts, and short-form video or social content suggestions for podcast platforms, websites, YouTube, SoundCloud, newsletters, and X, so one long-form episode can become multiple publishable versions. When information, timestamps, links, or account details are missing or unconfirmed, the content clearly marks items for completion or verification rather than inventing facts. It also flags sponsor segments, sensitive wording, anonymization needs, source citations, legal risks, and content that may need review before publication. Whether you need a complete episode package or want to build a trackable podcast content structure from existing materials, you get Traditional Chinese output that is clear, easy to scan, engaging, and ethically considered.

Human-Sounding WeChat Writing
Make WeChat Official Account articles, posts, and spoken scripts sound more like a real person talking: grounded in specific situations, shaped by personal judgment, and carried by natural emotion and conversational rhythm. Readers will find the writing relaxed and fluid rather than stiff or formal, with a clear sense of the author and their point of view. Whether you are writing from scratch, rewriting an existing draft, polishing copy, or reviewing it for a more human feel, less AI-like wording, or a more authentic voice, this Skill helps reduce clichés, excessive parallel phrasing, and overly structured expression while preserving facts, brand tone, and key information. The writing will better match WeChat reading habits, with a natural opening, a clear point of view in the middle, and an ending that avoids empty slogans. When needed, everyday details, actions, dialogue, or small conflicts can make the content more specific and vivid. You will get a publication-ready WeChat article, along with multiple title options, optional quotable lines, image suggestions, and feedback from a human-voice review. It will not invent experiences, data, or quotes to create a more human feel, nor overuse internet slang, rely on excessive sentimentality, or compromise the brand’s character. It works well for personal accounts, brand content, and spoken scripts that need a natural voice.

Search PNCP
Searches the National Public Procurement Portal (PNCP) by keyword and organizes attachments from the notices found. By default, it applies the filters Status: Closed, Instrument Type: Notice, Bidding Method: Electronic Auction, and Government Level: Federal—all of which can be adjusted by the user. It presents the notices found for confirmation and, after approval, creates a dedicated project (one group per notice), locates the attachments for each procurement, attempts to save them to the project, and, when a file type is unsupported (application/octet-stream), provides a direct download link for each attachment, generating a table report.