Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Intelligently compress and rewrite documents into TTS-friendly scripts. Uses Claude AI to analyze content, compress to target duration, convert to spoken style with emotional language, and auto-segment. Perfect for video narration.
将 Markdown 文章转换为微信公众号 HTML 格式，支持自动插入配图、微信样式优化。
Text-to-speech conversion using GLM-TTS service via the `uvx zai-tts` command for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, podcast, driving, cooking). (3) Using pre-cloned voices for speech.
Audit and fix Beamer slide decks for compilation errors, layout problems, and visual issues. Use this skill whenever the user says "check my slides", "fix my slides", "the slides don't compile", "text is running off the page", "slides look wrong", or after generating a Beamer deck to verify it before delivering. Also use when the user mentions overfull boxes, overlapping content, broken images, or any Beamer formatting issue.
Generate LaTeX Beamer slide decks using my defined style and conventions. Use this skill whenever the user asks to create slides, a presentation, a lecture deck, or Beamer content — for teaching.
Generate shareable PNG report cards of your Claude Code carbon footprint
Downloads embedded videos from web pages. Fetches the page, identifies the video hosting service (Vimeo, YouTube, etc.), resolves the correct embed/player URL, and downloads using yt-dlp. Handles private/unlisted videos that require referer headers or embed URLs. Use this skill when someone says "download this video", "save this video", "grab the video from this page", "rip this video", or provides a URL and asks to download media from it. Also trigger when someone pastes a URL to a page with an embedded video and wants the video file locally.
Download video from X/Twitter posts using yt-dlp. Use when the user wants to "download this X video", "save this tweet video", "grab video from Twitter", or provides an x.com/twitter.com status URL with a video. Handles HLS streams and uses --print after_move:filepath for reliable path detection.
Generic media transformation orchestrator — download videos from any source (X/Twitter, Zoom, YouTube, web embeds), upload to YouTube, transcribe with timestamps, generate chapters, create thumbnails with GPT-Image-2, and A/B test titles. Use when the user wants to move a video from one platform to another, or asks to "download and upload this video to YouTube", "publish this recording", "save and transcribe this", or any video pipeline task. Encodes learned best practices and preferences for each stage.