视频·图像·音频技能

Turn a YouTube video idea into a designer-ready thumbnail brief: focal subject, face and emotion, a text overlay of 4 words or fewer that the title does not repeat, contrast and composition, and 2 to 3 A/B concepts for Test and Compare. Built on 2026 principles (one focal point, legible at 120 pixels, complements the title). Outputs the brief plus the Publora attach step (the image upload itself is out of band). Use to plan a thumbnail. Not for title words (use yt-title-optimizer).

中文简介正在准备中。当前显示原文说明。

Build a weekly YouTube upload plan: long-form vs YouTube Shorts mix, posting cadence, per-slot title and thumbnail pairing, hook angle, community-tab posts between uploads, and a goal balance across CTR, retention, and subscribes. Maps Shorts as top-of-funnel that points at long-form, and long-form as the loyalty and watch-time engine. Use to plan a week or a content calendar instead of shipping ad hoc. Not for writing a single title, description, or hook (use the dedicated yt skills).

中文简介正在准备中。当前显示原文说明。

Write a full YouTube video description under 5,000 characters with a first-150-character hook (the only part visible before Show more, and what shows in search and suggested), timestamped chapters, naturally placed keywords, links, and a clear call to action. Covers long-form and YouTube Shorts. Becomes the create-post content that publishes with the video. Use to write or rework a description. Not for the title (use yt-title-optimizer) or the spoken opening (use yt-hook-scripter).

中文简介正在准备中。当前显示原文说明。

Plan, write, and publish for YouTube and YouTube Shorts. Use when the user wants high-CTR video titles, an SEO description with chapters and links, a first-30-seconds retention script (or a 3-second Shorts hook), a designer-ready thumbnail brief, a community-tab post or poll, or a weekly upload plan. The user supplies the video; the skills produce the title, description, hook, and thumbnail brief, then on approval upload and schedule via the Publora API.

中文简介正在准备中。当前显示原文说明。

This skill should be used when the user runs /dd or /ㅇㅇ to act on the current OS clipboard (text or image) without pasting it into chat. It captures the live clipboard into a local cache and uses only the manifest plus a short preview as context, so error logs and reference images do not bloat the conversation. Korean triggers: "/dd", "/ㅇㅇ", "클립보드 보내줘", "이거 분석해줘", "방금 캡처한 거", "이 레퍼런스로", "스크린샷 드롭". English triggers: "/dd", "drop clipboard", "use what I copied", "this screenshot", "this reference".

中文简介正在准备中。当前显示原文说明。

Route requests to summarize files, URLs, images, inline text, or multiple sources. Select the requested format and preserve evidence, exact counts, uncertainty and source coverage through summarization, synthesis and agent-result relay.

中文简介正在准备中。当前显示原文说明。

Describe images, screenshots, diagrams and charts from visual inspection. Preserve visible text, counts, labels, directions and uncertainty; distinguish observation from interpretation. Use for image summaries, screenshot explanations and diagram descriptions.

中文简介正在准备中。当前显示原文说明。

Wrap a raster image in an SVG and overlay a numbered red "step" circle for course screenshots. Use when running /create-svg-image, or when asked to add a numbered callout badge to an image (e.g. a red circle with a "1" pointing at a UI control) that must still render on a GitHub README.

中文简介正在准备中。当前显示原文说明。

Rebuild or update the course overview video (about 98 seconds) for this course in videos/overview. Use when running /overview-video, or when asked to refresh the course overview video, add a chapter or feature to it, retake its dark-mode app screenshots, change its copy or timing, add music, or render a new MP4.

中文简介正在准备中。当前显示原文说明。

将口播稿、文章或已有音频与 SRT 制作为可自动播放的 16:9 网页视频演示（Vite + React + TypeScript）。用连续视觉场景、证据画面、卡片状态变化与 MG 动画解释内容；支持点击推进、整段原声驱动、按绝对时间验帧，以及预览页一键导出 1K/2K/4K MP4。适用于 B 站、YouTube、视频号口播配画面与产品演示。

中文简介正在准备中。当前显示原文说明。

Use the Ta macOS app and ta CLI to capture displays, foreground apps, windows, or known regions without taking focus, then annotate, OCR, understand, translate, copy, or save images. Use when an Agent needs visual input or deterministic screenshot markup; do not use it as a general mouse-and-keyboard automation tool.

中文简介正在准备中。当前显示原文说明。

Repurpose one source asset into platform-specific social media posts while preserving the original idea and adapting format, tone, and call to action. Use when turning blogs, transcripts, changelogs, podcasts, videos, demos, notes, or launch plans into a social content package.

中文简介正在准备中。当前显示原文说明。

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.

中文简介正在准备中。当前显示原文说明。

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

中文简介正在准备中。当前显示原文说明。

Trigger when: (1) User wants to create an educational/explainer video, (2) User has a vague concept they want visualized, (3) User mentions "3b1b style" or "explain like 3Blue1Brown", (4) User wants to plan a Manim video or animation sequence, (5) User asks to "compose" or "plan" a math/science visualization. Transforms vague video ideas into detailed scene-by-scene plans (scenes.md). Conducts research, asks clarifying questions about audience/scope/focus, and outputs comprehensive scene specifications ready for implementation with ManimCE or ManimGL. Use this BEFORE writing any Manim code. This skill plans the video; use manimce-best-practices or manimgl-best-practices for implementation.

中文简介正在准备中。当前显示原文说明。

Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.

中文简介正在准备中。当前显示原文说明。

Transcribe audio/video files via MLX Whisper (Apple Silicon). Usage: /transcribe path/to/file.mp3

中文简介正在准备中。当前显示原文说明。

Preview a Remotion video

中文简介正在准备中。当前显示原文说明。

Export a Remotion video

中文简介正在准备中。当前显示原文说明。

Create a new Remotion video

中文简介正在准备中。当前显示原文说明。

西瓜视频（Xigua）公开视频数据查询与内容分析 skill，通过 MaxHub API 查询视频详情、作者、评论、搜索、推荐和相关视频。适合长视频/中视频选题、作者画像、互动分析、热点跟踪和内容复盘。默认 read-only；agent 应按 recipes 匹配视频详情、评论、作者、搜索等意图，并通过字段流传递 item_id/video_id/user_id。所有请求发送到 https://www.aconfig.cn。

中文简介正在准备中。当前显示原文说明。

今日头条（Toutiao）内容数据查询与资讯分析 skill，通过 MaxHub API 查询文章/视频详情、评论、用户/媒体号、搜索、热榜和推荐内容。适合资讯选题、舆情监控、内容互动分析、媒体号画像和热点跟踪。默认 read-only；agent 应按 recipes 匹配文章、评论、搜索、热榜等意图，并用字段流字典传递 item_id/group_id/user_id 等参数。所有请求发送到 https://www.aconfig.cn。

中文简介正在准备中。当前显示原文说明。

微博（Weibo）公开社交数据查询与热点分析 skill，通过 MaxHub API 查询微博内容、评论、转发、用户资料、粉丝/关注、搜索、热搜、话题和榜单。适合舆情监测、热点追踪、KOL 画像、内容传播分析和竞品研究。默认 read-only；agent 应优先使用 recipes 串联搜索→微博详情→评论/用户画像等流程，避免自行猜测 mid/uid/container_id 参数。所有请求发送到 https://www.aconfig.cn。

中文简介正在准备中。当前显示原文说明。

小红书（Xiaohongshu/RED）公开笔记与用户数据分析 skill，通过 MaxHub API 查询笔记详情、评论、用户资料、搜索、话题、商品/种草内容、推荐流与蒲公英（PGY）创作者商业化数据。适合品牌种草分析、KOL 画像、内容选题、竞品监控、评论洞察与蒲公英博主选号。默认 read-only；PGY 域为 POST 写入式查询（high risk），调用前需用户显式确认；agent 应按 recipes 选择笔记/用户/搜索/评论/PGY 链路，使用 note_id/user_id/keyword/brand_user_id 等字段流传参，并避免采集超出授权的个人数据。所有请求发送到 https://www.aconfig.cn。

中文简介正在准备中。当前显示原文说明。