Media AI Skills

Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano (豆包) ASR; other languages (Spanish,…

The Flutter v6 UI Kit widget catalog — which drop-in widgets exist, which barrel each comes from, and how to compose or swap them (conversations, messages, users, groups, threads, calling, bubbles).…

Local text-to-speech via sherpa-onnx (offline, no cloud)

When the user wants to create developer YouTube content, technical screencasts, or video tutorials. Trigger phrases include "YouTube," "developer video," "screencast," "video tutorial," "live coding,"…

Read your YouTube audience from the comments: pull commenters and top comments on any video, surface recurring questions and themes (content ideas), repeat commenters (superfans), sentiment, and which…

Publish long-form videos to YouTube from a local folder. Drop your edited videos into the watch folder and this skill uploads them with AI-generated titles, descriptions, and tags. Trigger when asked…

Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).

Use for live stream and VOD ingestion pipelines, including YouTube, Twitch, uploads, capture jobs, queues, transcription, clip generation, media storage, retries, idempotent workers, consent,…

How Pi accesses the web — search, fetch URLs/PDFs/YouTube/GitHub, and retrieve current information. Use whenever a task needs facts, docs, current/latest info, news, prices, versions, or content from…

Apply iconic resemblance — designing or choosing icons that visually look like what they represent. Use when picking icons for actions or objects with strong visual referents (camera, clock, lock,…

Pixel art w/ era palettes (NES, Game Boy, PICO-8).

HyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, validate, inspect, layout, snapshot, preview, play, render, publish, lambda, doctor, browser, info,…

Develop examples for AI SDK functions. Use when creating, running, or modifying examples under examples/ai-functions/src to validate provider support, demonstrate features, or create test fixtures.

Produce a content calendar and a week of platform-specific copy from the account positioning, delivered as an Excel workbook plus a Markdown document

Internal deterministic consent gate for meta-short-drama. Normalizes draft review and post-revision confirmation replies, and fails closed before external image/video generation.

This skill helps users automatically extract structured channel data from YouTube search results via BrowserAct API. Agent should proactively apply this skill when users express needs like finding…

Pluggable, category-toggleable debug logging for TanStack AI activities. Toggle with `debug: true | false | DebugConfig` on chat(), summarize(), generateImage(), generateSpeech(),…

Pixel art w/ era palettes (NES, Game Boy, PICO-8).

Write YouTube chapters from a transcript, validated against YouTube's own rules so they actually render. Use for "add chapters", "timestamps", "break this video into sections".

Use when the user asks about Vibe Motion, motion graphics, kinetic typography, animated text, brand animations, logo animations, infographic animation, presentation animation, data-driven video, or…

Analyzes video hooks and scripts using Meta's TRIBE v2 fMRI model, providing a neuro-marketing breakdown of scroll-stopping power and retention risk.

Download or open videos and recover platform captions, audio transcripts, keyframes, screen text, visual facts, and editing observations as a plain multimodal_transcript.md. Use for Douyin, Bilibili,…

把长视频按 Agent 选择的原片区间剪成短片。作为两阶段创作流程中的剪辑环节，读取 clip_plan.json 与源视频， 输出 edited_source.mp4；随后 Agent 按输出时间线写 narration.json。支持单视频与多视频（sources manifest）拼剪， 本工具不读取、不映射旁白。 触发词：视频剪辑、剪辑式解说、video cut、clip plan、拼剪。

Create a persistent HeyGen avatar — a reusable face + voice identity for the agent, the user, or any named character — powered by HeyGen Avatar V technology. Prompt-based creation by default…

Yuval Avidani's YUV.AI brand and design system. Apply ONLY when YUV.AI-branded output is requested — presentations, decks, keynotes, portfolio, brand site, profile, speaker bio, brand assets, or any…

从视频片段裁剪缩放变速以制作GIF动态表情

Use when user asks to synthesize speech, convert text to audio, or read text aloud. 讯飞超拟人语音合成 - 支持文本转语音、语音合成（发音人/语速/语调/音量/输出格式）。大模型语音合成技能。语音合成, 文字转语音, 超拟人, TTS.

Download and process YouTube content for research. Use when: downloading competitor videos for analysis; extracting audio for podcasts; getting transcripts for content repurposing; archiving webinars;…

Use when the user has an SRT (or transcript text) in one language and wants it translated to another, with punctuation-bounded re-segmentation so cues end at real sentence breaks. Simplified Chinese…

地图动效视频：用高德地图（真实路线、行政区边界、标准/卫星瓦片底图）做旅行与解说视频里的地图动画，出竖屏/横屏 MP4 和…

Analyzes PHP code for command injection vulnerabilities. Detects shell_exec, exec, system, passthru with user input, missing escapeshellarg/escapeshellcmd.

Product Hunt 发布剧本。从 30x 日冠经验提炼的完整 GTM 流程：T-14 预热 → T-0 发布日 → T+7 post-launch。 覆盖 hunter 选择、maker comment、community seeding、评论节奏、防踩雷。当用户说"我要发 PH"、 "Product Hunt 准备"、"找 hunter"、"写 maker comment"时调用。

Audit and rewrite a YouTube channel end-to-end for 2026: name and @handle, banner (2560x1440 with the 1235x338 mobile/TV safe area), profile picture, About plus searchable keywords, trailer for…

End-to-end longform video cloning pipeline. Downloads YouTube video, transcribes, generates HeyGen avatar chunks, detects PIP vs fullscreen vs noface segments, precisely locates webcam bubbles,…

Generate videos through an available or configured video backend using structured prompts, explicit output paths, capability checks, and verified delivery.

Use when David is choosing the next YouTube video idea. Helps evaluate candidates, apply David's principles, and reach a decision.

Paid advertising on Google, Meta, LinkedIn with campaign structure and bidding strategies.

Add subtitles, captions, narration cues, or zoom to a proof video or PR recording using repo-local capture helpers and a system ffmpeg renderer.

The HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned…

This skill helps users extract structured video list data and comment data from YouTube using the BrowserAct API. The Agent should proactively apply this skill when users request searching for YouTube…

图片相册 → 视频：把一组图片做成带 Ken Burns 缓慢缩放、图间转场、背景音乐和逐图字幕的视频，自动适配平台画幅（竖版/方形/横版）。当用户说 图片转视频、图片做成视频、相册视频、照片视频、一组图生成视频、图片轮播视频、幻灯片视频、把这几张图做成短视频、图集成片、卡点图片视频 时使用。基于 shared/scripts/slideshow.py 确定性 ffmpeg 封装。与…

Use when evaluating markets through Li Bei's macro hedge lens: regime identification, trend + contrarian timing, position management by conviction, and risk control for drawdown.

演讲与分享教练。基于Patrick Winston（MIT AI教授）的How to Speak方法论，帮助准备线下培训、技术分享、B站教程视频等演讲场景。当用户提到"演讲"、"分享"、"培训"、"讲课"、"PPT演讲"、"开场"、"结尾"、"如何讲"、"演讲结构"时使用此技能。

Draft replies to YouTube comments in the creator's voice, triaged by which ones are worth answering. Use for "reply to my comments", "handle the comment section", "someone asked X", or a pasted…

Translate or audit the values in a Video.js locale pack. Use when a key needs values, en.ts copy changes underneath a pack, or one pack needs an audit.

Expert WCAG (Web Content Accessibility Guidelines) advisor covering WCAG 2.0, 2.1, and 2.2 — the W3C international accessibility standards. Use this skill whenever a user asks about WCAG success…

Upscale and restore video in ComfyUI. Both the quick local path (per-frame ESRGAN like 4x_foolhardy_Remacri via ImageUpscaleWithModel + 4x→2x supersample, with its temporal-flicker tradeoff) and…

Use when the user is unsure which Higgsfield workspace fits their task, needs to decide between Cinema Studio / Lipsync Studio / Draw-to-Video / Viral Hub presets / Click to Ad / Higgsfield Audio…

Generate high-potential viral title candidates for content across WeChat public account articles, X/Twitter posts, YouTube videos, Bilibili videos, and similar content platforms. Use when the user…

Generates 150-750+ ad variations using Alex Hormozi's combinatorial Hook x Meat x CTA framework. Triggers on requests to create ads, ad copy, ad scripts, marketing creatives, video ad scripts, ad…

从输入视频生成中文解说成片或原声剧情短片。用户提供 .mp4 / .mov / .mkv / .webm，并要求剪辑、添加旁白、 配音、总结、短剧/电视剧/电影/纪录片/科普解说时使用。负责编排 video-* 技能链：视频理解 → Agent 制定故事与视听方案 → 剪辑 → 配音 → 合成。触发词：视频解说、视频旁白、生成解说、 视频 recap、video…