Use when generating hooks, headlines, titles, and scroll-stopping openers for content. Also use when analyzing viral posts, Reels, TikToks, YouTube Shorts, or successful social examples to extract reusable hook patterns and improve hook guidance.

Use when judging content quality OR editing/improving existing copy: shareability, readability, voice, cuttability, angle, copy sweeps.

Use when a first draft is complete and all Phase 1 gates are done: topic selected (seo-research), title approved (hooks), outline approved (outline-generator), draft written (writer). Runs autonomous diagnosis-prescribe-rewrite loop before Substack.

Write or improve marketing copy for any surface: pages, ads, app stores, landing pages, TikTok/Meta scripts, push notifications, UGC. Combines page copy frameworks with direct response principles.

Use when building content strategy: hooks, angles, and ideas from what's trending now. Covers organic and paid creative across TikTok, X, YouTube, Meta, LinkedIn.

Orchestrator for the 3-article content pipeline — runs research phase, spawns parallel article sub-agents, creates Typefully drafts. Use when running the full content pipeline (usually via cron at 3am).

Download audio/video from YouTube and other sites using yt-dlp. Use when the user asks to download music, songs, albums, podcasts, or video from YouTube or similar platforms. Triggers on 'download song', 'get mp3', 'yt-dlp', 'youtube download', 'rip audio'.

Generate high-CTR YouTube titles and thumbnail concepts using 119 proven frameworks ranked by performance score. Use when creating YouTube titles, optimizing video titles for CTR, generating thumbnail text, A/B testing title variations, or pairing titles with complementary thumbnails. Covers framework fitting method, universalization strategy, complementarity principle, and psychological trigger analysis.

Write retention-optimized long-form YouTube scripts through a checkpoint workflow (research, hook, structure, body, editing). Use when asked to "write a YouTube script", "YouTube video outline", "long-form video script", "improve video retention", "structure a YouTube video", or when turning raw ideas/transcripts/notes into a compelling video script. Covers hook formats, 7 story structures, rehook techniques, editing audits, and outro binge loops.

Fetch YouTube video transcripts and transform them into structured content (chapters, summaries, threads, blog posts). Use when the user shares a YouTube URL or video link, asks to summarize a video, requests a transcript, or wants to extract and reformat content from any YouTube video.

Generate structured scene-by-scene video scripts with production metadata (visuals, audio, sources, transitions, captions) ready to feed into the video-production pipeline (Sora, Kling, ElevenLabs, InfiniteTalk, Remotion, stock-footage, video-editor). Use when asked to "write a video script", "script for TikTok", "video outline", "plan a video", "storyboard", "scene breakdown", "video concept", "content brief for video", "shooting script", or whenever the video-production pipeline needs a structured script before production begins. Also trigger for "Reels script", "Shorts script", "YouTube script", "video idea with scenes", or any request that implies breaking a video concept into timed scenes with production directions.

Programmatic video editing via ffmpeg CLI. Handles trimming clips, merging/concatenating videos, overlays (picture-in-picture, watermarks, logos), crossfade transitions between clips, speed ramping (speed up/slow motion), cropping to aspect ratios (16:9 to 9:16), scaling/resizing, adding or replacing audio tracks, fade in/out effects, text overlays (drawtext), rotation, looping clips, extracting frames, GIF creation, audio ducking (sidechaincompress), volume normalization (loudnorm), mixing audio tracks (amix), and audio fades. Use whenever asked to edit video, trim clip, merge videos, add music to video, overlay, picture in picture, video transition, speed up video, slow motion, crop video, resize video, audio ducking, mix audio tracks, normalize audio, create GIF from video, extract frames, loop a clip, add text to video, fade video, or any ffmpeg-based media manipulation. Also use when assembling finished videos from clips, audio, and overlays for content creation pipelines.

Generate video cover frames and thumbnails for YouTube, TikTok, Reels, and social media. Use when asked for a video thumbnail, cover frame, YouTube thumbnail, or to extract a still from a video.

Use when generate, remix, and manage Sora AI videos.

Use when create animated marketing videos with Remotion (renders to MP4).

Generate AI videos with Kling 3.0 using cinematic directing techniques. Supports direct API execution (text-to-video, image-to-video, multi-shot, elements), Higgsfield browser automation, and prompt engineering.

Generate a talking avatar video from a character image + audio file using InfiniteTalk via Fal.ai. Lip-syncs the audio to the character with full-body animation.

Use when generate interactive SVG animations via Gemini.

Generate voiceover audio from a script using ElevenLabs v3 via Fal.ai. Outputs an MP3 file for use with InfiniteTalk or standalone audio.

Build, preview, and render videos with Editframe, the HTML/CSS/React video composition tool. Use this whenever the user mentions Editframe, wants code-generated videos, asks to scaffold an Editframe project, build an HTML/CSS video composition, render MP4 locally, use ef-timegroup/ef-video/ef-audio/ef-text components, or automate video generation with Node.js and FFmpeg.

Create product demo videos by automating browser interactions and capturing frames. Use when the user wants to record a demo, walkthrough, product showcase, or interactive video of a web application. Supports Playwright CDP screencast for high-quality capture and FFmpeg for video encoding.

Find the funniest moments in a video, cut them as standalone clips, optionally reformat 16:9 → 9:16 (face-pan or split-screen), and burn opus-style word-by-word captions. Use when the user mentions "clipify," "cut clips from this video," "make shorts from this," "find funny moments," "reframe to 9:16," "vertical clips," or pastes a video file path and wants social-ready cuts.

Create and manage consistent AI video characters — define the persona, generate the portrait with Nano Banana, and store the config for reuse across all videos in the series.

Use when create browser-based motion graphics with Framer Motion, GSAP, and Tailwind.