Video & Animation

Turn an idea into a reel plan: verify it against its source, write the script in the creator's voice with proven hooks and Alex Hormozi's model, give a viral score, then suggest the two or three best edit styles before any editing. Use when they type /reel-idea or send an idea, product, service, customer question or topic for a reel («یه ایده دارم», «این رو ریل کنیم»).

Edit one of the owner's reels in the Pop comic style («پاپ»). Use when they type /pop, ask for the pop comic look, or pick it from /reel-style. Builds a 9:16 HyperFrames motion edit on their own take and SRT, mostly full-screen b-roll with their face only in short windows.

Edit one of the owner's reels in the Neon night style («نئون»). Use when they type /neon, ask for the neon night look, or pick it from /reel-style. Builds a 9:16 HyperFrames motion edit on their own take and SRT, mostly full-screen b-roll with their face only in short windows.

Edit one of the owner's reels in the Receipt printer style («رسید»). Use when they type /receipt, ask for the receipt printer look, or pick it from /reel-style. Builds a 9:16 HyperFrames motion edit on their own take and SRT, mostly full-screen b-roll with their face only in short windows.

Plan the coming week (or month) of reels, stories and channel posts for this page from its business playbook, its analytics and its filming days, plus the shot list to film. Use when they type /content-plan, ask «برنامه‌ی این هفته», «چی بسازیم؟», «ایده بده», or after /analytics.

Edit one of the owner's reels in the Clean style («کلین»). Use when they type /clean, ask for the clean look, or pick it from /reel-style. Builds a 9:16 HyperFrames motion edit on their own take and SRT, mostly full-screen b-roll with their face only in short windows.

Edits a raw long-form YouTube recording (screen recording export, camera file, or either plus a separate mic) into a publish-ready video automatically, like Descript on autopilot: transcribes with word timestamps, removes retakes and keeps the last take, tightens dead space while keeping silent on-screen action (speeding up long waits), masters the voice to -14 LUFS / -1.5 dBTP with no music bed, re-transcribes the FINAL render for an every-word SRT (optional burned-in captions), drafts chapters, titles and a description, and fails loudly on QA gates (words, A/V sync, caption sync per chapter, caption coverage, loudness) plus contact sheets you look at. Use when someone says edit this long-form, clean up my recording, cut the retakes and dead space, process the long-form inbox, or descript this. Needs Claude Code with ffmpeg, whisper.cpp and Python 3.

Turns notes, voice-note transcripts and half ideas into Reel, TikTok and YouTube scripts in the creator's own voice: ranks an idea bank, writes ten hooks per idea, writes the script at the right length, rewrites anything that sounds like AI using transcripts of the creator's past videos, and fact-checks every claim with a source and date. Use when someone wants a video script, hooks, a ranked list of what to film, a voice pass, a claims check, or a record sheet to read from while filming.

Turns one podcast episode transcript into a week of written content: an Episode Prep agent that checks the transcript and speaker names, a Clip Spotter that picks the best short-clip moments with exact timestamps and hooks for an editor to cut, a Show Notes Writer that writes show notes and chapter markers, a Repurpose Writer that turns the big ideas into a newsletter, a LinkedIn post and Instagram captions, and an Episode Planner that spreads it all over the week. Works from a transcript the user supplies or exports from their transcription tool. It does not edit audio or video and does not cut clips. Use when a podcaster asks for show notes, chapters, clip timestamps, or posts from an episode, or says \"repurpose this episode\". Drafts only; never posts.

Find and use pictures, video, music, sound effects, icons, illustrations, emoji, fonts and maps that the brand may legally use in posts and ads, and keep a record of each licence. Use when they type /assets, need b-roll, a photo, a background track, an icon or an illustration, ask «عکس از کجا بیارم», «موزیک بدون کپی‌رایت», "royalty-free", "stock video", or before using any file they did not make themselves.

Make a 1280x720 YouTube thumbnail (or a banner/cover) that reads at phone size: a text-free background plate (generated or from a real frame), a real cutout of the person, 1 to 3 words in tight colour blocks, an official logo, composed by a script that checks overlaps and frame edges and renders the 320px and 168px views you must look at. Use when asked for a thumbnail, cover, banner, 'make this clickable', or to fix a thumbnail that looks cluttered or small.

Turns one raw talking-head take into a finished 1080x1920 vertical reel in Claude Code with free local tools (ffmpeg, whisper.cpp, headless Playwright): transcribes, keeps the last take of repeated lines, cuts pauses, captions every word, adds real screenshots and official logos, and runs measured QA gates. Use when someone wants a raw phone take edited into a Reel, TikTok or Short, retakes and silences cut, word-by-word captions, or a finished video checked. In Claude.ai it only produces a cut list, shot plan and .srt from a pasted transcript.

Make an Instagram carousel (1080×1350, up to 20 slides) in the brand from one of 10 templates (tips, steps, myth-fact, before-after, price-menu, faq, comparison, testimonial, checklist, showcase), written in the brand voice with real facts, rendered to PNGs. Use when they type /carousel, ask for a carousel, a post with slides, «کروسل», «اسلاید», "Karussell", "carrousel".

Turn a raw talking-head take into a dynamically edited 1080x1920 reel: full-face, full-graphic and split layouts that switch every 2 to 5 seconds, real UI and official-logo panels, captions on every word timed by Whisper, voice plus synthesised SFX (no music bed) mastered to -14 LUFS, and hard QA gates (caption sync on the final render, A/V length, loudness, colour, framing, contact sheet, claims). Also covers writing the script so it does not read as AI. Use when asked to 'edit this reel', 'make it look edited', 'add captions / dynamic layout / graphics', or 'write a reel script'.

Reviews and rewrites a video script (YouTube long-form, a short, or a talking-head reel) so it sounds like one person talking to one friend and holds attention: kills forced analogies and presenter phrases, fixes framing, checks hooks, open loops and re-engagement beats, and suggests titles. Use when someone says fix this script, polish my script, make it sound like me, tighten this before I film, or asks for a hook or title for a video. Returns the rewritten script plus a short change log.

Edit one of the owner's reels in the Neo-brutal style («بروتال»). Use when they type /brutal, ask for the neo-brutal look, or pick it from /reel-style. Builds a 9:16 HyperFrames motion edit on their own take and SRT, mostly full-screen b-roll with their face only in short windows.

Burn subtitles into a finished vertical video in the brand font, inside Instagram's safe zone, from an SRT, the kit's words.json or WhisperX output; styles pill, outline, brand colours or word-by-word highlight; right-to-left for Persian and Arabic; optional proofreading. Use when they type /captions, ask for subtitles, «زیرنویس», «کپشن روی ویدیو», "Untertitel", "sous-titres", "sottotitoli", "altyazı".

Edit one of the owner's reels in the Chalkboard style («تخته»). Use when they type /chalk, ask for the chalkboard look, or pick it from /reel-style. Builds a 9:16 HyperFrames motion edit on their own take and SRT, mostly full-screen b-roll with their face only in short windows.

Turns one published long-form video or podcast transcript into up to thirty pieces: 10 clips with new hooks and exact timestamps, 8 X posts, 4 LinkedIn posts, 3 carousels, 2 threads, a newsletter, a community post and a blog post, laid out on a two-week plan, all built only from what was said. In Claude Code it also cuts, reframes and captions the clips with ffmpeg. Use when someone wants to repurpose a long video, find clips, or write social posts from a transcript. Never posts or schedules.

Build dark, cinematic, awwwards-style landing pages with seamless scroll choreography — endless/infinite scroll loops, pinned image-morph galleries, book page-flip feature sections, full-page book sites, cross-dissolve scene transitions, unified AI-generated imagery, film-slate section markers. Use when the user asks for an "endless scroll", "infinite scroll", "seamless scroll", "cinematic", "movie-like", "page-flip", "flipbook", "book landing page", "book-style scroll", "morphing images" landing page, or references sites like activetheory.net, or complains that an existing scroll experience feels disjointed ("sections don't flow", "images feel unrelated"). Stack: React 19 + Vite + Tailwind + GSAP ScrollTrigger + Lenis.

Generate images and videos with Wan27, discover available models, estimate credit costs, and retrieve generation results through its MCP tools or CLI. Use when the user chooses Wan27 or wan2-7.io for media creation or task tracking.

Shared M1 social-content workflow for HL, Beauty, RU and other configured channels, extending verified content through 9:16/4:5 image creation and Canva Image to Video Custom animation prompts derived strictly from the finished image.

Research and create original, monetization-aware, faceless English YouTube health videos for adults 50+/60+, including topic validation, evidence research, titles, thumbnails, 15–20 minute scripts, retention, B-roll, fact-checking, descriptions, and originality checks.

Build a Seedance 2.0 brand, product, website, app, shop, or personal-project promo from verified assets and claims. Use when the user needs a truthful 4–15 second reel with a clear hook, product proof, controlled typography, camera, sound, CTA, and provenance-aware asset roles; not for inventing claims or imitating unavailable brand marks.