Video & Animation

Translate and dub existing videos into multiple languages using HeyGen.

Agent skill 'google-agents-cli-scaffold' from google/agents-cli.

Run one authorized Neural Labs local-business prospect concept from bounded city discovery through an original cinematic site, browser QA, optional demo-pi publication, and preference-aware automation notification.

Antigravity AI Agent Skill for ffmpeg optimization — encoding ladders, compression, and delivery-ready exports.

Build video content with Remotion in React. Use for programmatic video creation, animated sequences, data-driven video rendering.

Use when creating, brainstorming, producing, or scheduling social media content (photos, videos, reels, shorts, captions, and campaign packs) for Jack Howlin using Kie.ai (Seedream 5 Pro, Seedance 2.5) and the canonical Jack Core Set.

Remotion Map animation knowledge

Transcribing, displaying and animating captions

A comprehensive skill for extracting chapter indices from tutorial videos using FFmpeg audio extraction, OpenAI Whisper ASR transcription with word-level timestamps, and semantic chapter alignment via fuzzy string matching.

Content, animation and effects best practices

Summon Adam Neumann into this chat. Building one of the most spectacular narrative-driven valuations in startup history, and the cautionary tale of what happens when the story outruns the numbers. Use when the user types /adam-neumann, says "summon Adam Neumann" or "ask Adam Neumann", or wants Adam Neumann on vision, mission, storytelling, fundraising, blitzscaling, community, brand, charisma, real estate, hubris, unit economics, founder mode, narrative, S-1, comeback. Routes every answer throug

Image handler for the Hugo blog newsletter. Adds an image URL to the target newsletter post's Bonus → Images with a detected label. For Substack-hosted images it finds the source post (ByteByteGo and other configured publications) via RSS then sitemap, using the figure caption or post title as the label; for other sites it is best-effort; if no label is found it asks you to type one. Normally invoked by the mt-add-url meta skill after classification, but can be used directly for a known image UR

Search Remotion documentation

Generate complete TikTok / Douyin(抖音) / YouTube Shorts / Reels short videos from a one-line brief, end to end: script writing, free stock footage & image download, TTS voiceover (Chinese & English), word-level karaoke captions, background music, and ffmpeg composition into a finished 1080x1920 MP4. Use when the user asks to create, make, or generate a short video (短视频/抖音视频/TikTok video) on any topic.

飞书妙记：搜索妙记、查看妙记基础信息、下载/上传音视频、读取或编辑妙记的产物内容、改标题、替换说话人/关键词、申请妙记查看/编辑权限。当给出minute_token、本地音视频文件，要查/改/转妙记产物，或用户明确要主动申请妙记权限时使用；本地音视频转纪要/逐字稿优先走本 skill，不要用 ffmpeg/whisper 本地转写。不负责：获取会议关联妙记，或仅按自然语言标题定位纪要

Record PsyNet participant-flow visual evidence with Playwright-driven interaction, screenshots, and ffmpeg screen/audio capture. Use when collecting participant evidence, creating participant.mp4, or documenting participant-facing behavior.

Agent 2 of the video editing pipeline. Finds and removes spoken mistakes — stutters, repeated words, false starts, and retakes (re-recorded lines) — from a talking-head recording. Use after cut-silences, when asked to cut mistakes, remove stutters / repeats / filler restarts, clean up flubs, or keep the best take. Works review-gated: it proposes every cut with context and a reason for approval, then renders only the approved cuts via ffmpeg. Requires a word-level transcript.

Create a new Remotion video

Agent 1 of the video editing pipeline. Removes silences and dead air from a talking-head recording. Use when asked to cut silences, trim pauses, remove dead air / gaps, or tighten the pacing of a raw video, given a word-level transcript. Produces an edit list (EDL), a re-timed transcript for downstream agents, and optionally the cut video via ffmpeg. Does NOT cut mistakes, repeats, or false starts — that is the cut-mistakes agent.

Build a short (~15-40s) animated "story video" as a single self-contained HTML file — kinetic typography on a cinematic ground, with the brand logo and a royalty-free music track embedded (trimmed + faded to the cut, beat-synced). Use when the user wants a promo / brand / campaign / launch / explainer / "sizzle" video, a video for an email or landing page, or says "make a video / a short film / a story cut / an animated intro." Produces a self-contained playable HTML, and renders it to a real MP

Process video, audio, and images with FFmpeg, ImageMagick, and RMBG. Use when converting, compressing, resizing media files, or removing backgrounds. NOT for UI image assets (use design-system) or prompt-based generation (use ai-artist).

Generate a ~45–60 s vertical short (YouTube Shorts / Reels / X) for a Feel Your Protocol exploration — draft content / playbook / narration from `canonical.ts` (coreQuestion is the anchor), run QA, synthesize voice with ElevenLabs, record with Playwright, mux with ffmpeg. Use for round-trip phase 5, or when the user asks for a short / video for EIP-xxxx.

Use for any FFmpeg/ffprobe work in the video pipeline — probing a media file, cutting/trimming/concatenating, retiming, scaling for YouTube 16:9 or Shorts/Reels 9:16, thumbnails, NVENC or CPU encoding choices, loudness normalization (-14/-16 LUFS), silence/dead-air removal, ducking music, burning or muxing subtitles, drawtext lower thirds, alpha overlays, GIF/WebP, image sequences, stream mapping/metadata/timecode, ffmpeg quoting in PowerShell/cmd/Git Bash, progress and exit-code handling, and v

FFmpeg media processing skill — 40 tools for clipping, stitching, noise removal, subtitles, transcoding. No cloud API required.