Guides for AI video

For AI agents: find the right skill in one call — curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>" returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the how-to page.

Know-how your agent reads before it works: how to write a script, storyboard, edit and caption, and how to use Remotion, HyperFrames, GSAP, Three.js and FFmpeg.

Guides is the word 5.0% of tweets about making video use for this kind of thing (“guide / tutorial”). Every card here is an agent skill: one install command for Claude Code, Codex, Cursor, OpenClaw or Gemini CLI.

Editing & clips (24)

• Short-form FFmpeg cookbook: copyable commands for Reels — varg: Footage into a 9:16 MP4 with FFmpeg: crop to vertical, burn captions, trim and join, music under the voice.
• Splice AI clips into a video with FFmpeg — varg, beta: Splice generated clips into an original video with ffmpeg without A/V drift: absolute trims, one audio track.
• DaVinci Resolve MCP — Samuel Gursky: The most-starred Resolve MCP: drive timelines, media pool, color, Fusion and render from any MCP client.
• Unofficial DaVinci MCP — wassermanproductions: Resolve MCP with live Studio control plus FCPXML/LUT workflows for the free edition and beat-aware cuts.
• Adobe Premiere Pro MCP (premiere-mcp.com) — Het Patel: Premiere Pro MCP with a local CEP bridge, Claude Code and Codex plugins, and search-then-invoke tools.
• Premiere Pro MCP (premiere-pro-mcp.com) — leancoderkavy: Independent local-first Premiere Pro MCP over a CEP bridge for Claude, Codex and Cursor.
• ae-mcp (After Effects MCP) — JUNKDOGE-JOE: Adobe After Effects automation via MCP: 16 tools for editing comps, previews, recovery and reusable work.
• FCP MCP Server (FCPXML) — DareDev256: Read, edit and generate real Final Cut Pro timelines as FCPXML: cut detection, markers, roles, transcript edits.
• SpliceKit — Elliott Tate: Patched Final Cut Pro with a command palette and an MCP server of ~200 tools that talk to FCP's runtime.
• pyJianYingDraft — GuanYixuan: Python library that writes JianYing (CapCut China) drafts: tracks, clips, text, effects, transitions, export.
• pyCapCut — GuanYixuan: International CapCut version of pyJianYingDraft: generate CapCut drafts in Python for automated edits.
• JianYing MCP — hey-jian-wei: MCP server that creates JianYing drafts: tracks, clips, transitions, filters, masks, keyframes, audio fades.
• OpenTimelineIO — Academy Software Foundation: Academy Software Foundation's interchange format and API for editorial timelines (EDL, FCPXML, AAF adapters).
• Kinocut — Kyanite Labs: Guardrailed local video editing MCP (formerly mcp-video): ~200 FFmpeg tools, quality gates, Shorts repurposing.
• ffmpeg-mcp-lite — kevinwatt: Small FFmpeg MCP: convert, compress, trim, extract audio and add subtitles, installable with uvx.
• ffmpeg-mcp (video-creator) — video-creator: FFmpeg MCP for local video search, trimming, concatenation, overlays and playback through dialogue.
• Video Jungle MCP (video-editing-mcp) — Kirk Kaiser: MCP for Video Jungle: upload, analyze and search footage, then generate edits from the results.
• AI YouTube Shorts Generator — Anil-matcha: Open-source Opus Clip alternative: LLM finds highlights in long videos and renders 9:16 shorts with face crop.
• claude-shorts — AgriciDaniel: Claude Code skill that scores segments of a long video, snaps cuts to words and renders captioned 9:16 clips.
• SupoClip — FujiwaraChoki: Self-hostable OpusClip alternative: long video in, captioned vertical clips out, no watermark.
• ClipsAI — Clips AI: Python library that segments long transcripts into clips and resizes video to 9:16 around the speaker.
• OpenMontage Sound Design Rules — Calesthio: Mix targets an agent can check: dialogue −16 to −14 LUFS, music 18–20 dB under speech, whoosh timing, true-peak limits.
• OpenMontage Visual QA — Calesthio: Self-review after render: frames at each cut, codec and duration checks, captions over faces, broken transitions.
• OpenMontage B-roll Planning — Calesthio: Plans b-roll from a script: stock vs generated, search queries per beat, and how to judge a clip before using it.

Tools & renderers (17)

• Templates Gallery Ops — varg, beta: Internal runbook for the varg app Templates gallery: publish renders, preview clips, frame-0 posters, shelves.
• HyperFrames CLI — HeyGen: Drive the HyperFrames CLI: scaffold, check, preview, snapshot, edit the timeline, render locally or in the cloud.
• HyperFrames Registry — HeyGen: Pull any of ~450 ready-made blocks into a video as editable source: transitions, titles, captions, charts, 3D.
• HyperFrames Media Use — HeyGen: Find or make every asset a video needs: music, SFX, voiceover, images, logos, avatars, transcripts, grades.
• Remotion to HyperFrames — HeyGen: Port Remotion, Lottie, Three.js, p5 or canvas animations into HyperFrames and verify them frame by frame.
• Remotion Best Practices — Remotion: Make videos in React with Remotion: the router that loads the right Remotion skill for each step.
• Remotion Docs — Remotion: Search the Remotion docs and pull any page as Markdown instead of guessing at APIs.
• Remotion Interactivity — Remotion: Structure Remotion markup so every element can be edited visually in Remotion Studio.
• Remotion Multimedia — Remotion: Read media metadata in Remotion with Mediabunny: audio duration, video dimensions and length.
• Remotion Render — Remotion: Render a Remotion composition to a video file or a still, including transparent video.
• Remotion SaaS — Remotion: Build a video app or SaaS on Remotion: embed the Player, choose a framework, decide how to render.
• Remotion Studio — Remotion: Launch Remotion Studio to preview and scrub a composition in the browser before rendering.
• Remotion Upgrade — Remotion: Upgrade Remotion and every @remotion/* package to one matching version, skills included.
• fal Workflow — fal: Author fal workflow JSON that chains models, or orchestrate the same pipeline locally with genmedia.
• fal genmedia Workflow — fal: Design multi-step media pipelines with genmedia: generate, edit, add audio and subtitles, batch, deliver.
• PixiJS — PixiJS: Build fast 2D WebGL/WebGPU graphics with PixiJS v8; routes each task to the right PixiJS skill.
• Runway Workflows — Runway: Author, validate and run multi-step Runway workflow graphs from chat through Runway's MCP tools.

Animation & motion graphics (10)

• Remotion Markup — Remotion: Write Remotion markup that animates well: timing, transitions, motion blur, effects, audio, fonts and 3D.
• Motion AI Kit — Motion: Write production-grade UI animation with Motion or CSS: best practices, docs search, springs, perf audits.
• Motion Design — LottieFiles: Animate with intent: timing, easing, choreography and Disney principles for UI and motion graphics.
• dotLottie Web — LottieFiles: Ship Lottie animations on the web with dotLottie: package choice, workers, state machines, theming, slots.
• LottieFiles Animation Review — LottieFiles, beta: Inspect, compare and diagnose animation renders with LottieFiles Creator's Engine tools (pre-release).
• LottieFiles Animation Workflows — LottieFiles, beta: Create, edit and export animation documents through LottieFiles Creator's Engine tools (pre-release).
• Rive — Rive: Know when to reach for Rive for interactive graphics and motion, then start from its CLI or runtime docs.
• GSAP Core — GSAP (GreenSock): Official GSAP core guide: to/from/fromTo tweens, eases, staggers, defaults and transforms for DOM and SVG motion.
• GSAP Plugins — GSAP (GreenSock): Official GSAP plugins guide, incl. SplitText chars/words/lines with masks and re-splitting once fonts load.
• GSAP Timeline — GSAP (GreenSock): Official GSAP timeline guide: position parameter, labels, nesting, defaults and time/progress seeking.

Cuts & pacing (8)

• SmartCut (capcut-ai-editor) — mrbuslov: MCP that reads CapCut auto-captions to cut silences and duplicate takes right inside your CapCut project.
• Auto-Editor — WyattBlue: CLI that cuts dead space by loudness or motion and exports MP4 or editor timelines; now also an agent skill.
• AutoCut — Mu Li: Edit video in a text editor: Whisper transcribes, you delete lines in Markdown, AutoCut cuts the video.
• Cut Video — Louise de Sadeleer: Claude Code skill that tightens long recordings with forced-aligned cuts, keeping laughs and comedic pauses.
• Videogrep — Sam Lavigne: Search spoken words across videos and auto-build supercuts of every match.
• PySceneDetect — Brandon Castellano: Find cuts, fades and scene changes in a video, then split it or export scene lists for the edit.
• video-editing-skill (Bash + FFmpeg) — 6missedcalls: Pure Bash skill for OpenClaw, Claude Code and Codex: trim, jump cut, captions, text overlay, speed.
• OpenMontage Silence Cutter & Auto Reframe — Calesthio: Automatic jump cuts from silencedetect, plus a face-tracked 16:9 → 9:16 reframe with a smoothed crop.

Captions & subtitles (7)

• Pretext Text Metrics — Yaniv Golan, beta: Measure and fit text without the DOM using pretext: auto-fit sizes, know line breaks before render, canvas/WebGL text.
• Chinese Font Selector — Songzhi-lab, beta: Pick Chinese fonts by license tier first (OFL, vendor-free, avoid), then by scene and mood, with Latin pairings.
• Transcribe Anything — Shawn Wang (swyx): Transcribe hours of audio or video with whisper, whisperX or cloud STT: word timestamps, speaker labels, SRT/VTT.
• FFmpeg Captions and Subtitles — Josiah Siegel: FFmpeg subtitle reference: burn SRT/ASS/VTT with libass, soft tracks, conversion, styling and FFmpeg 8's Whisper filter.
• Subtitle Translator — Matheus Castro: Agent-translated SRT/ASS subtitles in resumable batches that keep cue count, timing and ASS styling tags intact.
• WJS Translating Subtitles — Jian Shuo Wang: Translate an SRT to Chinese, English or another language and re-cut cues at real punctuation; bilingual SRTs too.
• WhisperX — Max Bain: Fast Whisper ASR with word-level timestamps and speaker diarization: the timing layer for captions and cuts.

Stories & short dramas (6)

• fal Storytelling — fal: Plan multi-shot stories: storyboards, shot lists, first-to-last-frame chains and continuity across scenes.
• Drama Skills (ZenStory) — ZenStory AI: Short-drama skills that beat a no-skill control in blind tests: script, assets, storyboard, keyframe and video prompts.
• Screenwriting Skills — Terry Jia: 26 screenwriting and dramaturgy skills, from story structure to writing in the style of Ozu, Chekhov or Succession.
• Emma Short-Drama Writing Skills — Emma Wang, beta: Short-drama writing kit (hooks, outlines, dialogue, trims, US localization) that beat a no-skill control in blind tests.
• Short Drama Skill Finder — Underleveled Builder: Picks short-drama and manju skills from a hand-checked list of 90+ projects by stage, video model and agent.
• AI Video Script — aguo333, beta: Turns a topic into a video script: shot list, per-shot image/video prompts and voiceover text

Backgrounds & shaders (6)

• PixiJS Blend Modes — PixiJS: Composite PixiJS v8 layers with add, multiply and screen, or advanced modes like overlay and color-burn.
• PixiJS Custom Rendering — PixiJS: Write custom shaders, uniforms and batchers for PixiJS v8 that run on both WebGL and WebGPU.
• PixiJS Filters — PixiJS: Add blur, displacement, color-matrix and custom GLSL/WGSL filters to PixiJS v8 scenes without killing FPS.
• PixiJS Meshes — PixiJS: Deform images with custom geometry in PixiJS v8: meshes, planes, ropes and 2.5D perspective corners.
• PixiJS Particles — PixiJS: Render thousands of lightweight particles in PixiJS v8 with ParticleContainer and dynamic properties.
• WebGPU Three.js TSL — Dan Greenheck, beta: TSL node materials, GPU compute, post-processing and WGSL for three.js WebGPURenderer, by the Three.js Roadmap author.

Dubbing & lip sync (5)

• VideoLingo — Huanshere: One-click subtitle cutting, translation, alignment and dubbing with Netflix-style subtitle rules.
• pyVideoTrans — jianchang512: Full video translation: ASR, subtitle translation, multi-voice dubbing and muxing, with a headless CLI.
• OpenCreator (formerly KrillinAI) — KrillinAI: Creator workspace on Codex CLI: download, translate, dub and edit video with reusable Skills and Agents.
• Sync. lipsync MCP — sync.: Official MCP for the sync. lipsync API: re-time mouths in existing footage to new or translated audio.
• OpenMontage Localization & Dub — Calesthio: Transcript-first translation of an existing video into subtitles, dubbed audio and optional lip-synced language variants

Images & thumbnails (5)

• PixiJS GIFs — PixiJS: Load, play and control animated GIFs inside a PixiJS v8 scene.
• Book Cover Design — inference.sh: Design book covers that fit their genre: typography rules, sizing, thumbnail tests and AI iterations.
• OG Image Design — inference.sh: Design Open Graph and social share images to platform specs, with text placement and branding.
• YouTube Thumbnail Design — inference.sh: Design YouTube thumbnails that read on a phone: dimensions, contrast, safe zones, text and faces.
• Social Media Carousel — inference.sh: Design swipeable carousels for Instagram, LinkedIn and X: slide structure, hooks, text hierarchy.

Explainers (4)

• HyperFrames — HeyGen: Turn HTML, CSS and seekable animation into deterministic MP4s: launch films, explainers, captions, title cards.
• Remotion Create — Remotion: Scaffold a new Remotion project and lay the video out as clips or scenes before writing any frames.
• Explainer Video Guide — inference.sh: Plan explainer videos end to end: script formulas, pacing, scene planning, voiceover and assembly.
• viscript Scenes — LottieFiles, beta: Write animated scenes, diagrams and math shorts in Lua or JS with viscript, then audit and render them.

Ads & UGC (3)

• Video Ad Specs — inference.sh: Build video ads to each platform's exact specs: TikTok, Instagram, YouTube, Facebook and LinkedIn.
• TikTok Selling Video Guide — zhenyangze, beta: Guide to TikTok product-selling videos: formats, 3-second hooks, shooting, editing, hashtags, metrics
• Video Script Generator — oliviapp8, beta: Writes a short-video script and shot list as YAML/JSON from pain-solution, before-after or plot-twist templates

3D scenes (3)

• Three.js Skills — CloudAI-X: 13 Three.js skills: scenes, geometry, materials, lighting, GLSL and TSL shaders, animation, post-processing, R3F.
• Three.js Scene Composition — Calesthio: Plan, build and capture Three.js scenes for video: absolute-time frames, seeded motion, color-safe glTF, render QA.
• R3F Skills — Nicolas Zullo: 11 React Three Fiber skills checked against Fiber 9.7 and three r185: Canvas, demand loops, loaders, shaders, post.

Text & titles (2)

• PixiJS Text — PixiJS: Render and animate text in PixiJS v8: canvas Text, BitmapText, HTMLText and per-character SplitText.
• Title & Kinetic Typography Direction — Calesthio: Typography direction for video: text jobs, hierarchy, reveal-hold-exit timing, safe zones, contrast, font licensing.

Editing services (2)

• Video Editing Best Practices — varg: Best practices for editing video with agents: which service for each edit, and the rules that keep cuts clean.
• Video editing skills for Claude Code and AI agents — varg: 206 named edits with recipes for FFmpeg, HyperFrames, Remotion and CapCut: cuts, transitions, titles, UI, numbers.

Product videos (1)

• Product Photography — inference.sh: Apply packshot conventions to AI product photos: angles, backgrounds, shadows, hero shots, store specs.

Shorts & Reels (1)

• Short Video Script — rascal6666, beta: Short-video scripts, titles and cover ideas for Douyin, Kuaishou, Bilibili and WeChat Channels

Cinematic & short films (1)

• FLUX 3 Keyframes & Continuation — Black Forest Labs: Build FLUX 3 video from supplied stills or footage: keyframe image-to-video and continuation chains.

Talking heads & avatars (1)

• Spoken Script Writer — dlazyai, beta: Writes short-video talking-head scripts in a fixed 7-step story structure for a personal brand

Phone & app screens (1)

• App Store Screenshots — inference.sh: Make App Store and Google Play screenshots to exact specs: sizes, gallery order, mockups and previews.

Transitions (1)

• editly — Mikael Finstad: Declarative JSON5 video editing CLI/API: clips, titles, transitions, audio mixing, rendered with ffmpeg.

Characters (1)

• Character Design — varg: How to make AI characters people remember: definition, details, clothing, and a sheet that keeps them consistent.

Logos & brand kits (1)

• Logo Design Guide — inference.sh: Design logos with AI image models: logo types, prompting techniques, scalability rules and iteration.

Camera & shots (1)

• Storyboard Creation — inference.sh: Storyboard a video before generating: shot types, angles, moves, the 180-degree rule, annotated panels.

Research & trends (1)

• Head of Content — Brad Bonanno, beta: TikTok, Instagram, YouTube and X outlier research, hook analysis and a content plan.

Other kinds of skills

• Prompts: The words a video model obeys: camera angles, shot sizes, lighting, characters, hooks and prompt guides for Seedance, Kling, Veo, FLUX and Higgsfield. Your agent writes the prompt with them, or you paste them into the model.
• Effects: An effect you can see, added to your video: animated titles, captions, transitions, shader backgrounds, logo animations, device mockups and viral camera tricks. Hand your agent the footage or the brief and get the effect.
• Styles: The look of the whole video: art styles, film looks, color grades and LUTs, caption fonts and style references. Pick a style and every shot your agent makes follows it.
• Workflows: A brief in, a finished video out: UGC ads, product videos, music videos, talking heads, explainers, Shorts and short dramas, step by step, with the models and the edit chosen for you.
• Models & tools: Run one model or tool from your agent: Seedance, Veo, Kling, FLUX, GPT Image, Nano Banana, ElevenLabs and 1,200+ more, plus scrapers, trend search and video analysis.

Questions

What is a guide skill?

Know-how your agent reads before it works: how to write a script, storyboard, edit and caption, and how to use Remotion, HyperFrames, GSAP, Three.js, PixiJS and FFmpeg correctly.

Does a guide make a video by itself?

No. A guide makes the agent better at the job; pair it with a workflow or a model skill to produce the video.