Skills & repos directory
Video-specific agent skills, MCP servers, GitHub repos and ComfyUI workflows. Star counts are from GitHub on 2026-10-14. Listing isn’t endorsement: everything here is spotted, not yet tested unless a Lab post says otherwise.
37 of 37 items
Code-to-video engine
HTML → deterministic MP4; /hyperframes router picks launch, explainer, PR-to-video, recut or music workflows.
Code-to-video engine
React components → video. Mature, Lambda rendering; paid licence above 3 people.
Code-to-video engine
Official Remotion best practices for Claude Code, Codex, Cursor.
Code-to-video engine
Single-binary HTML → MP4/WebM renderer with Chrome and ffmpeg bundled. Very early.
Motion graphics
Taste rules with numbers, contact-sheet self-review, Python sound engine, web sims → 60 fps.
Motion graphics
Canvas + Playwright + FFmpeg animation in 7 styles; storyboard gates; Whisper word timing.
Motion graphics
Launch videos from code: GSAP, word-locked VO, camera moves, film grade, loudness.
Motion graphics
13 skills for launches, animated charts and reels.
Motion graphics
HTML + Playwright + ffmpeg motion design; cuts on the beat.
Motion graphics
Motion B-roll timed to your words over your own footage.
Motion graphics
Remotion skill targeting flat fades and stiff motion.
Motion graphics
Official GSAP skills; the engine under many launch kits.
Motion graphics
Timing, easing, choreography and Disney's 12 principles for agents.
Motion graphics
Motion.dev web animation skill (springs, scroll, gestures).
Generation
All Higgsfield models, Soul characters, audio, upscaling, Kling Motion Control inside Claude. Uses credits.
Generation
generate / soul / product-photoshoot CLI skills for coding agents.
- Higgsfield KatanaSkill
VFX & compositing
Rebuild a reference edit you own with up to 5 photos of your characters/products.
Audio & music
Official MCP for TTS, voices and sound effects.
- ComfyUI Wan 3.0 templatesComfyUI
Generation
Official t2v / i2v / r2v graphs; @Image1/@Video1/@Audio1 reference tags (Partner Nodes, credits).
Generation
Official template repo (Wan 3.0, vCube enhance, Meshy 3D...).
Generation
Community nodes for running Wan models locally.
Generation
Load/combine video nodes used in most ComfyUI video graphs.
Generation
Open video model family for self-hosting.
Generation
30 s native clips, up to 20 reference assets, instruction video editing.
Audio & music
Local song generation, covers, stems, LoRA from a few songs, BPM/key extraction.
Audio & music
Lyrics → full-length song, fast.
Audio & music
Video-to-audio synced foley (~6 GB VRAM). Check licence for commercial use.
Audio & music
Foley generation from video + text.
Audio & music
Stem separation, used for beat detection on drums and clean vocal timing.
Lip-sync & timing
Open audio-conditioned lip-sync (v1.6, 512px). Consenting subjects only.
Lip-sync & timing
Word-level timestamps + diarization for captions and cut timing.
Lip-sync & timing
Fast local transcription; used by the animate skill for word timing.
VFX & compositing
Depth + SAM 3 + Seedance subject replacement on your own footage, with a hashed mask-approval gate.
Image & design
Lint scripts for AI tells before voice-over.
Image & design
Open-source Rust photo editor agents can drive, for fixing starting frames.
Image & design
Open-source Photoshop alternative for Mac.
- SkillrySkill
Motion graphics
400+ in-house designed skills (video, slides, web, image); free + paid tiers.
Request a skill
Tell us about a video workflow you wish an agent could run. We’ll prioritise building, testing and writing up the most-requested ones.