skilld
All skills
hoodini avatar

/yuv-video-director

@f412198
by Yuval Avidanihoodini/ai-agents-skills281 stars
66

Yuval's all-in-one AI video pipeline. Turns an idea/script into a finished, on-brand MP4 by orchestrating HyperFrames (HTML→deterministic video render), Lottie (branded motion graphics), ManimCE (math / neural-network / concept animations), and a transcribe→approve caption flow — all wrapped in the YUV.AI Neon Phoenix brand via a frame.md. Use whenever Yuval wants to make, edit, or explain something as a video: promo, explainer, launch, social reel, "make a video about X", "explain X as a video", "neural network animation", "turn this into a video", captioned tutorial, 16:9 or 9:16. Triggers: video, explainer, promo, reel, manim, lottie, hyperframes, animation, "make a video", "explain ... as a video", מצגת וידאו, סרטון, הסבר וידאו. Routes each beat to the right engine, wraps in brand, self-verifies, and renders.

Ask your Agent

Use this Skill: https://skilld.dev/gh/hoodini/ai-agents-skills/yuv-video-director

This session only. Nothing lands on disk.

referencesprereqs.md

≈347 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Prerequisites & environment (check first; degrade gracefully)

Need Check Notes
Node 22+ node --version HyperFrames CLI (npx hyperframes)
FFmpeg ffmpeg -version encode/probe
Python 3.11+ with pip py -m pip --version Manim + captions
ManimCE py -m manim --version py -m pip install manim if missing
Headless Chrome npx hyperframes doctor downloaded on first render/validate

Windows gotchas (this machine)

  • python on PATH is Hermes' venv → NO pip. Use the py launcher (defaults to real C:\Python313). Always py -m pip ..., py -m manim ....
  • The PowerShell shell **resets to C:\ each call** — Set-Location <project> inside every command.
  • The sandbox blocks Remove-Item on C:\-relative paths — use absolute paths or just don't remove.
  • Anton (and most display fonts) are not auto-resolved by the HyperFrames renderer — download the latin woff2 and declare @font-face. Inter + JetBrains Mono auto-resolve.

Graceful degradation

  • No Manim / no pip → skip math beats (route to GSAP/Three.js) or offer to install; don't fail the whole video.
  • No LaTeX → fine; author Manim with Text()/MarkupText, never Tex/MathTex.
  • Offline → fonts/Lottie/Manim assets must be local (no Google Fonts <link>, no remote Lottie path).

Source: SKILL.md on GitHub

Third-party checks

1 warning3mo3 checks · Risk SAFE
  • Gen Agent Trust Hub3mo

    The yuv-video-director skill is a comprehensive and well-architected video production pipeline for AI agents. It orchestrates HyperFrames, Lottie, and ManimCE to create professional-grade video content with synchronized captions and branded motion graphics. The skill follows standard practices for asset management, using helper scripts to fetch legitimate resources like fonts and libraries from trusted sources. No malicious patterns, obfuscation, or data exfiltration risks were identified during the analysis.

  • Socket3mo

    No alerts

  • Snyk3mo

    Risk: MEDIUM · 1 issue

Provenance

Signed by skilld at f412198. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Steadyupdated 4 months ago

README badge

README badge for hoodini/ai-agents-skills/yuv-video-director