Claude MarketplacesSubmit

Yuv Video Director

hoodini/ai-agents-skills

Yuval's personal video factory that routes each beat of an idea to the right rendering engine and wraps it in the YUV.AI Neon Phoenix brand. It conducts HyperFrames (HTML to deterministic video), Lottie motion graphics, and ManimCE math animations into a single MP4. The architecture is clever: anything seekable runs live inside the render loop, anything that can't be seeked gets pre-rendered as a clip. You get branded templates, a neural net canvas background, six production Lotties, and a self-verification gate system that lints before render. Built for making explainers, promos, and social reels when you need more than screen recording but less than After Effects.

GitHub stars: 225
last updated: Jun 10, 2026

Install

$ npx -y skills add hoodini/ai-agents-skills --skill yuv-video-director --agent claude-code

Installs into .claude/skills of the current project.

Files

yuv-video-director

The conductor for YUV.AI video. You (the agent) decide what each beat needs, route it to the right engine, compose everything into one HyperFrames composition, wrap it in the YUV.AI Neon Phoenix brand, self-verify, and render to MP4. This skill is the router + the working reference implementations; load a reference file only when that engine is in play.

Design source of truth: the yuv-design-system skill (Neon mode — pink #FF1464, cyan #00E5FF, rich-black/white, Anton+Inter+JetBrains Mono, neural-net phoenix motif). The video form of it is frame.md — see references/frame-md.md. Bundled template: assets/FRAME.md. Drop it in the project root; HyperFrames reads it.

The one law (decides everything)

HyperFrames renders by seeking each frame in headless Chrome → FFmpeg (frameIndex = floor(t·fps), same input → same output). So every visual is one of two kinds:

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly

Agent CaffeineSponsoredClose your lid, come back to finished work

SnugSponsoredThe clipboard manager for the AI era Promote your product hereReach 125k+ visitors monthly

WaxSponsoredBlock anything with supervision, without erasing your iPhone Promote your product hereReach 125k+ visitors monthly

knobsSponsoredSee your site on any phone, any day, in any language

Details

Repository: github.com/hoodini/ai-agents-skills
Category: AI & Agent Building
First seen: Jun 11, 2026

Recommended

More AI & Agent Building

1

yuv-viral-videohoodini/ai-agents-skillsEdit any selfie or screen-share footage into a viral short-form video in YUV.AI's signature style — Apple-style liquid-glass cards (real CSS backdrop-filter), d0skills.sh installs

2

generating-cli-testshttps-deeplearning-ai/sc-agent-skills-filesGenerate pytest tests for Typer CLI commands. Includes fixtures (temp_storage, sample_data), CliRunner patterns, confirmation handling (y/n/--force), and edge c0skills.sh installs

3

learning-a-toolhttps-deeplearning-ai/sc-agent-skills-filesCreate learning paths for programming tools, and define what information should be researched to create learning guides. Use when user asks to learn, understand0skills.sh installs

4

reviewing-cli-commandhttps-deeplearning-ai/sc-agent-skills-filesProvides checklist for reviewing Typer CLI command implementations. Covers structure, Annotated syntax, error handling, exit codes, display module usage, destru0skills.sh installs

5

dspy-advanced-workflowintertwine/dspy-agent-skillsDrive a complete DSPy 3.2.x project end-to-end — spec → program → metric → baseline → GEPA optimize → export → deploy. Orchestrates the other four DSPy skills (0skills.sh installs

6

dspy-evaluation-harnessintertwine/dspy-agent-skillsBuild DSPy evaluation harnesses with rich-feedback metrics that are essential for GEPA optimization. Use when writing a metric function, calling dspy.Evaluate, 0skills.sh installs