video-ai-automation

video-ai-automation is a skill for Claude Code, Codex from chadixearth/graphyloop. It costs 57 tokens per session (810 once invoked), scanned A, original, MIT.

A guide for planning faceless videos made with AI, from scripts and voiceovers to clips, captions, music, and export.

In plain words
What is it for?
Use it to choose video subjects, plan a YouTube channel, select AI video tools, and consider advertising or affiliate income.
Why use it?
It helps turn an AI-video idea into a defined content niche and production process instead of choosing tools or topics at random.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to choose video subjects, plan a YouTube channel, select AI video tools, and consider advertising or affiliate income.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chadixearth/graphyloop/video-ai-automation
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add chadixearth/graphyloop --skill video-ai-automation
Clone the repo
git clone --depth 1 https://github.com/chadixearth/graphyloop

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for video-ai-automation

README.md
[![agentmods](https://agentmods.dev/badge/skills/chadixearth/graphyloop/video-ai-automation/github.svg)](https://agentmods.dev/skills/chadixearth/graphyloop/video-ai-automation)
Your own site
<a href="https://agentmods.dev/skills/chadixearth/graphyloop/video-ai-automation"><img src="https://agentmods.dev/badge/skills/chadixearth/graphyloop/video-ai-automation/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for video-ai-automation

Your own site · 80×15
<a href="https://agentmods.dev/skills/chadixearth/graphyloop/video-ai-automation"><img src="https://agentmods.dev/badge/skills/chadixearth/graphyloop/video-ai-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 810 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.00810
Opus 5 $0.00028 $0.00405
Sonnet 5 $0.00011 $0.00162
Haiku 4.5 $0.00006 $0.00081

Measured 6d ago against content hash 6980710b0c30, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

video-ai-automation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/video-ai-automation/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video AI Automation

1. Overview

Faceless AI video pipeline: script → AI voiceover → AI clips/stills → captions → music → export 9:16.

Niche beats production quality: "YouTube doesn't care who is talking, it only cares whether people keep watching."

2. Winning Niches

Niche Why it works Notes
History / boring-history documentaries Older affluent audience, high RPM Videos from ~$60 cost, margins 85-89%, AdSense long-form
Space / science news Evergreen search e.g. "what did the James Webb telescope find"
Unsolved mysteries / cold cases Watch-time loyalty Avoid oversaturated cases; use historical/uncovered cases
Odd facts / "worth more than you think" Beginner entry Production quality barely matters
Survival myths / frontier history Strong repeat audience Steady view pattern
Niche hobby / collector (aircraft, ships, tools) Consistent growth Audience buys, good affiliate fit
AI-narrated character / storytelling Highest ceiling via recognizable brand Most setup, brand compounds

3. Monetization Ladder

  1. AdSense — long-form, multiple ad breaks, high RPM
  2. Affiliates / reviews — commission per video
  3. Sponsors — only at scale

4. Growth Patterns

  • Volume + consistency: algorithm needs data points; 2-3 weeks of consistent posting can break through
  • Double-down on outliers: find the video beating your sub count, repeat that angle
  • Real photos beat AI images for thumbnails
  • Evaluate niche on: RPM, view velocity, saturation risk, format simplicity

5. Tool Stack (2026)

Stage Tool Notes
Script LLM + story-engineering skill structure via story-engineering
Voiceover ElevenLabs quality leader
Voiceover MiniMax TTS cheapest volume
Voiceover OpenAI gpt-4o-mini-tts budget option
Video clips Veo 3.1 native audio, camera controls
Video clips Kling 3.0 cheap, native 4K
Video clips Seedance budget
Video clips Runway / Pika / Luma alternatives
Video clips Sora DISCONTINUED (app Apr 2026, API Sep 2026) — do not recommend
Images Midjourney V7 hero stills
Images Flux Ken Burns fallback
Captions CapCut auto-captions, Whisper word-sync
Edit CapCut, Descript assembly + cleanup
Music Suno, YouTube Audio Library library is safe for monetization
Rendering HyperFrames HTML/CSS-keyframe, local, deterministic, no per-clip API cost — strong for text/data-driven channels

Read the full file on GitHub · 75 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 75 lines · 57 tokens per session scan A 6980710b0c30

Subscribe to this mod's changes

video-ai-automation is a skill published in the GitHub repository chadixearth/graphyloop (2 stars, last pushed 24d ago), licensed MIT. It adds 57 tokens to every session and 810 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

hipson-hyperframes-video

Use for optional HyperFrames video composition workflows, website-to-video planning, product videos, launch videos, animated case studies, social shorts, and deterministic timeline QA.

Hipson47/Hipson · 39 tokens

nano-banana

REQUIRED for all image generation requests. Generate and edit images using Nano Banana (Gemini CLI). Handles blog featured images, YouTube thumbnails, icons, diagrams, patterns, illustrations, photos, visual assets, graphics, artwork, pictures. Also routes specialty creative recipes (anime-to-life…

GobbyAI/gobby · 120 tokens

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…

Hipson47/Hipson · 62 tokens

canvas-design

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Hipson47/Hipson · 59 tokens

theme-factory

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

Hipson47/Hipson · 62 tokens

podcast-generation

Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.

bytedance/deer-flow · 38 tokens