AgriciDanielAgriciDaniel/claude-youtube/CLAUDE.md

claude-youtube

CLAUDE.md343 starsChanged 8 months agoMITView on GitHub

This repository contains Claude YouTube, a Claude Code skill for YouTube creators. It covers channel audits, video SEO, retention-engineered scripts, hook writing, thumbnail briefs, content strategy, Shorts optimization, analytics, monetization, competitor research, and cross-platform repurposing. 14 sub-skills, 9 reference guides, 9 channel templates, and 6 execution scripts.

The file

We split this CLAUDE.md into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Keep SKILL.md under 500 lines
line 53
Distinctive:
Follow kebab-case naming for directories
line 57

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

CLAUDE.md

Claude YouTube — YouTube Creator Skill

Project Overview

This repository contains Claude YouTube, a Claude Code skill for YouTube creators. It covers channel audits, video SEO, retention-engineered scripts, hook writing, thumbnail briefs, content strategy, Shorts optimization, analytics, monetization, competitor research, and cross-platform repurposing. 14 sub-skills, 9 reference guides, 9 channel templates, and 6 execution scripts.

Architecture

claude-youtube/
  CLAUDE.md                          # Project instructions (this file)
  skills/claude-youtube/             # Main skill (single skill, not orchestrator)
    SKILL.md                         # Entry point, routing, core rules
    sub-skills/                      # 14 sub-skill instruction files (.md)
      audit.md, seo.md, script.md, hook.md, thumbnail.md,
      strategy.md, calendar.md, shorts.md, analyze.md,
      repurpose.md, monetize.md, competitor.md, metadata.md, ideate.md
    references/                      # 9 on-demand knowledge guides
    templates/                       # 9 channel type templates
    execution/                       # 6 Python scripts
      fetch_channel_data.py         # YouTube Data API v3 channel stats
      fetch_transcript.py           # Video transcript extraction
      fetch_video_analytics.py      # Analytics data retrieval
      search_competitor_videos.py   # Competitor video search
      utils/                        # Shared Python utilities

Commands

Command	Purpose
`/youtube audit`	Full channel health audit (4 dimensions)
`/youtube seo`	Video SEO package (titles, description, tags, schema)
`/youtube script`	Retention-engineered script with pattern interrupts
`/youtube hook`	5 hook variants with drop-off risk ratings
`/youtube thumbnail`	Thumbnail brief with 3 A/B variants
`/youtube strategy`	Channel positioning and 30/60/90-day milestones
`/youtube calendar`	Monthly content calendar with Shorts plan
`/youtube shorts`	Shorts production package
`/youtube analyze`	Analytics interpretation and priority actions
`/youtube repurpose`	Cross-platform content package
`/youtube monetize`	Revenue strategy across 7 streams
`/youtube competitor`	Competitor analysis with parallel agents
`/youtube metadata`	Copy-paste-ready upload package
`/youtube ideate`	10 ranked video ideas with keyword analysis

Development Rules

Keep SKILL.md under 500 lines
Sub-skills are instruction files in sub-skills/, not separate SKILL.md directories
Reference files should be focused and under 200 lines
Python scripts in execution/ must have docstrings and CLI interface
Follow kebab-case naming for directories

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free