~ / rigs / utillayer / youtube-agent-skill

utillayer/youtube-agent-skill

Check a YouTube video before you upload it: score the hook, test the title against the thumbnail, cut dead air from the transcript, find where viewers drop off, and pull Shorts from long videos. Works in Claude Code, Codex and claude.ai.

↗ GitHub ★ 17 MIT updated 19d ago collection Claude Code Claude plugin
stack: Python
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~125 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 0/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit utillayer/youtube-agent-skill/skills ./rig-youtube-agent-skill/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit utillayer/youtube-agent-skill/skills/yt-audit .claude/skills/yt-audit
$ npx degit utillayer/youtube-agent-skill/skills/yt-chapters .claude/skills/yt-chapters
$ npx degit utillayer/youtube-agent-skill/skills/yt-comment .claude/skills/yt-comment
$ npx degit utillayer/youtube-agent-skill/skills/yt-edit .claude/skills/yt-edit
$ npx degit utillayer/youtube-agent-skill/skills/yt-package .claude/skills/yt-package
$ npx degit utillayer/youtube-agent-skill/skills/yt-plan .claude/skills/yt-plan
$ npx degit utillayer/youtube-agent-skill/skills/yt-research .claude/skills/yt-research
$ npx degit utillayer/youtube-agent-skill/skills/yt-retention .claude/skills/yt-retention
$ npx degit utillayer/youtube-agent-skill/skills/yt-script .claude/skills/yt-script
$ npx degit utillayer/youtube-agent-skill/skills/yt-seo .claude/skills/yt-seo
$ npx degit utillayer/youtube-agent-skill/skills/yt-shorts .claude/skills/yt-shorts
$ npx degit utillayer/youtube-agent-skill/skills/yt-viral .claude/skills/yt-viral

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(git push --force:*)",
      "Read(**/*.pem)",
      "Read(.env)",
      "Read(~/.aws/**)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Bash(rm -rf *)",
      "Bash(sudo *)",
      "Bash(sudo:*)",
      "Bash(rm -rf /)",
      "Bash(git push -f:*)",
      "Read(.env.*)",
      "Bash(git reset --hard*)",
      "Bash(rm -rf /*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(gh pr merge *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(gh pr merge:*)",
      "Bash(gh pr create *)",
      "Bash(git reset --hard:*)",
      "Bash(npm publish:*)",
      "Bash(git rebase *)"
    ]
  }
}

Skills (12)

Similar rigs

copied ✓