Update to YouTube Agent

{
  "description": "Write and lint the title and thumbnail for a YouTube video as one pairing, checking truncation, duplication and vagueness before publish. Use for \"title ideas\", \"what should I call this\", \"thumbnail text\", \"my CTR is bad\", packaging, or any request to rename or repackage an existing video.",
  "included_files": [
    {
      "relative_path": "title.py",
      "size_in_bytes": 4080
    }
  ],
  "name": "yt-package",
  "skill_md_contents": "---\nname: yt-package\ndescription: >-\n  Write and lint the title and thumbnail for a YouTube video as one pairing,\n  checking truncation, duplication and vagueness before publish. Use for\n  \"title ideas\", \"what should I call this\", \"thumbnail text\", \"my CTR is\n  bad\", packaging, or any request to rename or repackage an existing video.\n---\n\n# yt-package\n\nUse scripts relative to this skill directory, not the user’s working directory. If local execution or inputs are unavailable, explain the limitation and provide a clearly labeled manual alternative; do not claim a tool ran. Scores and thresholds are heuristics, not guarantees or causal proof. Use only accessible or user-provided data; never invent analytics.\n\nThe title and the thumbnail are ONE unit. Writing them separately is why most packaging fails: the\nthumbnail repeats the title, and half the click surface says the same thing twice.\n\n```bash\npython3 title.py --title \"...\" --thumb \"AI RAN IT\"\npython3 title.py titles.txt            # one per line, ranked\n```\n\n## Before you write\n\n1. Use a voice profile or samples the user provides; otherwise ask for a short style description and continue with stated assumptions. Save a profile only when the user requests it.\n2. Never invent a number, a result or a source. If a figure would strengthen it and you do not have\n   one, ask for it or write the line without it.\n\n## Rules the tool enforces, and why\n\n- **60 characters** is where desktop search truncates, **40** is a mobile home feed. Both are\n  reported because they fail differently: a desktop cut loses the tail, a mobile cut can lose the\n  subject.\n- **The thumbnail must not repeat the title.** Different words, same promise.\n- **Three words maximum on the thumbnail.** At feed size a fourth word is a grey smear.\n- **A number, a name or a date** beats every adjective available to you.\n- **Two all-caps words is the ceiling** before a title reads as spam.\n\n## Write ten, keep two\n\nGenerate ten titles, run them all through `title.py`, show the user the top three with their scores\nand the specific issue on each. For the winner, write the thumbnail brief: the expression, the\nframing, the three words, and what the background has to do to hold contrast at feed size.\n\n## The gate\n\nNothing here publishes. This skill writes and you publish. Every output ends in a block the user\ncopies, and the last line of every run is the question: **ship it, or change it?**\n"
}