Update to YouTube Agent

{
  "description": "Write a YouTube video script from a raw idea - hook options off 21 formulas, scored, then the full spoken script with the retention beats marked. Use whenever the user wants a video script, a hook, an opening line, \"what should I say\", \"write my next video\", or is about to record and does not have the first fifteen seconds yet.",
  "included_files": [
    {
      "relative_path": "hooks.json",
      "size_in_bytes": 9894
    },
    {
      "relative_path": "hookscore.py",
      "size_in_bytes": 5703
    }
  ],
  "name": "yt-script",
  "skill_md_contents": "---\nname: yt-script\ndescription: >-\n  Write a YouTube video script from a raw idea - hook options off 21\n  formulas, scored, then the full spoken script with the retention beats\n  marked. Use whenever the user wants a video script, a hook, an opening\n  line, \"what should I say\", \"write my next video\", or is about to record\n  and does not have the first fifteen seconds yet.\n---\n\n# yt-script\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\nOne idea into a script somebody finishes.\n\nTwo tools live in this folder and both actually run. Use them. Do not eyeball the hook.\n\n```bash\npython3 hookscore.py hooks.txt              # rank your hook options\npython3 hookscore.py --hook \"one line\"      # score a single one\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## The shape\n\n**The first 15 seconds is the whole job.** It does three things or the video leaks: confirm the\nclick the title promised, open a question the viewer cannot close, and prove the payoff exists.\n\n1. **Hook.** Write FIVE against [the 21 formulas](hooks.json), run them through `hookscore.py`,\n   keep the top two, and show the user both with their scores. Never hand over one hook.\n2. **The turn** (0:15-0:45). Say what the video is going to do, in one sentence, and start doing it.\n   No channel intro, no \"before we get started\", no subscribe pitch. Those are the single most\n   common cause of the 0:30 cliff.\n3. **The body.** One idea per beat. Mark each beat with what is ON SCREEN, not just what is said -\n   a talking head with nothing to look at is a podcast.\n4. **The payoff.** Deliver the thing the hook promised, explicitly, and say that you are delivering\n   it: \"that is the prompt, it is in the description\".\n5. **The close.** One ask. Not three.\n\n## What to hand back\n\n- the two best hooks with their scored panels\n- the script, beat by beat, with `[ON SCREEN: ...]` on every beat\n- the runtime estimate at 150 words per minute\n- one line naming which formula the winning hook used and why it fits this idea\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"
}