← YouTube AgentCONTENT HISTORY

Update to YouTube Agent

Snapshot Oct 29, 2026 · 12:08 UTC · version 0.1.0

Collection source: downloaded plugin package.

WHAT CHANGED

First saved snapshot

No earlier snapshot is available to establish a change.

Save YouTube Agent and check future changes in Following.

Up to 10 plugins free · no card required.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "description": "Find what is actually working in the user's niche on YouTube and rank it by how far each video beat its own channel, then name the formula. Use for \"what's working right now\", \"find viral videos in my niche\", \"why did this blow up\", competitor research, or a swipe file.",
  "included_files": [
    {
      "relative_path": "swipe.py",
      "size_in_bytes": 3573
    }
  ],
  "name": "yt-viral",
  "skill_md_contents": "---\nname: yt-viral\ndescription: >-\n  Find what is actually working in the user's niche on YouTube and rank it\n  by how far each video beat its own channel, then name the formula. Use for\n  \"what's working right now\", \"find viral videos in my niche\", \"why did this\n  blow up\", competitor research, or a swipe file.\n---\n\n# yt-viral\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\nRaw view counts rank channel size, not ideas. This ranks by **multiple over each channel's own\nmedian**, which is the only version of the question that is about the video.\n\n```bash\npython3 swipe.py collected.json --min 2.0\n```\n\n## Collecting the input\n\nYou need at least **four videos per channel** or a median means nothing, and the tool will skip the\nchannel and tell you it did. Collect them however the user prefers - `yt-dlp --flat-playlist -J`\nagainst a channel URL is the fastest, the public page works, a manual list works.\n\n```json\n[{\"channel\":\"...\",\"title\":\"...\",\"views\":412000,\"url\":\"...\",\"duration\":613}]\n```\n\n**Read, do not scrape.** Public listings only, never a logged-in session, never the user's own\naccount credentials.\n\n## Reading the output\n\nThe multiple is the signal. The formula line is a judgement about the TITLE, matched against\n[the 21 formulas](../yt-script/hooks.json) - it is not a claim about why the video worked, and you\nshould say so when you present it.\n\nWhat to hand back: the top five with their multiples, the formula each used, and the ONE structural\nthing they share. Then the harder line - which of those the user could actually make this week, in\ntheir voice, with what they have.\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"
}

SHA-256 of public snapshot: 15a520563a450243b3a5a8a455847119c0ccffc85fdab0a241aa07a2acdc2f28