← YouTube AgentCONTENT HISTORY
WHAT CHANGED
Update to YouTube Agent
Snapshot Oct 29, 2026 · 12:08 UTC · version 0.1.0
Collection source: downloaded plugin package.
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 JSONFull technical diff · 0 changed fields
Full snapshot data
{
"description": "Read a YouTube Studio audience-retention export and find where viewers actually leave, then say what to change. Use for \"why do people stop watching\", \"my retention is bad\", a pasted retention chart or CSV, or \"fix my pacing\".",
"included_files": [
{
"relative_path": "retention.py",
"size_in_bytes": 4666
}
],
"name": "yt-retention",
"skill_md_contents": "---\nname: yt-retention\ndescription: >-\n Read a YouTube Studio audience-retention export and find where viewers\n actually leave, then say what to change. Use for \"why do people stop\n watching\", \"my retention is bad\", a pasted retention chart or CSV, or \"fix\n my pacing\".\n---\n\n# yt-retention\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 retention graph is the only honest feedback YouTube gives you. Almost nobody exports it.\n\n```bash\npython3 retention.py retention.csv --duration 600\npython3 retention.py retention.csv --transcript transcript.srt\n```\n\nGetting the file: Studio -> a video -> Analytics -> Engagement -> the audience-retention chart ->\nthe download icon -> \"Audience retention\".\n\n## Three different problems\n\n- **HOOK LEAK** - what is lost in the first 30 seconds. Under 25% is healthy. This is always the\n first thing to fix and it is always the first fifteen seconds of script, never the edit.\n- **CLIFFS** - single steep drops. A cliff is a moment: a topic change with no signposting, a\n sponsor read, a long setup. With `--transcript` the tool prints what was being said there, which\n is what makes the report actionable instead of interesting.\n- **SLIDE** - the steady bleed across the middle. A flat slide is pacing. The fix is cutting, not\n rewriting.\n\n## What to hand back\n\nName the single biggest leak and one change for it. Not a list of five. Then, only if asked, the\nrest. And if the hook leak is healthy and the slide is flat, say the video is fine and the problem\nis packaging - send them to `/yt-package`.\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: 3afd625813e99bd6527ecc82b04ae113f049d46a27ca7e5a0308b92f18c7d3af