← 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 the Shorts hiding inside a long video and write them, using the transcript to pick self-contained moments. Use for \"cut this into shorts\", \"clip this\", \"repurpose this video\", \"what should I clip\".",
  "included_files": [],
  "name": "yt-shorts",
  "skill_md_contents": "---\nname: yt-shorts\ndescription: >-\n  Find the Shorts hiding inside a long video and write them, using the\n  transcript to pick self-contained moments. Use for \"cut this into shorts\",\n  \"clip this\", \"repurpose this video\", \"what should I clip\".\n---\n\n# yt-shorts\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\nA Short cut out of a long video is not a clip of the best moment. It is a moment that **survives\nwithout the video around it**, which is a much smaller set.\n\n## Picking\n\nRead the transcript and find spans of 20-55 seconds where all three are true:\n\n1. It opens on a complete thought. If the first sentence needs the previous minute, it is not a Short.\n2. There is a turn in it - a claim, then something that complicates or proves it.\n3. It ends on a line, not a trail-off.\n\nRank the candidates and show the user the top five with their timecodes and first line, so they can\nreject one without reading the whole transcript.\n\n## Writing each one\n\n- **A NEW first line.** The long video's line assumes context this viewer does not have. Write the\n  replacement and run it through `../yt-script/hookscore.py`.\n- **On-screen text for the first two seconds**, different words from the spoken line.\n- **A loop point**: what the last line sets up so the first line answers it.\n- Vertical framing note - what gets cropped out of a 16:9 frame and whether that matters.\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: 9c8f29f2a3499cde7026bcc6c983066835a8b9599f7aa305901f17b835972bdb