← Creator WorkspaceCONTENT HISTORYWHAT CHANGED · RULE-BASED ANALYSIS
Update to Creator Workspace
Snapshot Sep 30, 2026 · 23:14 UTC · version 0.3.3
Collection source: not recorded for this historical snapshot.
First saved snapshot
No earlier snapshot is available to establish a change.
Compare saved observations
Download comparison JSONFull technical diff · 0 changed fields
Full snapshot data
{
"description": "Develop a YouTube thumbnail concept and production prompt from a video title, topic, or angle. Use when the user asks for a thumbnail, thumbnail prompt, thumbnail text, or thumbnail A/B concepts.",
"included_files": [
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 261
}
],
"name": "youtube-thumbnail",
"skill_md_contents": "---\nname: youtube-thumbnail\ndescription: Develop a YouTube thumbnail concept and production prompt from a video title, topic, or angle. Use when the user asks for a thumbnail, thumbnail prompt, thumbnail text, or thumbnail A/B concepts.\n---\n\n# YouTube Thumbnail\n\n## Goal\n\nMake the thumbnail and title create one curiosity unit rather than repeat each other.\n\n## Process\n\n1. Identify the promise of the video.\n2. Identify what the title already communicates.\n3. Choose what the thumbnail should add.\n4. Limit thumbnail text to the minimum needed.\n5. Specify subject, crop, expression, environment, contrast, and negative space.\n6. Create 3 distinct concepts.\n\n## Output\n\nFor each concept:\n- thumbnail text, if any\n- visual idea\n- composition\n- production prompt\n- why it complements the title\n\nIf the host has image generation and the user asked for the image itself, use it. Otherwise return prompts only.\n"
}SHA-256 of public snapshot: f83dfaca5655251ee4e11e578a492ef1981847e1b520eec92dd6760558bb6970