Video ad creation with exact platform-specific specs for TikTok, Instagram, YouTube, Facebook, LinkedIn. Covers dimensions, duration limits, AIDA framework, and caption requirements.
SkillScore100Maintained
Automatic
◆Marketing & Content pack
Last verified 8/21/2026
What it changes
Passed 23 of 23 test cases with the skill, and 12 of 23 without it.
Without skill52%
With skill100%
Checks it passed that the model alone missed
States the TikTok hook window duration as 1 second
Uses belt app run falai/dia-tts for audio generation
Assigns the Desire phase to the 10 to 20 second window
and 14 more in the full report
11 fixed12 passed either way0 still failing0 broke
Pass-rate lift
+48 pp
Tokens
+101%
Agent turns
0%
Response time
-50%
Model gemini-3.6-flashMeasured 8/21/2026v123 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 11
Prompt
What strict runtime constraint applies to YouTube Bumper ad spots?
What was checked, without and with the skill
Checked
Without skill
With skill
Specifies YouTube Bumper ads must be exactly 6 seconds long
Missed
Passed
case-20 · gemini-3.6-flash · 8/21/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md253 linessingle file
Install the belt CLI skill:npx skills add belt-sh/cli
Video Ad Specs
Create platform-specific video ads via inference.sh CLI.
belt login
# Generate a vertical video ad scene
belt app run bytedance/seedance-2-0 --input '{
"prompt": "vertical video, person excitedly unboxing a product, clean modern room, bright natural lighting, social media ad style, authentic feeling",
"ratio": "9:16",
"generate_audio": true
}'