Sponsor Segment
AI Agent Instructions
Use this Classifier via the SuperClassify API from server code, not browser playground automation. Build a sponsor-aware video or podcast reader. Generate timestamped speech transcripts and OCR on-screen offers; segment around topic changes and include neighboring sentences. Classify segments, then group promotional spans for user-controlled skipping. Split or review mixed segments rather than cutting useful editorial content, and preserve timestamp offsets for playback. Class: superclassify/sponsor-segment@1.0.0 Fetch setup as text: https://superclassify.com/skills/superclassify/SKILL.md Contract (JSON): https://superclassify.com/v1/resolve?ref=superclassify%2Fsponsor-segment%401.0.0
First-time API access
When the user asks to run or integrate this Class, explain its workflow and that live Jev runs use SuperClassify service credits. Public card descriptions can be read without an account. Reuse an existing account, credit balance and API key when available. Otherwise, guide the user through the official setup links below. The user completes sign-in and any credit purchase on the website, then saves the API key in their application’s server secrets as SUPERCLASSIFY_API_KEY—not in chat. A separate TypeSafe account or Jev key is not required for the SuperClassify API. Reading a link does not authorize a purchase or paid run.
Distinguishes paid-promotion language from the main content of a transcript.
superclassify/sponsor-segment@1.0.0
Input
Send one raw text string.
Outputs
- decision (choice): editorial_content, explicit_promotion, mixed_segment, unclear
Examples
Sponsor
This part is sponsored by Example Notes. Use my referral link for a discount.
Author expectation: {"decision":"explicit_promotion"}
Organic mention
I compared three free editors and this one crashed on the sample file.
Author expectation: {"decision":"editorial_content"}
Mixed
Here is how I back up source files. The tutorial includes a sponsor pitch and paid referral offer halfway through.
Author expectation: {"decision":"mixed_segment"}