Hot Take
AI Agent Instructions
Use this Classifier via the SuperClassify API from server code, not browser playground automation. Create a user-controlled feed view for provocative opinion posts. Extract readable text from media and include nearby conversation. Use the result as a style tag, not a truth verdict; let users choose whether to downrank it. Retain factual reporting and provide a way to inspect posts excluded by the filter. Class: superclassify/hot-take@1.0.0 Fetch setup as text: https://superclassify.com/skills/superclassify/SKILL.md Contract (JSON): https://superclassify.com/v1/resolve?ref=superclassify%2Fhot-take%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.
Finds posts centered on a provocative opinion rather than an ordinary update.
superclassify/hot-take@1.0.0
Input
Send one raw text string.
Outputs
- matches (noul): true, false
Examples
Provocative opinion
Hot take: most productivity software creates more work than it saves.
Author expectation: {"matches":true}
Ordinary update
The library will open at 10 tomorrow because the lift is being inspected.
Author expectation: {"matches":false}
Balanced discussion
There are trade-offs to four-day weeks. This survey compares workload and staffing constraints.
Author expectation: {"matches":false}