Community Policy Fit

AI Agent Instructions

Use this Classifier via the SuperClassify API from server code, not browser playground automation.

Build a moderation queue around the community's fixed policy. For media, transcribe speech, OCR visible text and obtain frame descriptions first; Jev receives text only. Submit the post with conversational context. Keep the independent profanity signal separate from the policy outcome; route removals and uncertain cases through the community's configured review process.

Class: superclassify/community-policy-fit@2.0.0
Fetch setup as text: https://superclassify.com/skills/superclassify/SKILL.md
Contract (JSON): https://superclassify.com/v1/resolve?ref=superclassify%2Fcommunity-policy-fit%402.0.0

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.

1. Create an account or sign in
2. Add credits if needed
3. Create an API key

Legitimate criticism

Policy: prohibit targeted abuse; allow respectful criticism. Message: The update broke exports. Please fix it; this is frustrating.

Author expectation: {"policy":"allow","profanity":false}

Direct abuse

Policy: prohibit targeted personal abuse. Message directed at another member: You are worthless and nobody wants you here.

Author expectation: {"policy":"remove_recommended"}

Reporting an incident

Policy: allow reports quoting abuse. Message to moderators: Someone wrote “you are worthless” at me; please review the thread.

Author expectation: {"policy":"allow"}