Anti-AI Slop Filter
OpenClaw / KiloClaw recipe that maintains a living AI-slop pattern filter from Wikipedia and screens every piece of generated content before publish.
Overview
Anti-AI Slop Filter is a community OpenClaw recipe (KiloClaw bytes) that turns an agent into a self-updating content quality gate. On a weekly schedule it visits Wikipedia’s AI slop article, extracts current patterns, updates a local Anti-AI Slop skill, and runs new content through that filter before you see it. Best as an always-on publishing gate alongside prose skills like Stop Slop or No AI Slop.
Work with LimeDock
Using this skill? LimeDock can wire it into a durable automation you own.
Agents are a starting point. LimeDock turns the workflow into production automation your SaaS team owns — not another prompt library.
We sell owned automations for SaaS teams — live workflows that plug into Slack, CRM, and your internal platform — not just a skill list.
Link
Installation guide
In OpenClaw / KiloClaw, run the recipe prompt:
Create a skill called "Anti-AI Claw Slop". Weekly, visit https://en.wikipedia.org/wiki/AI_slop and find all of the patterns that are considered the latest in AI slop. Update your Anti-AI Slop skill with the latest patterns. Then any content you create should go through this filter to make sure we don't fall into any of these traps.Schedule the skill weekly and require the filter on publish workflows.
How to use it
1. Install the recipe / create the skill in your Claw. 2. Set weekly refresh against the Wikipedia AI slop page. 3. Route blog, docs, email, and social drafts through the filter before publish. 4. Periodically review the living checklist for trending patterns. 5. Pair with AI Smell Detector / De-Botinator bytes if available.
Example prompts
- “Set up the Anti-AI Slop Filter skill and run the first Wikipedia sync.”
- “Run this blog draft through the Anti-AI Slop Filter before I publish.”
- “Show me the current living slop pattern checklist and what changed this week.”
- “Add the filter as a required step in my content publishing workflow.”
Use cases and examples
- Always-on pre-publish filter for an OpenClaw content agent
- Weekly refresh of slop patterns as community definitions evolve
- Screen newsletters and social posts before scheduling
- Maintain a living team checklist sourced from Wikipedia
Prerequisites
- OpenClaw, KiloClaw, or similar agent host with web access + scheduling
- Permission for the agent to create/update a local skill file
- Human review still required for facts and brand voice
Tips
- Wikipedia is community-maintained — treat patterns as signals, not law.
- Works on any content type once the filter skill exists.
- Combine with no-ai-slop for deterministic pattern removal.