unslop-reasoning

Rewrite reasoning traces by removing six AI-slop patterns while preserving details.

91|2|Updated Apr 19, 2026

Search Tags:#chain-of-thought #reasoning #conciseness #rewriting #slop #cot #unslop

Ready to run

npx skills add https://github.com/MohamedAbdallah-14/unslop --skill unslop-reasoning

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: unslop-reasoning
Source: https://github.com/MohamedAbdallah-14/unslop/tree/main/plugins/unslop/skills/unslop-reasoning
Command: npx skills add https://github.com/MohamedAbdallah-14/unslop --skill unslop-reasoning

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Strip AI-slop patterns from chain-of-thought and extended reasoning traces—over-explaining, over-hedging, over-decomposing trivial problems, and infinite-loop rationalization—without altering the final prose.

Core Features & Use Cases

Detects six canonical AI-slop patterns in reasoning traces and provides tighter rewrites.
Rewrites traces to be concise and directive while preserving concrete details.
Use Case: paste a reasoning trace into a chat and request a version that reads more like deliberate thinking than robotic inner monologue.

Quick Start

Paste your reasoning trace and request a concise, less robotic rewrite.

Frequently Asked Questions about unslop-reasoning

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I clean up chain-of-thought reasoning traces to make them less robotic?▼

To clean up chain-of-thought reasoning traces, paste the extended thinking output into the chat and request a concise rewrite. The tool detects six canonical AI-slop patterns and rewrites traces to read like deliberate thinking without altering factual content.

What are common AI-slop patterns in extended thinking outputs?▼

Common AI-slop patterns in extended thinking outputs include over-explaining, over-hedging, over-decomposing trivial problems, and infinite-loop rationalization. These robotic inner monologue patterns are detected and removed while preserving concrete details.

Can I rewrite a reasoning trace without changing the factual content?▼

Yes, you can rewrite a reasoning trace without changing factual content. The tool produces a concise, directive version that preserves all concrete details while stripping over-hedging and over-decomposing patterns from the internal reasoning trace.

What is the best way to make chain-of-thought outputs more concise?▼

The best way to make chain-of-thought outputs more concise is to apply a targeted rewrite that removes infinite-loop rationalization and over-explaining. This approach cleanses the reasoning trace while producing a tighter, more natural thinking version.

Does rewriting reasoning traces work for over-decomposed trivial problems?▼

Yes, rewriting reasoning traces works for over-decomposed trivial problems. The tool specifically detects over-decomposition as one of six AI-slop patterns and provides tighter rewrites to eliminate unnecessary robotic inner monologue.