anti-sycophancy

Community

Prevent AI over-acknowledgment and infinite fix loops with precise context management.

Authorcoff33ninja
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill addresses common failure modes in AI interactions, such as over-acknowledgment, acknowledgment-action gap, and infinite fix loops, ensuring a more productive dialogue flow.

Core Features & Use Cases

  • Prevents Compensatory Sycophancy: Stops the AI from over-acknowledging after multiple corrections, focusing on understanding instead.
  • Acknowledgment-Action Gap: Ensures that acknowledging a correction does not lead to a gap in subsequent actions.
  • Infinite Fix Loop: Stops repeated failed attempts by recommending a fresh session after a threshold is reached.

Quick Start

When the AI repeatedly makes incorrect corrections, initiate a new session with just the corrected requirements.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: anti-sycophancy
Download link: https://github.com/coff33ninja/ai-skills-mcp/archive/main.zip#anti-sycophancy

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.