domains / families / agent-tooling / anti-sycophancy

anti-sycophancy

authentic

Eliminate sycophantic agreement patterns in AI responses. Load via /skill anti-sycophancy.

When to use

• Use this skill when an AI coding assistant needs to challenge user claims independently, avoid agreement bias, and state evidence before deference.

When not to use

• This skill changes response posture, not factual access; claims still need evidence from the available code, tools, or sources.
• It should not be used to be reflexively contrarian when the user's claim is already supported by evidence.

Skill page

Source