anti-sycophancy
Makes your agent not agree with everything. It ensures responses are more honest and useful by preventing the agent from blindly agreeing.
What it does
This tool teaches AI not to blindly agree with you. It checks your ideas based on facts, rather than just saying 'yes'.
When to use it
- ✓When you want the AI to think for itself.
- ✓When you want the AI to show evidence before agreeing.
- ✓When you want to avoid the AI being overly agreeable.
Example of what to ask your AI
“Evaluate this idea: 'Using Python for this project is the best option'.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
The AI identifies your main point, checks if facts support or contradict it, and responds with the conclusion and evidence, regardless of your agreement.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add sickn33/agentic-awesome-skills --skill anti-sycophancyOr download just the file:
curl -L https://raw.githubusercontent.com/sickn33/agentic-awesome-skills/main/plugins/agentic-awesome-skills-claude/skills/anti-sycophancy/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
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.
Process
For every response when this skill is active:
- Extract the user's core claim from their framing. State it in one sentence stripped of premises.
- Assess that claim independently — evidence for/against, without referencing user agreement or authority.
- Conclude based solely on step 2.
- Respond with the conclusion first, evidence second.
When the user disagrees with your assessment: a) Categorise the pushback: is it new evidence or repeated opinion? b) If new evidence → update your position, state what changed c) If repeated opinion → restate your position with the evidence
References
Full bibliography in README.md.
Limitations
- 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.
FAQ
Will the AI always disagree with me?
No, it only disagrees if the facts don't support your idea. If the facts do support it, it will agree based on the evidence.
Will the AI make up information?
No, it uses the information it already has (code, tools, etc.) to check your idea.
What happens if I disagree with the AI?
The AI will check if your disagreement brings new evidence or is just a repeat. If it's new evidence, it might change its mind. If it's a repeat, it will restate its position with the evidence.
Details
Original description by the author
Eliminate sycophantic agreement patterns in AI responses. Load via /skill anti-sycophancy.
Popularity
- GitHub stars
- 48k
- Ranking position
- #2142
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
00-andruia-consultant
Helps your agent start or improve AI projects. It analyzes code, suggests tools, and creates action plans in Spanish.
sickn33/agentic-awesome-skills
007
Lets your agent perform security audits and threat modeling. It's useful for protecting projects against attacks and vulnerabilities.
sickn33/agentic-awesome-skills
10-andruia-skill-smith
Helps your agent create or improve AI tools. It defines how tools work, writes documentation, and validates the structure.
sickn33/agentic-awesome-skills
20-andruia-niche-intelligence
Lets your agent create a summary about a specific industry. It's useful for understanding the context, rules, usage patterns, and risks of a project, using reliable sources.
sickn33/agentic-awesome-skills
Similar skills
agent-architecture-audit
Makes your agent check if everything is working correctly. It finds and fixes problems in AI systems, ensuring they perform as expected.
affaan-m/ECC
agent-eval
Helps your agent compare different AI coding tools. It measures which one is faster, cheaper, and more reliable for specific tasks.
affaan-m/ECC
agent-harness-construction
Makes your agent better understand how to perform tasks. It optimizes the tools and instructions the agent uses to increase its chances of success.
affaan-m/ECC