Help an AI coding assistant assess claims independently instead of automatically agreeing with the user. Responses lead with a conclusion and supporting evidence, while disagreements are evaluated for new information that could justify changing the assessment.
Eliminate sycophantic agreement patterns in AI responses. Load via /skill anti-sycophancy.
Run score Not tested
See how to installThis skill guides an AI coding assistant to assess claims using evidence instead of agreeing with the user automatically. It identifies the user's central claim in one sentence, considers evidence for and against it independently, then responds with the conclusion followed by its reasons. If the user disagrees, the assistant distinguishes new evidence from a repeated opinion.
Use it when you want code-related judgments or explanations assessed independently of the way you phrase a request or the position you take. It can also help when you provide new evidence and want the assistant to reconsider its assessment and explain what changed.
This skill is for opencode and is loaded with /skill anti-sycophancy. It is licensed under MIT. It changes the assistant's response approach; it does not give the assistant access to more facts. It is not intended to make the assistant oppose claims that are already supported by evidence.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).
Not counted in the score. Rated by AI (OpenAI Codex) as of Oct 24, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Use this skill when an AI coding assistant needs to challenge user claims independently, avoid agreement bias, and state evidence before deference.
For every response when this skill is active:
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
Full bibliography in README.md.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Assess a new or existing AI project by examining its code, goals, and constraints. Recommend skills confirmed to exist in the available registry, then outline tasks and implementation phases with dependencies, completion criteria, and checks.
Review code and infrastructure for security risks, map potential threats, and plan stronger defenses. The skill covers OWASP checks, attack and defense exercises, and incident response, with validation required for each environment.
Turn a repeatable task into an Andru.ia skill with clear inputs, outputs, examples, and limits. Draft SKILL.md, check the folder structure and required validations, and prepare a pull request describing the changes for review.
Prepare an industry briefing once a project's sector is defined. It covers sector context, potentially applicable regulations, familiar interface patterns, technology choices, and risks, while separating verified evidence from hypotheses and questions requiring further review.
Create presentation drafts from text, outlines, or documents through the 2slides API. Match a reference image's style, choose themes, add AI voice narration, and export slide images or audio for review and use.
Plan a 360-degree or peer feedback process and create empty response templates from confirmed requirements. Produces consistent CSV, SQL, JSON Schema, or Notion property mappings while keeping visibility choices and scoring configuration separate.