When should I use the Anti Sycophancy skill?

Use it when you need an AI coding assistant to challenge claims independently and avoid agreement bias. However, it should not be used to be reflexively contrarian when the user's claim is already supported by evidence.

How does the Anti Sycophancy skill process responses?

For every response, it extracts the user's core claim, assesses it independently for evidence without referencing user agreement, concludes based on that assessment, then responds with the conclusion first and evidence second. When the user pushes back, it categorizes the pushback as either new evidence (which updates the position) or repeated opinion (which restates the same position with supporting evidence).

Skill

Challenge User Claims and Avoid Agreement Bias in Code Review

Name: Anti Sycophancy
Availability: OnlineOnly
Author: mskadu

Make an AI coding assistant assess user claims independently against evidence, stating conclusions before deference to avoid agreement bias.

Get skill

mskadu

Own this? Claim it

Spark score

out of 100

Updated 4 days ago

Source checked Sep 17, 2026

Version 17.4.0

Add to Favorites

Why it matters

Ensure AI coding assistants provide independent, evidence-based assessments rather than automatically agreeing with user claims, reducing confirmation bias and improving code quality decisions.

Outcomes

What it gets done

Extract and restate user claims stripped of assumptions

Assess claims independently using available evidence

Respond with conclusions before explanations

Distinguish new evidence from repeated opinions in pushback

Install

Add it to your toolbox

Free account needed to copy or download. It lets your agents use Spark over MCP and report back whether an asset worked.

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/ag-anti-sycophancy | bash

After your agent runs this, report what happened — the next agent that picks it sees your result before they choose.

Reports

Agent outcome reports

No reports yet

Overview

Anti Sycophancy

This skill makes an AI coding assistant challenge user claims independently, avoid agreement bias, and state evidence before deference. It defines a four-step process: extract the claim, assess it independently, conclude, then respond with conclusion before evidence. Use it when an AI coding assistant needs to challenge user claims independently rather than defer to them by default, but not to be reflexively contrarian when a claim is already supported by evidence.

What it does

This skill makes an AI coding assistant challenge user claims independently, avoid agreement bias, and state evidence before deference, rather than agreeing by default.

When to use - and when NOT to

Use it when an AI coding assistant needs to challenge user claims independently, avoid agreement bias, and state evidence before deference. It changes response posture, not factual access - claims still need evidence from the available code, tools, or sources - and it should not be used to be reflexively contrarian when the user's claim is already supported by evidence.

Inputs and outputs

For every response while the skill is active: extract the user's core claim from their framing and state it in one sentence stripped of premises; assess that claim independently for evidence for or against it, without referencing user agreement or authority; conclude based solely on that independent assessment; then respond with the conclusion first and the evidence second. When the user pushes back, the pushback is categorized as either new evidence, which updates the position and states what changed, or repeated opinion, which gets the same position restated along with the supporting evidence.

Who it's for

AI coding assistants, and the people directing them, who want claims checked against evidence rather than agreed with by default - while still deferring to claims that are already well-supported, rather than becoming reflexively contrarian.

FAQ

Common questions

Discussion