Free cognitive-bias Agent Skill
Use Backfire Effect as a focused cognitive-bias lens. Explain the pattern, check whether it plausibly fits the situation, surface an alternative non-bias explanation, and return a practical counter-check without diagnosing people or claiming causation.
What the agent should do
The Backfire Effect is a specific outcome in which a correction increases belief in the false claim it was meant to correct. Research suggests this is uncommon: factual corrections usually improve belief accuracy, so disagreement, anger, or refusing to concede is not enough to call something a backfire effect.
Install
Hermes Agent
mkdir -p ~/.hermes/skills/bias-confirmation-bias-backfire-effect && curl -fsSL https://cognitive-biases.github.io/agent-skills/bias-confirmation-bias-backfire-effect/SKILL.md -o ~/.hermes/skills/bias-confirmation-bias-backfire-effect/SKILL.mdOpenClaw
mkdir -p ~/.openclaw/workspace/skills/bias-confirmation-bias-backfire-effect && curl -fsSL https://cognitive-biases.github.io/agent-skills/bias-confirmation-bias-backfire-effect/SKILL.md -o ~/.openclaw/workspace/skills/bias-confirmation-bias-backfire-effect/SKILL.mdOther Agent Skills-compatible tools
Download SKILL.md and put it in the skill directory or import surface supported by your agent.
Boundary
The skill must preserve uncertainty, surface a non-bias explanation and avoid turning a cognitive-bias label into a claim about a person's motives, intelligence or mental health.