Free cognitive-bias Agent Skill
Use Confirmation Bias 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
Confirmation Bias is a broad label for ways an existing belief or hypothesis can influence how information is searched for, interpreted, remembered, or evaluated. It is wider than simply reading agreeable news, and it does not mean that every preference for confirming evidence is irrational.
Install
Hermes Agent
mkdir -p ~/.hermes/skills/bias-cognitive-bias-confirmation-bias && curl -fsSL https://cognitive-biases.github.io/agent-skills/bias-cognitive-bias-confirmation-bias/SKILL.md -o ~/.hermes/skills/bias-cognitive-bias-confirmation-bias/SKILL.mdOpenClaw
mkdir -p ~/.openclaw/workspace/skills/bias-cognitive-bias-confirmation-bias && curl -fsSL https://cognitive-biases.github.io/agent-skills/bias-cognitive-bias-confirmation-bias/SKILL.md -o ~/.openclaw/workspace/skills/bias-cognitive-bias-confirmation-bias/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.