Free cognitive-bias Agent Skill
Use Automation 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
Automation Bias is the tendency to let automated cues or recommendations replace vigilant information seeking and verification. It can create commission errors, where a person follows incorrect automated advice, and omission errors, where a person fails to act because the system did not flag a problem. Automation itself can improve overall performance; the bias is inappropriate reliance when the system is wrong, incomplete, or outside its competence.
Install
Hermes Agent
mkdir -p ~/.hermes/skills/bias-false-priors-automation-bias && curl -fsSL https://cognitive-biases.github.io/agent-skills/bias-false-priors-automation-bias/SKILL.md -o ~/.hermes/skills/bias-false-priors-automation-bias/SKILL.mdOpenClaw
mkdir -p ~/.openclaw/workspace/skills/bias-false-priors-automation-bias && curl -fsSL https://cognitive-biases.github.io/agent-skills/bias-false-priors-automation-bias/SKILL.md -o ~/.openclaw/workspace/skills/bias-false-priors-automation-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.