Free cognitive-bias Agent Skill
Use Conservatism 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
Conservatism bias is under-updating a belief: new evidence changes a probability estimate less than a Bayesian benchmark would predict. It concerns the weight given to evidence, not a political position. Caution about a weak report is not automatically a bias.
Install
Hermes Agent
mkdir -p ~/.hermes/skills/bias-belief-perseverance-conservatism-bias && curl -fsSL https://cognitive-biases.github.io/agent-skills/bias-belief-perseverance-conservatism-bias/SKILL.md -o ~/.hermes/skills/bias-belief-perseverance-conservatism-bias/SKILL.mdOpenClaw
mkdir -p ~/.openclaw/workspace/skills/bias-belief-perseverance-conservatism-bias && curl -fsSL https://cognitive-biases.github.io/agent-skills/bias-belief-perseverance-conservatism-bias/SKILL.md -o ~/.openclaw/workspace/skills/bias-belief-perseverance-conservatism-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.