Canonical definition
Do you think you’ll learn a new language in a month but doubt you can pass a simple test? That’s Hard–Easy Effect – the tendency to overestimate performance on hard tasks and underestimate it on easy ones.
Free cognitive-bias Agent Skill
Hard–Easy Effect
Use Hard–Easy 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.
Agent SkillsHermes AgentOpenClawChatGPT SkillsCodex
What the agent should do
Use one bias carefully, not as a diagnosis.
Output
- Plain-language explanation
- Observed signal
- Alternative explanation
- Evidence boundary
- Practical counter-check
- What would change the assessment
Install
Free. One SKILL.md. No API key.
Hermes Agent
mkdir -p ~/.hermes/skills/bias-self-assessment-hard && curl -fsSL https://cognitive-biases.github.io/agent-skills/bias-self-assessment-hard/SKILL.md -o ~/.hermes/skills/bias-self-assessment-hard/SKILL.mdOpenClaw
mkdir -p ~/.openclaw/workspace/skills/bias-self-assessment-hard && curl -fsSL https://cognitive-biases.github.io/agent-skills/bias-self-assessment-hard/SKILL.md -o ~/.openclaw/workspace/skills/bias-self-assessment-hard/SKILL.mdOther Agent Skills-compatible tools
Download SKILL.md and put it in the skill directory or import surface supported by your agent.
Boundary
A lens, not a verdict.
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.