Free cognitive-bias Agent Skill

Surrogation

Use Surrogation 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

Open SKILL.md Read canonical bias

What the agent should do

Use one bias carefully, not as a diagnosis.

Canonical definition

Surrogation is a management-accounting construct in which a performance measure starts to be treated as though it were the strategic objective it was meant to represent. A KPI can be useful and still capture only part of the underlying goal. The problem begins when improving the number becomes evidence, by itself, that the real objective improved.

Evidence, related concepts and current review state →

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-cognitive-bias-surrogation && curl -fsSL https://cognitive-biases.github.io/agent-skills/bias-cognitive-bias-surrogation/SKILL.md -o ~/.hermes/skills/bias-cognitive-bias-surrogation/SKILL.md

OpenClaw

mkdir -p ~/.openclaw/workspace/skills/bias-cognitive-bias-surrogation && curl -fsSL https://cognitive-biases.github.io/agent-skills/bias-cognitive-bias-surrogation/SKILL.md -o ~/.openclaw/workspace/skills/bias-cognitive-bias-surrogation/SKILL.md

Other 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.

Free to install · instruction-only · no secrets · no executable code · no required network access