Free portable Agent Skill

Information Verification

Verify important information by tracing provenance, counting independent sources instead of repetitions, preserving corrections and keeping verified, disputed and unknown claims separate.

Agent SkillsHermes AgentOpenClawChatGPT SkillsCodex

Open SKILL.md Back to marketplace

What it does

A repeatable workflow, not another bias-name list.

Use it when

A claim feels true mainly because it is familiar or repeated.
Several articles or summaries may depend on the same original source.
A correction exists but the older explanation still shapes discussion.
A generated answer makes consequential claims without inspectable provenance.

It returns

Claim ledger
Provenance / source lineage
Independent confirmation count where knowable
Corrections and version/date notes
Open verification gaps
What is safe to rely on now

Install

One SKILL.md. No API key.

Hermes Agent

mkdir -p ~/.hermes/skills/information-verification && curl -fsSL https://cognitive-biases.github.io/agent-skills/information-verification/SKILL.md -o ~/.hermes/skills/information-verification/SKILL.md

OpenClaw

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

Other Agent Skills-compatible tools

Download SKILL.md and place it in the skill directory supported by your agent. ChatGPT Skills and Codex support the Agent Skills format; their installation surface can vary by product.

Safety boundary

Useful skepticism without amateur diagnosis.

Do not call a claim verified when you cannot inspect supporting evidence.
Do not treat multiple summaries of one source as independent confirmation.
Do not erase the correction history when a claim changes.
Do not infer truth from popularity, repetition or confident language.

Instruction-only · no secrets · no executable code · no required network access · CC BY-NC-SA 4.0

Evidence-linked lenses

The skill checks patterns. It does not diagnose people.

Illusory Truth Effect

Repeated claims receive higher truth ratings than comparable new claims on average, but the effect is heterogeneous and does not generalize equally to every kind of statement. A 2026 systematic review and meta-analysis covering 182 studies, 366 effect sizes and more than 31,000 participants found a reliable corrected average effect. A later 2026 paper with two preregistered experiments found little or no meaningful repetition effect for social-political opinion statements. The useful claim is therefore narrower than 'repeat anything and people will believe it.'

Continued Influence Effect

The continued influence effect describes a specific pattern: false or outdated information can keep affecting later reasoning even after a clear correction. It does not mean the correction had no effect, that the person rejected the correction, or that belief in the false claim became stronger. Corrections often reduce misinformation reliance without removing it completely. That distinction matters because continued influence is much broader than the rarer backfire outcome.

Confirmation Bias

Confirmation bias is an umbrella label for several ways existing beliefs or hypotheses can influence information search and interpretation. It should not be reduced to one behaviour such as reading only agreeable news, and a preference for confirming tests is not irrational in every task or environment.

Availability Heuristic

Availability is a judgment heuristic: people can use how easily examples or scenarios come to mind when estimating frequency or probability. That shortcut is not automatically an error because memorable or accessible examples can correlate with real frequency. Bias appears when accessibility is driven by factors that are not diagnostic of the quantity being judged.