impostor-syndrome

Require explicit evidence for every claim and surface unknowns.

10|Updated Feb 26, 2026

Search Tags:#evidence #uncertainty #claims #prompt-design #self-audit #verifiability #impostor-syndrome

Ready to run

npx skills add https://github.com/olivierlesnicki/addhumanity --skill impostor-syndrome

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: impostor-syndrome
Source: https://github.com/olivierlesnicki/addhumanity/tree/main/skills/impostor-syndrome
Command: npx skills add https://github.com/olivierlesnicki/addhumanity --skill impostor-syndrome

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Impostor syndrome imposes a cognitive pressure to ensure every claim is grounded in explicit evidence, reducing overconfidence and promoting epistemic honesty.

Core Features & Use Cases

Explicitly require evidence for each claim and highlight uncertainties.
Distinguish knowns from guesses and surface unstated assumptions.
Encourage transparent sourcing and traceability in reasoning; useful for audits, debates, and research reviews.

Quick Start

Ask the agent to audit every claim, demand explicit evidence, and reveal uncertainties.

Frequently Asked Questions about impostor-syndrome

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I audit analytical reasoning to ensure every claim has explicit evidence?▼

Auditing analytical reasoning requires enforcing explicit evidence for every claim and surfacing unknowns. This process distinguishes knowns from guesses and highlights unstated assumptions to promote epistemic honesty and reduce overconfidence.

What is the best way to tighten conclusions and reduce overconfidence in problem-solving?▼

Tightening conclusions requires a rigorous self-audit that demands verifiable data for each claim. By clearly labeling knowns versus guesses and transparently justifying reasoning trails, you build resilience against overconfidence in problem-solving.

How do I distinguish knowns from guesses during a rigorous review workflow?▼

Distinguishing knowns from guesses involves transparently sourcing and tracing reasoning steps during a rigorous review. The workflow requires grounding claims in verifiable data and explicitly labeling uncertainties to reveal unstated assumptions.

Does this claim verification approach work for analytical debates and research reviews?▼

Claim verification works for analytical debates and research reviews by enforcing explicit evidence and traceable justification trails. It ensures resilience against overconfidence by requiring clear labeling of knowns versus guesses in analytical contexts.

When should I not use a self-audit for prompt design and claim verification?▼

You should avoid self-auditing for claim verification when your workflow lacks verifiable data or transparent sourcing. The process demands explicit evidence trails, making it unsuitable for contexts where grounding conclusions in verifiable data is impossible.