dunning-kruger

dunning-kruger is a skill for Claude Code, Codex from deciqAI/knowledge-skills. It costs 124 tokens per session (1,848 once invoked), scanned A, original, MIT.

A psychology concept describing how people with limited skill in an area may overestimate their ability because they lack the knowledge needed to judge their own performance.

In plain words
What is it for?
Use it when assessing hiring or promotion claims, responding to overconfident opinions from beginners, or checking confidence about unfamiliar technical or AI topics.
Why use it?
It helps separate confidence from demonstrated ability. External measurements and feedback can reveal gaps that self-assessment misses.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when assessing hiring or promotion claims, responding to overconfident opinions from beginners, or checking confidence about unfamiliar technical or AI topics.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/deciqai/knowledge-skills/dunning-kruger
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add deciqAI/knowledge-skills --skill dunning-kruger
Clone the repo
git clone --depth 1 https://github.com/deciqAI/knowledge-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dunning-kruger

README.md
[![agentmods](https://agentmods.dev/badge/skills/deciqai/knowledge-skills/dunning-kruger/github.svg)](https://agentmods.dev/skills/deciqai/knowledge-skills/dunning-kruger)
Your own site
<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/dunning-kruger"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/dunning-kruger/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dunning-kruger

Your own site · 80×15
<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/dunning-kruger"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/dunning-kruger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,848 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00124 $0.01848
Opus 5 $0.00062 $0.00924
Sonnet 5 $0.00025 $0.00370
Haiku 4.5 $0.00012 $0.00185

Measured 9d ago against content hash 52f3c93f431c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dunning-kruger scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

dunning-kruger/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dunning-Kruger Effect

Overview

The Dunning-Kruger effect is the systematic self-assessment asymmetry demonstrated by Kruger & Dunning (1999): bottom-quartile performers overestimate rank by ~50 percentile points; top-quartile performers underestimate by ~5 points. Mechanism: the cognitive skills needed to perform a task are the same ones needed to evaluate performance — so novices lack the metacognition to see their own gap. The corrective is external measurement and feedback, not internal vigilance.

Composes with metacognition, probabilistic-thinking, critical-thinking, and confirmation-bias.

When to Use

  • A novice is expressing high confidence or dismissing expert opinion ("I could do that better")
  • Hiring/promotion decisions are based on candidate self-assessment
  • "How hard could it be?" asked about a domain the asker hasn't worked in
  • Feedback loops are absent; self-assessment is contradicted by external data and rejected
  • Someone mentions "overconfident," "doesn't know what they don't know," or "imposter syndrome" (the inverse)
  • Confidence about AI capabilities/limits, AI capex or valuations, or AI adoption after light exposure ("I built a demo, so I understand production AI"; "we can ship this AI feature in a quarter")

Not when: person is a known expert with an external track record; domain has tight, recent feedback loops that already calibrate performance; high-confidence claim is self-deprecating (actual metacognition signal).

Coaching Novices (Adaptive Front Door)

  • Engine mode: user brings a specific confidence claim → diagnose directly.
  • Coach mode: user unfamiliar → guide step by step.

In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.

  1. One-line: confidence is not a proxy for competence unless the person has metacognitive feedback — check against external data.
  2. Check fit. If external performance data exists and the person can see it, the bias may already be corrected. If unsure, ask: "Are you diagnosing a specific claim, or learning the framework?"
  3. Elicit the specific claim and basis for confidence. What is being claimed? Self-assessment, external metrics, peer comparison, formal evaluation?

[WAIT — do not advance until user responds]

  1. One question at a time: what would they accept as evidence they were wrong? How much feedback have they received? Bottom, middle, or top of comparable performers by an external measure?

[WAIT — do not advance until user responds]

  1. Close: name an external feedback mechanism (calibration test, peer review, blind evaluation) + a re-measurement schedule.

[WAIT — do not advance until user responds]

Read the full file on GitHub · 116 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 116 lines · 124 tokens per session scan A 52f3c93f431c

Subscribe to this mod's changes

dunning-kruger is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 10d ago), licensed MIT. It adds 124 tokens to every session and 1,848 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

voice-builder

Ingests 5–20 of the user's writing samples and distils a reusable voice-profile.md — signature phrases, sentence-length distribution, opener/closer habits, punctuation quirks, vocabulary do/don't lists, tone sliders, and three calibration paragraphs with self-checks. Other skills load this file so every post sounds…

alebgl77/claude-inc · 110 tokens

english-swe-daily

Daily English expression coach for intermediate software engineers. Use this skill whenever the user wants to improve their spoken or written English in a software engineering work context — especially for standups, Slack messages, 1:1s, meetings, giving feedback on code, asking for help, disagreeing politely, or…

wquguru/skills · 168 tokens

agent-teacher

A teaching aid that explains technical ideas with a small runnable code example and a guided walkthrough. It is meant for learning how something works, not fixing existing code.

JackyYang258/agent-teacher · 151 tokens

lecture-notes

Transform raw lecture content (transcript, plain text, or slides) into clean, structured, study-ready notes in Markdown. Use this skill whenever the user pastes lecture material — a transcript (with or without timestamps), course/lecture text, or slide content — and asks for notes, a summary, or help studying. Also…

ChristinaAndrinopoyloy/claude-skills · 125 tokens

skill-creation-walkthrough

Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the SKILL.md file, structuring reference material, and making it trigger reliably. Use when you want to package a workflow, framework, or repeated task into a reusable Skill, when an existing skill is not…

rampstackco/claude-skills · 135 tokens

master-debate

A skill for running an adversarial, multi-round debate between two Buddhist teachers. It is designed for questions where the teachers argue from different positions.

xr843/Master-skill · 127 tokens