Home / deciqai / knowledge-skills · GitHub

critical-thinking SKILL.md skillA

critical-thinking from deciqai/knowledge-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add deciqai/knowledge-skills/critical-thinking@git:20261025.cb4e537

Pins git:20261025.cb4e537 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: deciqai/knowledge-skills
Path: critical-thinking/SKILL.md
Versions recorded: 5
Latest version: git:20261025.cb4e537, committed Oct 25, 2026
First version recorded: Jul 16, 2026
Size: 9,492 bytes
Repository stars: 13
License: MIT

"Activate when: user says 'challenge my thinking', 'play devil's advocate', 'what's the strongest counter-argument', 'ACH', 'analysis of competing hypotheses'; user needs to evaluate a high-stakes claim or decision with multiple possible interpretations; user suspects motivated reasoning or a team is converging too fast on one answer.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Critical Thinking

## Overview

**Critical thinking** evaluates a conclusion by **explicitly testing it against alternative interpretations** — the conclusion that survives the most disconfirmation attempts is the one to act on, not the one with the most confirming examples. Operationalized by **Richards J. Heuer Jr.** (CIA, 1999) as **Analysis of Competing Hypotheses (ACH)**: a matrix marking each evidence-hypothesis pair as Consistent / Inconsistent / N/A. The hypothesis with the **fewest Inconsistencies** wins.

**Compose:** [first-principles](../first-principles/SKILL.md) (surface assumptions) · [probabilistic-thinking](../probabilistic-thinking/SKILL.md) (calibrate evidence) · [inversion](../inversion/SKILL.md) (generate alternatives). Critical thinking = *evaluation*; first-principles = *construction*; occams = *selection*; second-order = *projection*.

## When to Use

- High-stakes claim (yours or someone else's) that needs evaluation
- Multiple interpretations of the same evidence are possible
- Motivated reasoning detected — conclusion shaped by what you want to be true
- Team converging on a hypothesis too fast without seriously considering alternatives
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add deciqai/knowledge-skills/critical-thinking@sha256:25c26cbc4f9fd16d

The line at the top of this page pins the label git:20261025.cb4e537, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_6dvejceleapqw3cg.svg)](https://markdownregistry.com/a/art_6dvejceleapqw3cg)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Jul 16, 2026 and Oct 25, 2026, about one every 25 days.

version	committed	commit	size	audit
git:20261025.cb4e537 latest	2026-10-25	cb4e537	9,492 B	A	view · diff
git:20260816.be84677	2026-08-16	be84677	9,492 B	A	view · diff
git:20260719.ed3f856	2026-07-19	ed3f856	9,492 B	A	view · diff
git:20260717.2ed857e	2026-07-17	2ed857e	9,492 B	A	view · diff
git:20260716.fac12bf	2026-07-16	fac12bf	9,492 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (9492 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

deciqai/knowledge-skills · 13 stars · license MIT · pushed 2026-10-25 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_6dvejceleapqw3cg
GET https://markdownregistry.com/api/v1/resolve?ref=deciqai/knowledge-skills/critical-thinking
GET https://markdownregistry.com/api/v1/blob/25c26cbc4f9fd16d49db9b7c5aac27f92c4ed8ec1b290f46da1b385472cf5139

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from deciqai/knowledge-skills

10-10-10 SKILL.md skill

deciqai/knowledge-skills · 10-10-10/SKILL.md · Activate when: someone is making a decision under emotional pressure and worries they'll regret it later; someone says…