logical-thinking SKILL.md skillA

logical-thinking from thegoat395/codex-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add thegoat395/codex-skills/logical-thinking@git:20260910.feff772

Pins git:20260910.feff772 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
thegoat395/codex-skills
Path
skills/logical-thinking/SKILL.md
Versions recorded
3
Latest version
git:20260910.feff772, committed Sep 10, 2026
First version recorded
Aug 30, 2026
Size
5,056 bytes
Repository stars
137
License
MIT

Determine what premises and evidence warrant.

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

# Logical Thinking

Produce the strongest conclusion the available premises warrant, including `unknown`, conditional, or no conclusion when appropriate. Logical rigor means choosing the right inference system, preserving meaning and scope, checking each decisive step, and refusing to strengthen the result beyond its proof obligations.

## Scale the proof to the question

Adapt the inference family; do not impose a universal template. Preserve meaning, units, scope and quantifiers. Test whether premises can hold while the conclusion fails; use decisive calculations, solvers, tests or observations. Correlated self-review is not independent verification.

For **consequential, multi-step, ambiguous or contested inference**, read [proof and verification](references/proof-and-verification.md) plus the applicable family below for maps, step checks, conclusion types and adversarial tests. Simple entailment/calculation remains direct.

Use conditional or unknown when warranted. `Proven`, `must`, `causes`, `always` and `impossible` require their own proof burden.

## Normalize the problem

Before inference, identify:

- exact question and candidate conclusion;
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add thegoat395/codex-skills/logical-thinking@sha256:6496f9712089019e

The line at the top of this page pins the label git:20260910.feff772, 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 badge

[![mdr](https://markdownregistry.com/badge/art_5ynkzluu2worlihg.svg)](https://markdownregistry.com/a/art_5ynkzluu2worlihg)

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

Versions

The registry has recorded 3 versions of this file, between Aug 30, 2026 and Sep 10, 2026, about one every 6 days.

versioncommittedcommitsizeaudit
git:20260910.feff772 latest2026-09-10 feff772 5,056 BA view · diff
git:20260905.f7824ba2026-09-05 f7824ba 4,986 BA view · diff
git:20260830.0196be92026-08-30 0196be9 8,807 BA 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 (5056 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

thegoat395/codex-skills · 137 stars · license MIT · pushed 2026-10-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_5ynkzluu2worlihg
GET https://markdownregistry.com/api/v1/resolve?ref=thegoat395/codex-skills/logical-thinking
GET https://markdownregistry.com/api/v1/blob/6496f9712089019ef20775264c64c640f29d61f92f8b2f15c6cddc8f973b6898

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 thegoat395/codex-skills

AGENTS.md AGENTS.md file
thegoat395/codex-skills · AGENTS.md
git:20260910.feff772 · audit A · 137 stars
accessibility-audit-websites SKILL.md skill
thegoat395/codex-skills · skills/accessibility-audit-websites/SKILL.md · Audit semantic and keyboard accessibility.
git:20260908.40bbe41 · audit A · 137 stars
accessibility-performance-polish SKILL.md skill
thegoat395/codex-skills · skills/accessibility-performance-polish/SKILL.md · Finish accessibility and performance details.
git:20260910.feff772 · audit A · 137 stars
agent-evaluation-operations SKILL.md skill
thegoat395/codex-skills · skills/agent-evaluation-operations/SKILL.md · Evaluate agent and skill behavior or routing.
git:20260905.f7824ba · audit A · 137 stars
agent-memory-provenance SKILL.md skill
thegoat395/codex-skills · skills/agent-memory-provenance/SKILL.md · Design memory provenance and tenant isolation.
git:20260905.f7824ba · audit A · 137 stars
agent-orchestration-architecture SKILL.md skill
thegoat395/codex-skills · skills/agent-orchestration-architecture/SKILL.md · Resolve agent ownership and handoff design.
git:20260905.f7824ba · audit A · 137 stars
animation-easing-language SKILL.md skill
thegoat395/codex-skills · skills/animation-easing-language/SKILL.md · Define coherent motion timing and rhythm.
git:20260905.f7824ba · audit A · 137 stars
animation-jank-qa SKILL.md skill
thegoat395/codex-skills · skills/animation-jank-qa/SKILL.md · Diagnose a concrete rendered hitch or stutter.
git:20260905.f7824ba · audit A · 137 stars
animation-tool-router SKILL.md skill
thegoat395/codex-skills · skills/animation-tool-router/SKILL.md · Resolve motion tools or native View Transitions.
git:20260905.f7824ba · audit A · 137 stars
anti-generic-website-review SKILL.md skill
thegoat395/codex-skills · skills/anti-generic-website-review/SKILL.md · Repair interchangeable website design patterns.
git:20260910.feff772 · audit A · 137 stars
brand-voice-to-ui-copy SKILL.md skill
thegoat395/codex-skills · skills/brand-voice-to-ui-copy/SKILL.md · Translate brand voice into interface microcopy.
git:20260905.f7824ba · audit A · 137 stars
browser-inspection-workflow SKILL.md skill
thegoat395/codex-skills · skills/browser-inspection-workflow/SKILL.md · Coordinate rendered behavior and state evidence.
git:20260905.f7824ba · audit A · 137 stars

Every file in thegoat395/codex-skills

Browse by kind, by grade A, or by owner.