Metacognition

Metacognition is an AI Engineering skill for Claude Code, published by human-avatar in skills-for-humanity.

220 stars23 forkson human-avatar/skills-for-humanityAdded 2026/09/04Repository updated 2026/07/15

claude-codeclaude-code-plugincognitive-frameworkscreativitydecision-makingethicsmental-modelsproblem-solvingreasoningsystems-thinking

Install in seconds

Install Metacognition

Copy Metacognition into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/human-avatar/skills-for-humanity/tree/main/skills/s4h-cognition-metacognition ~/.claude/skills/s4h-cognition-metacognition

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/human-avatar/skills-for-humanity.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/s4h-cognition-metacognition/SKILL.md in human-avatar/skills-for-humanity
Installs to: ~/.claude/skills/s4h-cognition-metacognition
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2970 skills

What Metacognition does

Metacognition assesses how well you understand a specific problem by checking comprehension, prediction, contradictions, and confidence calibration. Use it when you need to judge what you know, what you may be missing, or how reliable your reasoning is.

Metacognition is cataloged under AI Engineering on DirSkills. Metacognition comes from a repository tagged claude-code, claude-code-plugin, cognitive-frameworks, creativity and decision-making.

Documentation

README

Excerpt

Cognition: Metacognition

Metacognition — the capacity to think about your own thinking — is what separates competent performance from expert adaptation. John Flavell, who established metacognition as a formal field of study at Stanford in the 1970s, identified three interlocking components: metacognitive knowledge (what you know about cognition in general and your own cognitive patterns in particular), metacognitive monitoring (tracking your comprehension and reasoning in real time), and metacognitive control (adjusting your approach when monitoring reveals a problem). All three are necessary. Most people engage in only the first.

This is the opening of the README. Read the full README on GitHub.

Commands Metacognition provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/s4h-epistemology-epistemic-status
/s4h-probability-confidence-calibration
/s4h-cognition-mental-models

Frequently asked about Metacognition

What else does human-avatar publish alongside Metacognition?
Metacognition is one of 25 skills that DirSkills catalogs from human-avatar/skills-for-humanity, the repository it ships in. Its siblings there include Aesthetic, Aesthetic Coherence Check and Aesthetic Elegance Testing. Each one is a separate skill with its own page in this directory, installs the same way Metacognition does, and is maintained by human-avatar in that same repository. The rest of the collection is listed on the human-avatar/skills-for-humanity page.
How does Metacognition compare to other AI Engineering skills?
Metacognition ranks #2585 by stars among the 2970 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Metacognition against them. Open each page to compare what they document and how they install.