Agent skill

thinking-map-territory

Recognize limits of mental models and diagrams. Use when models diverge from reality, debugging expectation mismatches, or questioning abstraction accuracy.

majiayu000534★ · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill thinking-map-territory --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 9 KB
Bundled scripts: none
Path: skills/analysis/thinking-map-territory/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Map-Territory Thinking ## Overview Map-Territory thinking, originated by Alfred Korzybski and popularized in general semantics, reminds us that **"the map is not the territory."** Every representation—mental model, diagram, metric, specification, or abstraction—is a simplified view that necessarily loses information. Confusing the map with the territory leads to flawed decisions, debugging dead-ends, and misaligned expectations. **Core Principle:** All models are wrong; some are useful. The question is: how wrong, and useful for what? ## When to Use - Debugging when behavior doesn't match expectations - Evaluating whether documentation/specs match implementation - Questioning metrics that seem to tell the "full story" - Architecture decisions based on diagrams or models - When a "perfect plan" meets messy reality - Resolving disagreements where parties hold different mental models - Analyzing why estimates consistently miss reality Decision flow: ``` Expectation ≠ Reality? → yes → Are you trusting a model/abstraction? → yes → CHECK MAP-TERRITORY FIT ↘ no → Model exists but isn't explicit ↘ no → Model may be accurate (verify anyway) ``` ## Key Concepts ### 1. Maps Are Abstractions

What's inside
Steps it walks through
  1. Overview
  2. When to Use
  3. Key Concepts
  4. 1. Maps Are Abstractions
  5. 2. Multiple Maps, One Territory
  6. 3. Map-Territory Confusion
  7. 4. Abstraction Leakage
  8. The Map-Territory Alignment Process
  9. Step 1: Identify Your Maps
  10. Step 2: Assess Map Freshness
  11. Step 3: Check Correspondence
  12. Step 4: Identify Missing Maps
  13. Step 5: Calibrate Confidence
  14. Map-Territory Mismatches by Domain
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the thinking-map-territory skill do?

Recognize limits of mental models and diagrams. Use when models diverge from reality, debugging expectation mismatches, or questioning abstraction accuracy.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill thinking-map-territory --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going