Testing & QAlow risk

n-mental-models

Select and apply relevant mental models. Use when explicitly invoked.

thepraggyverse/naval·skills/n-mental-models/SKILL.md

32/ 100推薦值

↓

匯入這個 Skill

選擇你的 coding agent，複製專案級或個人級安裝指令。

固定至平台收錄的 commit

匯入目前專案.agents/skills/n-mental-models

npx skills add https://github.com/thepraggyverse/naval/tree/256ecb9c6c45597d6e30df61c4ebf7a2ce65dddb/skills/n-mental-models -a codex -y

匯入個人環境~/.agents/skills/n-mental-models

npx skills add https://github.com/thepraggyverse/naval/tree/256ecb9c6c45597d6e30df61c4ebf7a2ce65dddb/skills/n-mental-models -a codex -g -y

手動放置目錄.agents/skills/n-mental-modelsOfficial docs ↗

匯入目前專案.claude/skills/n-mental-models

npx skills add https://github.com/thepraggyverse/naval/tree/256ecb9c6c45597d6e30df61c4ebf7a2ce65dddb/skills/n-mental-models -a claude-code -y

匯入個人環境~/.claude/skills/n-mental-models

npx skills add https://github.com/thepraggyverse/naval/tree/256ecb9c6c45597d6e30df61c4ebf7a2ce65dddb/skills/n-mental-models -a claude-code -g -y

手動放置目錄.claude/skills/n-mental-modelsOfficial docs ↗

匯入目前專案.agents/skills/n-mental-models

npx skills add https://github.com/thepraggyverse/naval/tree/256ecb9c6c45597d6e30df61c4ebf7a2ce65dddb/skills/n-mental-models -a github-copilot -y

匯入個人環境~/.copilot/skills/n-mental-models

npx skills add https://github.com/thepraggyverse/naval/tree/256ecb9c6c45597d6e30df61c4ebf7a2ce65dddb/skills/n-mental-models -a github-copilot -g -y

手動放置目錄.agents/skills/n-mental-modelsOfficial docs ↗

匯入目前專案.agents/skills/n-mental-models

npx skills add https://github.com/thepraggyverse/naval/tree/256ecb9c6c45597d6e30df61c4ebf7a2ce65dddb/skills/n-mental-models -a cursor -y

匯入個人環境~/.cursor/skills/n-mental-models

npx skills add https://github.com/thepraggyverse/naval/tree/256ecb9c6c45597d6e30df61c4ebf7a2ce65dddb/skills/n-mental-models -a cursor -g -y

手動放置目錄.agents/skills/n-mental-modelsOfficial docs ↗

匯入目前專案.agents/skills/n-mental-models

npx skills add https://github.com/thepraggyverse/naval/tree/256ecb9c6c45597d6e30df61c4ebf7a2ce65dddb/skills/n-mental-models -a gemini-cli -y

匯入個人環境~/.gemini/skills/n-mental-models

npx skills add https://github.com/thepraggyverse/naval/tree/256ecb9c6c45597d6e30df61c4ebf7a2ce65dddb/skills/n-mental-models -a gemini-cli -g -y

Native Gemini CLIgemini skills install https://github.com/thepraggyverse/naval.git --scope workspace --path skills/n-mental-models

手動放置目錄.agents/skills/n-mental-modelsOfficial docs ↗

⚠ 安裝指令使用開源 skills CLI。執行前請檢查來源、腳本與權限。

Skill 指令

在 GitHub 查看原始檔案 ↗

# Naval Mental Models

## Purpose

Use compounding, incentives, evolution, game theory, complexity, inversion, and probability.

## Read First

- `references/concept.md`

Read only the files needed for the current request.
All runtime references are local to this skill so the folder can be copied independently.

## Workflow

1. Define the system, actors, incentives, time horizon, and uncertain outcome.
2. Choose two to four non-redundant models from foundational domains.
3. Use each model to make a prediction and identify a blind spot.
4. Reconcile disagreements and select the observation that best separates the models.

## Output

Return these checkable fields:

- System frame
- Selected models
- Predictions
- Model conflicts
- Discriminating test

## Boundaries

Use n-inversion-filter for failure-first analysis and n-falsifiability-truth for one claim's testability.

Paraphrase by default and do not reproduce long passages from the book.
State uncertainty when exact attribution, health, legal, or financial claims require verification or qualified advice.

## Example

User: "Which mental models apply here?"

Assistant: Use the workflow above and return system frame, selected models, predictions.