跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 m14-mental-model

M14 Mental Model

Use when learning Rust concepts. Keywords: mental model, how to think about ownership, understanding borrow checker, visualizing memory layout, analogy, misconception, explaining ownership, why does Rust, help me understand, confused about, learning Rust, explain like I'm, ELI5, intuition for, coming from Java, coming from Python, 心智模型, 如何理解所有权, 学习 Rust, Rust 入门, 为什么 Rust

2984 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

官方 description 用英文写明「M14 Mental Model」做什么。中文介绍不改写这段原文,能力边界以文件结构与下方原文为准。

何时用

学习Rust的概念。 关键词:精神模型 如何思考所有权,理解借取检查器,可视化内存布局,类比,误解,解释所有权,为什么Rust,帮助我理解,困惑,学习Rust,解释就像我,ELI5,直觉

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Mental Models、Core Question、Key Mental Models、Coming From Other Languages、Thinking Prompt、Trace Up ↑。

文件分析

文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。

Mental ModelsCore QuestionKey Mental ModelsComing From Other LanguagesThinking PromptTrace Up ↑Trace Down ↓Common MisconceptionsDeprecated ThinkingOwnership VisualizationReference VisualizationLearning Path

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
m14-mental-model
description
Use when learning Rust concepts. Keywords: mental model, how to think about ownership, understanding borrow checker, visualizing memory layout, analogy, misconception, explaining ownership, why does Rust, help me understand, confused about, learning Rust, explain like I'm, ELI5, intuition for, coming from Java, coming from Python, 心智模型, 如何理解所有权, 学习 Rust, Rust 入门, 为什么 Rust
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「m14-mental-model」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-080e8cff4feb88c5-M14-Mental-Model.html
请存为 .cursor/skills/m14-mental-model/SKILL.md 或 .claude/skills/m14-mental-model/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/actionbook/rust-skills' --list

npx skills add 'https://github.com/actionbook/rust-skills' --skill 'm14-mental-model'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版
--- name: m14-mental-model description: "Use when learning Rust concepts. Keywords: mental model, how to think about ownership, understanding borrow checker, visualizing memory layout, analogy, misconception, explaining ownership, why does Rust, help me understand, confused about, learning Rust, explain like I'm, ELI5, intuition for, coming from Java, coming from Python, 心智模型, 如何理解所有权, 学习 Rust, Rust 入门, 为什么 Rust" user-invocable: false --- # Mental Models > **Layer 2: Design Choices** ## Core Question **What's the right way to think about this Rust concept?** When learning or explaining Rust: - What's the correct mental model? - What misconceptions should be avoided? - What analogies help understanding? --- ## Key Mental Models | Concept | Mental Model | Analogy | |---------|--------------|---------| | Ownership | Unique key | Only one person has the house key | | Move | Key handover | Giving away your key | | `&T` | Lending for reading | Lending a book | | `&mut T` | Exclusive editing | Only you can edit the doc | | Lifetime `'a` | Valid scope | "Ticket valid until..." | | `Box` | Heap pointer | Remote control to TV | | `Rc` | Shared ownership | Multiple remotes, last turns off | | `Arc` | Thread-safe Rc | Remotes from any room | --- ## Coming From Other Languages | From | Key Shift | |------|-----------| | Java/C# | Values are owned, not references by default | | C/C++ | Compiler enforces safety rules | | Python/Go | No GC, deterministic destruction | | Functional | Mutability is safe via ownership | | JavaScript | No null, use Option instead | --- ## Thinking Prompt When confused about Rust: 1. **What's the ownership model?** - Who owns this data? - How long does it live? - Who can access it? 2. **What guarantee is Rust providing?** - No data races - No dangling pointers - No use-after-free 3. **What's the compiler telling me?** - Error = violation of safety rule - Solution = work with the rules --- ## Trace Up ↑ To design understanding (Layer 2): ``` "Why can't I do X in Rust?" ↑ Ask: What safety guarantee would be violated? ↑ Check: m01-m07 for the rule being enforced ↑ Ask: What's the intended design pattern? ``` --- ## Trace Down ↓ To implementation (Layer 1): ``` "I understand the concept, now how do I implement?" ↓ m01-ownership: Ownership patterns ↓ m02-resource: Smart pointer choice ↓ m07-concurrency: Thread safety ``` --- ## Common Misconceptions | Error | Wrong Model | Correct Model | |-------|-------------|---------------| | E0382 use after move | GC cleans up | Ownership = unique key transfer | | E0502 borrow conflict | Multiple writers OK | Only one writer at a time | | E0499 multiple mut borrows | Aliased mutation | Exclusive access for mutation | | E0106 missing lifetime | Ignoring scope | References have validity scope | | E0507 cannot move from `&T` | Implicit clone | References don't own data | ## Deprecated Thinking | Deprecated | Better | |------------|--------| | "Rust is like C++" | Different ownership model | | "Lifetimes are GC" | Compile-time validity scope | | "Clone solves everything" | Restructure ownership | | "Fight the borrow checker" | Work with the compiler | | "`unsafe` to avoid rules" | Understand safe patterns first | --- ## Ownership Visualization ``` Stack Heap +----------------+ +----------------+ | main() | | | | s1 ─────────────────────> │ "hello" | | | | | | fn takes(s) { | | | | s2 (moved) ─────────────> │ "hello" | | } | | (s1 invalid) | +----------------+ +----------------+ After move: s1 is no longer valid ``` ## Reference Visualization ``` +----------------+ | data: String |────────────> "hello" +----------------+ ↑ │ &data (immutable borrow) │ +------+------+ | reader1 reader2 (multiple OK) +------+------+ +----------------+ | data: String |────────────> "hello" +----------------+ ↑ │ &mut data (mutable borrow) │ +------+ | writer (only one) +------+ ``` --- ## Learning Path | Stage | Focus | Skills | |-------|-------|--------| | Beginner | Ownership basics | m01-ownership, m14-mental-model | | Intermediate | Smart pointers, error handling | m02, m06 | | Advanced | Concurrency, unsafe | m07, unsafe-checker | | Expert | Design patterns | m09-m15, domain-* | --- ## Related Skills | When | See | |------|-----| | Ownership errors | m01-ownership | | Smart pointers | m02-resource | | Concurrency | m07-concurrency | | Anti-patterns | m15-anti-pattern |

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…