个人技能库，数十年累积价值。 技能不是工具。它们是冻结的决策。 每项技能都编码了对重要性、失败性和有效性判断的判断。

---

这是什么

一套精心策划的智能体技能集——可重复使用的智能单元，教AI编码智能体自主执行特定任务。

每个技能编码：

• 这里什么重要？（焦点）
• 会出什么问题？（护栏）
• 最快正确的路径是什么？（判断）
• 我怎么知道我完成了？（验证）

---

哲学

这个门槛比MIT、OpenAI或Google更高——因为这优化的是个人吞吐量、上下文优势和问题到解决方案的压缩，而不是协调、发表或规模化。

核心规则

如果两个技能在同一查询下合理触发，至少有一个设计错误。

---

结构

---

技能解剖学

SKILL.md 格式

---

钩子：零开销测量

Claude Code 钩子会自动追踪技能使用情况，无需人工干预。

技能如何被发现

当克劳德激活技能时，会读出 SKILL.md：

mjs-skills

Personal skill library that compounds value over decades. Skills are not tools. They are frozen decisions. Each skill encodes judgment about what matters, what fails, and what works.

---

What This Is

A curated collection of Agent Skills — reusable units of intelligence that teach AI coding agents how to perform specific tasks autonomously.

Each skill encodes:

• What matters here? (focus)
• What can go wrong? (guardrails)
• What is the fastest correct path? (judgment)
• How do I know I’m done? (verification)

---

Philosophy

Traditional: You write code → Code runs → Application works
Agentic:     You write Skills → AI learns patterns → AI writes code → Application works

The bar is higher than MIT, OpenAI, or Google — because this optimizes for personal throughput, context dominance, and problem-to-solution compression, not coordination, publication, or scale.

Core Rule

If two skills plausibly trigger on the same query, at least one is incorrectly designed.

---

Structure

mjs-skills/
├── .claude/
│   ├── skills/                    # The actual skills (22 total)
│   │   ├── meta/                  # Skills about skills
│   │   ├── mcp-powered/           # MCP server wrappers
│   │   ├── infrastructure/        # K8s & cloud
│   │   ├── application/           # Service scaffolding
│   │   ├── ui-patterns/           # Chat & frontend
│   │   ├── integration/           # Connecting services
│   │   ├── devops/                # Deployment & docs
│   │   └── voice/                 # Voice interfaces
│   │
│   ├── hooks/                     # Evaluation & tracking
│   │   ├── track-prompt.sh        # Log user prompts
│   │   ├── track-skill-start.sh   # Detect skill activation
│   │   ├── track-skill-end.sh     # Capture verify.py results
│   │   └── analyze-skills.py      # Weekly usage analysis
│   │
│   └── activity-logs/             # Passive data collection
│       ├── prompts.jsonl
│       └── skill-usage.jsonl
│
├── research/                      # Design documents
│   ├── skill-design-reference.md  # How to build skills
│   ├── h3-skills-master-prd.md    # What skills to build
│   └── skills-evaluation-prd.md   # How to measure value
│
├── spec/                          # Agent Skills Specification
│   └── ...                        # (cloned from agentskills.io)
│
├── CONSTITUTION.md                # Governance principles
└── README.md                      # You are here

---

Skill Anatomy

skill-name/
├── SKILL.md              # YAML frontmatter + instructions (~300 tokens)
├── scripts/
│   ├── verify.py         # Returns 0 (success) or 1 (failure)
│   └── deploy.sh         # Optional: execution script
├── references/           # Optional: deep docs (loaded on-demand)
└── templates/            # Optional: reusable scaffolds

SKILL.md Format

---
name: deploying-kafka-k8s
description: |