菜单
Create production-ready skills from expert knowledge. Extracts domain expertise and system ontologies, uses scripts for deterministic work, loads knowledge progressively. Use when building skills that must work reliably in production.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | create-expert-skill |
| description | Create production-ready skills from expert knowledge. Extracts domain expertise and system ontologies, uses scripts for deterministic work, loads knowledge progressively. Use when building skills that must work reliably in production. |
| version | 2.2 |
Transform expert knowledge into production-ready skills that combine domain expertise with system-specific understanding.
AI assistants fail not because they lack intelligence, but because they lack:
Both are required. Domain knowledge without system context produces generic output. System knowledge without domain expertise produces structurally correct but semantically wrong results.
Assess → Discover (Expertise + Ontology) → Design → Create → Refine → Ship
Create a skill when:
Don't create for: one-time tasks, basic knowledge Claude already has, rapidly changing content.
Deep knowledge that transcends any specific company:
Example (LEDES validation): LEDES 98B vs XML 2.0 formats, UTBMS code taxonomy, date format requirements, required vs optional fields.
How the skill maps to specific systems and organizations:
Example (LEDES validation): Firm-specific timekeeper codes, matter numbering conventions, approved billing rates, outside counsel guideline requirements.
When starting, I'll ask about:
skill-name/
├── SKILL.md # Layer 1: Core (300-500 tokens)
├── scripts/ # Layer 0: Automation (0 tokens to run)
│ └── validate.py
└── resources/ # Layer 2: Details (loaded selectively)
└── ADVANCED.md
Layer 0 (Scripts): Free execution, structured JSON output Layer 1 (SKILL.md): Loaded when triggered - keep lean Layer 2 (Resources): Fetched only when specific section needed
| Technique | Instead of | Do this | Savings |
|---|---|---|---|
| Scripts | 500 tokens explaining validation | python scripts/validate.py | ~450 tokens |
| Reference | Inline schema (200 tokens) | Link to resources/schema.json | ~185 tokens |
| Layer 2 | Everything in SKILL.md | Link to resources/ADVANCED.md | ~750 tokens |
<Action> <Object> for <Purpose>. Use when <Trigger>.
Example: "Validate billing data for system migration. Use before importing invoices."
When content is finalized:
python scripts/package_skill.py skill-name 1.0
Creates skill-name-v1.0.zip with:
See resources/templates/ for:
See resources/examples/ for domain-specific patterns.
Before shipping:
Version: 2.2 | Target: <500 tokens Layer 1