菜单
Create and maintain custom Skills with correct SKILL.md metadata, strong trigger-aware descriptions, concise instructions, progressive disclosure, and validation loops. Use when the user asks to write, improve, review, or organize a Skill.
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
Apply Clean Code principles (meaningful names, small functions, error handling, TDD, SRP, smells & heuristics) when authoring, refactoring, or reviewing code—especially TypeScript. Use when the user asks for clean code, refactoring, extract function or class, code smell or maintainability review, readable tests, or Robert C. Martin's Clean Code rules.
Detect, name, and remediate code smells using the classic taxonomy (Bloaters, Object-Orientation Abusers, Change Preventers, Dispensables, Couplers) when reviewing, refactoring, or authoring code. Use when the user asks to find code smells, review code for maintainability, identify long methods/large classes/duplicate code/feature envy, or wants refactoring guidance tied to a named smell.
Create and maintain custom subagent definition files for any AI agent platform, with strong descriptions, tight tool scope, and explicit handoff contracts. Use when the user asks to create, improve, or standardize a subagent.
Teach and apply the Chain of Responsibility (CoR) pattern to pass requests along a dynamic chain of handlers where each can process or forward the request. Use when users ask about CoR, Chain of Command, middleware pipelines, sequential validation, request bubbling, or comparing CoR to Decorator, Command, or Mediator.
Teach and apply the Command pattern to encapsulate requests as objects for decoupled invocation, queuing, scheduling, logging, and undo/redo workflows. Use when users ask about Command, Action, Transaction, invoker-receiver decoupling, reversible operations, or comparing Command with Strategy, Chain of Responsibility, or Memento.
Teach and apply the Iterator pattern to traverse collections without exposing their internal structure. Use when users ask about Iterator, custom traversal algorithms, decoupling traversal from collections, parallel iteration, lazy iteration, or comparing Iterator to for-each loops and language-native iterables.
| name | create-skills |
| description | Create and maintain custom Skills with correct SKILL.md metadata, strong trigger-aware descriptions, concise instructions, progressive disclosure, and validation loops. Use when the user asks to write, improve, review, or organize a Skill. |
Build production-ready custom Skills that AI agents can discover and apply reliably across real tasks.
Use this skill when the user asks to:
Follow these phases in order.
Before creating or editing any Skill files, ask targeted clarifying questions and wait for answers.
Minimum question set:
Do not draft final skill content until these answers are confirmed.
Capture:
If details are still missing, ask concise follow-up questions before writing files.
Create YAML frontmatter before writing instructions.
Requirements:
name: lowercase letters, numbers, hyphens; max 64 charsdescription: non-empty, max 1024 chars, third person, includes both:
Good description pattern: ". Use when <user intent/keywords>."
Naming guidance:
writing-documentation, testing-code)helper, utils, toolsname unless the skill is intentionally vendor-specificMatch specificity to task fragility:
Default to one recommended path. Add alternatives only when needed.
Keep SKILL.md focused and operational:
Prefer under 500 lines for fast loading and maintenance.
Put essentials in SKILL.md, move details to linked files:
REFERENCE.md for deep API/reference detailEXAMPLES.md for many examplesscripts/* for deterministic repeatable operationsReference files one level deep from SKILL.md.
For longer reference files, include a compact table of contents near the top.
For complex tasks, include a checklist-style workflow and explicit validation cycle:
For quality-critical operations, require loop behavior: "run validator -> fix issues -> rerun validator -> proceed only when clean."
Before large documentation expansion:
Test with the model families you intend to use.
Check:
/)When asked to create a Skill, produce:
namedescriptionSKILL.md contentsBefore this output, include a "Requirements Confirmed" section summarizing the user's answers to clarification questions.
Then implement by creating files in the requested scope.
Use this template when generating new Skills:
---
name: <skill-name>
description: <what it does>. Use when <when to trigger>.
---
# <Skill Title>
## Purpose
<1-2 lines about intended outcome>
## When To Use
- <trigger 1>
- <trigger 2>
## Inputs
- <required input>
- <optional input>
## Workflow
1. <step 1>
2. <step 2>
3. <step 3>
## Output Format
<exact expected structure, checklist, or schema>
## Validation
- <quality check 1>
- <quality check 2>
## Examples
<minimal high-signal example>
helper-skill or utilsSKILL.md -> advanced.md -> details.md)scripts\tool.pyIf scripts are included:
ServerName:tool_name)Rate each area from 0-2 (target total >= 10):
name and description satisfy constraintsSKILL.md is concise (prefer under 500 lines)SKILL.md