What it does
Write professional-grade skills for agents, validate them using LLMs, and maintain a lean context window.
- Connects Instruction files the AI reads
- Account or key Not confirmed (README mentions a key or .env file)
- Category 自动化与智能体
给作者:在 README 中加徽章
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/mgechev-skills-best-practices)相似的 Skill
同类工作,排序与 Skill 列表相同
Skill 和 MCP 有什么不同
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
适用的应用
开发者未说明 · SKILL.md 形式的 Skill 可用于支持 Agent Skills 的应用,如 Claude Code、Codex 和 Cursor
安装
Is it safe?
- Who made it
GitHub account mgechev (person), 16 years old
- Use and upkeep
★ 2,297 stars · code last changed 2026年7月27日
- Any scripts?
1 scripts that can run on a computer: scripts/validate-metadata.py
- Uses the internet?
No internet calls found in the scripts
- Changes machine-wide settings?
No hooks or writes to machine settings found
Checked automatically from the repo files at commit a0bfa56 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
Option 1Upload to claude.ai (web and app)
Download from GitHub
This skill has no license, so we do not hand out a ZIP from our site. Download it from GitHub and arrange the folder yourself, or use "Let the AI install it" above, which is easier
Download from GitHub (whole repo) ↗
Unzip it, then zip only the skill folder again. The ZIP must have a skill-creator folder with SKILL.md at the top level, no loose files
Open Skills on claude.ai and upload
+Create skillUpload a skillpick skill-creator.zip
No Upload button? Turn on file creation first
SettingsCapabilitiesCode execution and file creation
Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free
Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)
Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)
Checked against official docs 2026年11月12日 · Source: support.claude.com, support.claude.com, code.claude.com
Option 1让 Claude Code 帮你安装
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /skill,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
For Terminal users
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
打开终端
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
把 skill 文件夹复制到 ~/.claude/skills
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/mgechev/skills-best-practices.git /tmp/popnx-skill-mgechev-skills-best-practices-a0bfa56 && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-mgechev-skills-best-practices-a0bfa56/skill' ~/.claude/skills/skill重新打开 Claude Code,输入 /skill,或直接提出相关任务,Claude 会自动选用
ChatGPT 桌面应用
ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
Option 1让 ChatGPT 帮你安装
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Option 2自己放入文件夹
把 skill-creator 文件夹放到 ~/.agents/skills/skill-creator
~ 是你的主文件夹($HOME)
For Terminal users
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
打开终端
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
把 skill 文件夹复制到 ~/.agents/skills
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/mgechev/skills-best-practices.git /tmp/popnx-skill-mgechev-skills-best-practices-a0bfa56 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-mgechev-skills-best-practices-a0bfa56/skill' ~/.agents/skills/skill
安装之后
- ChatGPT 桌面应用:打开侧边栏中的 Skills,确认 Skill 已出现
- 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
- Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
网页版和手机版 ChatGPT
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Option 1让 Codex 帮你安装
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
For Terminal users
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
打开终端
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
把 skill 文件夹复制到 ~/.agents/skills
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/mgechev/skills-best-practices.git /tmp/popnx-skill-mgechev-skills-best-practices-a0bfa56 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-mgechev-skills-best-practices-a0bfa56/skill' ~/.agents/skills/skill重新打开 Codex 并提出相关任务,Codex 会列出这个 skill
Option 1让 Cursor 帮你安装
复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 skill
Checked against official docs 2026年11月12日 · Source: cursor.com
For Terminal users
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
打开终端
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
把 skill 文件夹复制到 ~/.cursor/skills
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/mgechev/skills-best-practices.git /tmp/popnx-skill-mgechev-skills-best-practices-a0bfa56 && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-mgechev-skills-best-practices-a0bfa56/skill' ~/.cursor/skills/skill在 Cursor 的 Agent 聊天中输入 / 并选择 skill
Option 1Let the AI install it
适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
For Terminal users
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
✓ 命令已检查 2026年11月18日
查看原始 SKILL.md
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
4,313 个字符 · 在 GitHub 打开完整文件
---
name: skill-creator
description: Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural instructions, or optimizing metadata for discoverability. Don't use for general documentation, non-agentic library code, or README files.
---
# Skill Authoring Procedure
Follow these steps to generate a skill that adheres to the agentskills.io specification and progressive disclosure principles.
## Step 1: Initialize and Validate Metadata
1. Define a unique `name`: 1-64 characters, lowercase, numbers, and single hyphens only. **This must exactly match the parent directory name** (e.g., name `angular-testing` must live in `angular-testing/SKILL.md`).
2. Draft a `description`: Max 1,024 characters, written in the third person. Include positive triggers ("Use when...") and negative triggers ("Don't use for...").
3. **Execute Validation Script:** Run the validation script to ensure compliance before proceeding:
`python3 scripts/validate-metadata.py --name "[name]" --description "[description]"`
4. If the script returns an error, self-correct the metadata based on the `stderr` output and re-run until successful.
## Step 2: Structure the Directory
1. Create the root directory using the validated `name`.
2. Initialize the following subdirectories:
* `scripts/`: For tiny CLI tools and deterministic logic.
* `references/`: For flat (one-level deep) context like schemas or API docs.
* `assets/`: For output templates, JSON schemas, or static files.
3. Ensure no human-centric files (such as `README.md`, `CHANGELOG.md`, `INSTALLATION.md`) are created.
## Step 3: Draft Core Logic (SKILL.md)
1. Use the template in `assets/SKILL.template.md` as the starting point.
2. Write all instructions in the **third-person imperative** (e.g., "Extract the text," "Run the build").
3. **Apply Specific, Procedural Formatting:**
* **Use Step-by-Step Numbering:** Define the workflow as a strict chronological sequence. Clearly map out decision trees (e.g., *"Step 2: If source maps are required, run `scripts/build.sh`. Otherwise, skip to Step 3."*).
* **Provide Concrete Templates:** If an output has a specific structure, place a template in `assets/` and command the agent to copy its structure instead of describing it in text.
* **Use Consistent, Specific Terminology:** Use identical, domain-native terms throughout (e.g., in Angular, use "template" consistently instead of "html" or "view").
4. **Enforce Progressive Disclosure:**
* Keep the main `SKILL.md` under 500 lines.
* If a procedure requires a large schema, complex rule set, or bulky context, move it to a flat file in `references/`.
* Command the agent to read the specific file only when needed (JiT loading): *"Read references/api-spec.md to identify the correct endpoint."*
## Step 4: Identify and Bundle Scripts
1. Identify "fragile" tasks (regex, complex parsing, or repetitive boilerplate).
2. Outline a single-purpose script for the `scripts/` directory designed as a tiny CLI with arguments.
3. Ensure the script uses standard output (stdout/stderr) to communicate success or failure. **Write descriptive, human-readable error messages** so the agent knows exactly how to self-correct without user intervention.
## Step 5: Skill Composition (Optional)
If a skill is complex, compose it using router/subskill patterns:
1. Create a high-level router skill.
2. Define conditional triggers or procedures referencing other specific skill folders (e.g., "To build the client, see [path to client-build skill]. To build the server, see [path to server-build skill].").
## Step 6: Final Logic Validation
1. Review the `SKILL.md` for "hallucination gaps" (points where the agent is forced to guess).
2. Verify all file paths are **relative** and use forward slashes (`/`).
3. Cross-reference the final output against `references/checklist.md`.
## Error Handling
* **Metadata Failure:** If `scripts/validate-metadata.py` fails, identify the specific error (e.g., "STYLE ERROR") and rewrite the field to remove first/second person pronouns.
* **Context Bloat:** If the draft exceeds 500 lines, extract the largest procedural block and move it to a file in `references/`.
讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
来自 GitHub
- GitHub 星标
- 2,297
- 开发者
- mgechev
- 许可证
- 未注明许可证 此 repo 未注明许可证,默认作者保留所有权利;转发或商用前请先询问作者。
- 最近代码更新
- 2026年7月27日
- repo 中的 SKILL.md 文件(含译本和模板)
- 1