Prototype · Preview: every server in the official registry, synced every 30 minutes. Reviews and accounts come in a later step.
PopNx MCPMCP servers for people who use AI · explained in plain words

Skill Deck

by xingbofengversion 1.0.0i★ –iRuns on your computer
Registry nameio.github.xingbofeng/skill-deck

Install

Overview

Description from the maker (original English)

Expose local Agent Skills as adapter tools, MCP resources, MCP tools, and share artifacts.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

  • Connection: Runs on your computer
  • Transport: stdio
  • Category: Other
  • You need to fill in: SKILL_DECK_SKILLS_ROOT

Install

Pick the AI app you use, then copy the settings.

Before you install

  • Basic checks: 1 of 1 passed
  • Runs on your computer with your user’s permissions (files, network, apps).
  • You fill in yourself: SKILL_DECK_SKILLS_ROOT

You need

  • npmNode.js installed (for the npx command)

Which app do you use?

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "skill-deck": {
      "command": "npx",
      "args": [
        "-y",
        "skill-deck"
      ],
      "env": {
        "SKILL_DECK_SKILLS_ROOT": "your-value"
      }
    }
  }
}

Run this in your terminal

claude mcp add skill-deck --env SKILL_DECK_SKILLS_ROOT=your-value -- npx -y skill-deck

Fill in the empty values before running it.

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "skill-deck": {
      "command": "npx",
      "args": [
        "-y",
        "skill-deck"
      ],
      "env": {
        "SKILL_DECK_SKILLS_ROOT": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "skill-deck": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "skill-deck"
      ],
      "env": {
        "SKILL_DECK_SKILLS_ROOT": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

Values you fill in

  • SKILL_DECK_SKILLS_ROOT required env
    Absolute path to the local Skill root directory exposed through SkillDeck.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account xingbofeng, which owns the repo

  • … Not checked yet

    Still maintained

    We have not read this repo from GitHub yet

  • … Not checked yet

    Has a licence

    We have not read this repo from GitHub yet

  • – Not applicable

    Endpoint responds

    This one runs on your computer; there is no internet endpoint

  • – Not applicable

    Sign-in with OAuth

    Runs on your computer and uses local settings instead

  • … Not checked yet

    No hidden instructions in tool descriptions

    Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Otheri

  • More stars than 0% of the other 32466 servers in this category
  • Published to the registry more recently than 10% of the other 32466 servers in this category
  • Basic checks equal to or better than 100% of the other 32466 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Skill Deck safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

You need to fill in: SKILL_DECK_SKILLS_ROOT

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (1.0.0) reached the registry 6 months ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.

What can I use instead?

In the same category: Spec Driven Development, Remote Desktop Commander, HotCodePush

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Spec Driven Development

by formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

Runs on your computer★ 440MITUpdated 14 months ago
Install

Remote Desktop Commander

by desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

Runs in the cloud★ 211Updated yesterday
Install

HotCodePush

by hotcodepush-team

Manage over-the-air (OTA) updates for React Native, Expo, Capacitor and Cordova apps.

Runs in the cloudUpdated today
Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

SkillDeck

中文 · English · 官网 · 快速开始 · GitHub

把散落在本机的 Agent Skills,变成模型看得见、用得上、也分享得出去的能力牌组。

Adapter for runtimes, MCP dynamic discovery, and share artifacts generated through agent conversation.

SkillDeck 是本地 Agent Skill 的适配、激活与分享工具。

它解决三个很具体的场景:

场景为什么需要它SkillDeck 做什么
我有一组 Skill,想通过工具的方式接入 OpenAI Agent SDK。OpenAI 已把 SKILL.md 定义成可复用工作流,Agents SDK 也支持 local skills,但手写 schema、handler 和 stable id 很繁琐。Adapter 扫描、解析、校验 SKILL.md,生成 provider-neutral tools 和 runtime handlers,让同一套 Skills 可以接入不同 Agent runtime。
我有一组 Skill,想接到 Claude Code、Cursor 或其他 MCP host。只给 list_skills / read_skill 不够,模型不一定知道复杂任务要先查本地 Skills。MCP + Skill Activation 把 Skills 暴露成 tools/resources,并通过 compact / guided / active 三种模式,让模型在任务里自己发现、搜索和加载 Skill。
我有一组 Skill,想发给同事、同行或社交平台看。私有 Skill 往往含本地路径、secret、私有 URL;只发截图又无法搜索、下钻和复用。Share 通过 MCP 让 agent 生成完整分享页和双图,默认脱敏,可搜索、可下钻、可审阅再接入。

背景参考:OpenAI Skills guide、Skills in ChatGPT、Agents SDK tools、openai-agents-python #2906。

对应到产品能力,它做三件事:

主线作用结果
Adapter扫描、解析、校验本地 SKILL.md,生成 stable id、provider-neutral tools 和 runtime handlers。同一套 Skills 可接 OpenAI、Anthropic、OpenAI Agents SDK、本地 runtime。
MCP把 Skills 暴露成 MCP tools/resources,并通过 Skill Activation 帮模型动态发现。模型可以通过 skill_guide、use_skill_*、search_skills、read_skill 加载 Skill。
Share你和 agent 说“帮我分享这套 Skills”,agent 通过 MCP 生成静态分享页和双图,默认脱敏。适合朋友圈、小红书和同行交流,不暴露本地路径、secret 和私有 URL。

它不是公开 marketplace,也不是远程托管服务。用户的 Skill 目录仍然在本机。

Skill Activation

默认的 list_skills / read_skill 能读 Skill,但模型不一定会主动调用。SkillDeck 增加三种模式,让模型更容易发现并加载本地 Skill。

模式暴露内容模型怎么发现 Skill适合场景代价
compactlist_skills、search_skills、get_skill_info、read_skill、resources模型需要主动搜索或列目录兼容旧行为、Skill 很多、工具列表要短自动发现能力弱
guidedcompact + skill_guide + MCP instructions模型看到 skill_guide 后获得使用指南想提高发现概率,但不想每个 Skill 都变 tool仍依赖模型调用向导
activeguided + 最多 N 个 use_skill_ _ 模型在 tools/list 阶段直接看到常用 Skill想最大化自动发现效果工具数量增加

示例:

npx -y skill-deck mcp serve \

--skills ~/.skills

安装

安装:

npm install skill-deck

MCP 三步接入

第一步,选择一种 Skill Activation 模式安装 MCP。推荐先用默认 active:

三种命令的 MCP server 名都叫 skill-deck;切换模式时更新同名 server 即可。

# active:默认模式,常用 Skill 会直接出现在 tools/list

claude mcp add skill-deck \ -- npx -y skill-deck mcp serve \ --skills ~/.codex/skills

# guided:暴露 skill_guide,让模型先看分组和推荐入口

claude mcp add skill-deck \ -- npx -y skill-deck mcp serve \ --skills ~/.codex/skills \ --skill-mode guided

# compact:只暴露 list/search/info/read/resources,工具列表最短

claude mcp add skill-deck \ -- npx -y skill-deck mcp serve \ --skills ~/.codex/skills \ --skill-mode compact

Codex / 其他 MCP host 使用同一组 stdio 参数;如需切换模式,在 args 中追加 --skill-mode 和对应值:

{

"mcpServers": { "skill-deck": { "command": "npx", "args": [ "-y", "skill-deck", "mcp", "serve", "--skills", "~/.codex/skills" ] } } }

第二步,在 Claude / Codex 中确认 skill-deck 已连接。Claude Code 里输入:

/mcp

第三步,直接对 agent 说:

请使用 SkillDeck MCP 的 generate_skill_share 工具,为当前已加载的 ~/.codex/skills 生成一套可以分享给同行看的 Skill 工作流分享物。

需要指定输出目录时,再追加:

输出到 ~/skilldeck-shares/codex-skills-share,注意脱敏,并在完成后告诉我 index.html、cover.png、detail.png 和 manifest.json 的路径。

Share

分享不是让你手写配置,也不是把私有 Skill 扔到公开市场。你只需要和 agent 对话:

帮我把 ~/.skills 这套 Skills 做成一个可以发给同行看的分享页和两张分享图,注意脱敏。

agent 会通过 SkillDeck 的 MCP Share 接口生成:

share/

index.html cover.png detail.png

index.html 是完整介绍页,支持搜索和下钻到 Skill 详情;cover.png 适合传播,detail.png 适合给同行看技术细节。默认会移除本地路径、secret 和私有 URL,reference 只展示路径,不读取文件内容。

实际生成效果:

全量能力

  • Skill Activation:compact / guided / active。
  • skill_guide 和 use_skill_*。
  • 搜索排序、分页、字段裁剪。
  • Catalog/resources。
  • watcher。
  • symlink 显式支持。
  • Share HTML + 双图。
  • docs-site 右上角搜索。
  • npm 包:skill-deck。
  • MCP Registry:server.json + npm/stdio 元数据。
  • MCP Streamable HTTP transport。

文档

  • 快速开始
  • Agent SDK 接入
  • MCP 接入

更完整的在线文档见 skill.counterxing.top。

License

MIT

Ask PopNx