原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

skill-up Skill

代码仓库 ↗

作者:alibaba★ 1,488 (whole repo)22 个 skill

★ Stars are for the whole repo, not each skill

Pick the skill to install

What it does

This repo is a collection of 22 skills

  • Connects Instruction files the AI reads, with steps that call an outside service
  • Account or key Some steps need a key for SIMULATION_API_KEY, OTLP_TOKEN, Anthropic, OPENSANDBOX_API_KEY, OpenAI (per the README)
  • Category 写代码
Maker’s original description
Evaluate Agent Skills and environments. Evolve Skills with evidence.
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。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/alibaba-skill-up.svg)](https://mcp.popnx.com/en/skills/alibaba-skill-up)

可搭配使用

在同一工作中把 AI 连到服务的 MCP

REA

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

作者:morluto广泛使用↓ 38.9万/周★ 46.6万6天前更新

MCP · 连接服务在你的电脑上运行

Fallow

Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.

作者:fallow-rs广泛使用↓ 244.1万/周★ 5379昨天更新

MCP · 连接服务在你的电脑上运行

Desktop Commander

MCP server for terminal commands, file operations, and process management

作者:wonderwhy-er广泛使用↓ 74万/周★ 1万6天前更新

MCP · 连接服务在你的电脑上运行

相似的 Skill

同类工作,排序与 Skill 列表相同

与相似项目对比
本项
skill-up
reaandrej-karpathy-skillsgraphifyMoneyPrinterTurbo
作者alibabamorlutomultica-aiGraphify-Labsharry0703
Skill 数221111
GitHub 星标1,488465,460233,910149,364144,149
最近代码更新2026年11月17日2026年11月17日2026年4月20日2026年11月17日2026年11月17日
许可证Apache-2.0MIT–Apache-2.0MIT

alibaba 提供的 22 个 Skill(指令集),AI 读取后照做 · 不是 MCP server

Pick the skill to install

Install only the ones you use. Open a skill to see how to install it

Install the whole set (22)

If you want every one, let the AI install them in one go. Know 2 things first

  • Every installed skill’s description is loaded into every chat. The more you install, the easier it is for the AI to pick the wrong one
  • Some skills duplicate tools the AI already has built in. Installing only the ones you use works better
Where to install
Please install all 22 skills from https://github.com/alibaba/skill-up: agent-judge-criteria, code-stats, custom-engine, deepseek-harness, expect-short-circuit, file-and-tool-rules, full-report-pipeline, git-context, mcp-case-overrides, mcp-mocked-marker, mcp-stdio-marker, mock-engine, multi-turn-conversation, multiturn-session, retry-and-parallelism, sample-no-evals, sample-with-evals, sandbox-mcp, script-judge-eval, skill-upper, text-match-rules, trigger-detection, for all my projects, putting each at ~/.claude/skills/<skill name> (in Codex use ~/.agents/skills/<skill name>, in Cursor ~/.cursor/skills/<skill name>). Folders in the repo: agent-judge-criteria = e2e/testdata/agent-judge-criteria · code-stats = examples/code-stats · custom-engine = e2e/testdata/custom-engine · deepseek-harness = examples/deepseek-harness · expect-short-circuit = e2e/testdata/expect-short-circuit · file-and-tool-rules = e2e/testdata/file-and-tool-rules · full-report-pipeline = e2e/testdata/full-report-pipeline · git-context = e2e/testdata/git-context · mcp-case-overrides = e2e/testdata/mcp-case-overrides · mcp-mocked-marker = e2e/testdata/mcp-mocked-marker · mcp-stdio-marker = e2e/testdata/mcp-stdio-marker · mock-engine = e2e/testdata/mock-engine · multi-turn-conversation = e2e/testdata/multi-turn-conversation · multiturn-session = e2e/testdata/multiturn-session · retry-and-parallelism = e2e/testdata/retry-and-parallelism · sample-no-evals = skills/skill-upper/evals/fixtures/skills/sample-no-evals · sample-with-evals = skills/skill-upper/evals/fixtures/skills/sample-with-evals · sandbox-mcp = e2e/testdata/sandbox-mcp · script-judge-eval = e2e/testdata/script-judge-eval · skill-upper = skills/skill-upper · text-match-rules = e2e/testdata/text-match-rules · trigger-detection = e2e/testdata/trigger-detection. First show me every file and tell me whether any has scripts or changes machine settings, then tell me the full path you will install each one to and wait for me to agree.
Please install all 22 skills from https://github.com/alibaba/skill-up: agent-judge-criteria, code-stats, custom-engine, deepseek-harness, expect-short-circuit, file-and-tool-rules, full-report-pipeline, git-context, mcp-case-overrides, mcp-mocked-marker, mcp-stdio-marker, mock-engine, multi-turn-conversation, multiturn-session, retry-and-parallelism, sample-no-evals, sample-with-evals, sandbox-mcp, script-judge-eval, skill-upper, text-match-rules, trigger-detection, into the project this chat is open in (at .claude/skills/<skill name>; in Codex use .agents/skills/<skill name>, in Cursor .cursor/skills/<skill name>). Folders in the repo: agent-judge-criteria = e2e/testdata/agent-judge-criteria · code-stats = examples/code-stats · custom-engine = e2e/testdata/custom-engine · deepseek-harness = examples/deepseek-harness · expect-short-circuit = e2e/testdata/expect-short-circuit · file-and-tool-rules = e2e/testdata/file-and-tool-rules · full-report-pipeline = e2e/testdata/full-report-pipeline · git-context = e2e/testdata/git-context · mcp-case-overrides = e2e/testdata/mcp-case-overrides · mcp-mocked-marker = e2e/testdata/mcp-mocked-marker · mcp-stdio-marker = e2e/testdata/mcp-stdio-marker · mock-engine = e2e/testdata/mock-engine · multi-turn-conversation = e2e/testdata/multi-turn-conversation · multiturn-session = e2e/testdata/multiturn-session · retry-and-parallelism = e2e/testdata/retry-and-parallelism · sample-no-evals = skills/skill-upper/evals/fixtures/skills/sample-no-evals · sample-with-evals = skills/skill-upper/evals/fixtures/skills/sample-with-evals · sandbox-mcp = e2e/testdata/sandbox-mcp · script-judge-eval = e2e/testdata/script-judge-eval · skill-upper = skills/skill-upper · text-match-rules = e2e/testdata/text-match-rules · trigger-detection = e2e/testdata/trigger-detection. First show me every file and tell me whether any has scripts or changes machine settings, then tell me the project name and the full path you will install each one to and wait for me to agree.

Uploading to Claude on the web and apps: you need 22 uploads, one ZIP per skill. Open each skill in the list below to download it

Checked against official docs 2026年11月12日 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com

  • agent-judge-criteria

    Reviews code and provides detailed quality assessment

  • code-stats

    Analyzes code files and reports statistics including line counts, file counts by extension, and total size. Use this skill whenever the user wants to understand the composition of a codebase - asking about "how many lines of code", "what file types exist", "code distribution", or needing a quick au…

  • custom-engine

    No description from the maker

  • deepseek-harness

    Decode the marker fixture used by the DeepSeek Harness integration example.

  • expect-short-circuit

    Quickly produces accurate calculation results when a user needs arithmetic, unit conversion, or mathematical formula solving. Triggered when users say things like "help me calculate", "compute", "how much is", etc.

  • file-and-tool-rules

    Triggered when the user needs to organize project files, analyze directory structure, or generate a project report. Use MCP tools to read file contents and produce a structured organization report. Trigger phrases include "help me organize this project", "look at the directory structure", "generate…

  • full-report-pipeline

    Triggered when the user submits code or requests a comprehensive code quality analysis. Automatically performs static analysis, code review, and quality scoring. Analysis covers coding standards, potential bugs, performance issues, and security vulnerabilities. Trigger phrases include "analyze code…

  • git-context

    Analyzes git repositories and commit history

  • mcp-case-overrides

    Per-case mocked MCP override smoke skill used by skill-up e2e tests.

  • mcp-mocked-marker

    MCP mocked marker smoke skill used by skill-up e2e tests.

  • mcp-stdio-marker

    MCP stdio marker smoke skill used by skill-up e2e tests.

  • mock-engine

    No description from the maker

  • multi-turn-conversation

    SDD-RIPER workflow executor with phase gating

  • multiturn-session

    No description from the maker

  • retry-and-parallelism

    A skill with potentially flaky behavior for testing retry

  • sample-no-evals

    帮助用户进行代码审查,识别常见代码问题并给出修改建议。

  • sample-with-evals

    帮助用户管理待办事项,支持添加、删除、标记完成、列出任务等操作。

  • sandbox-mcp

    Verify Sandbox MCP can be installed and called from skill-up.

  • script-judge-eval

    Triggered when the user needs to convert data formats, such as CSV to JSON, JSON to YAML, or XML to JSON. Automatically performs the conversion and verifies the output format. Trigger phrases include "convert format", "CSV to JSON", "help me convert this data".

  • skill-upper

    Capture and review Agent Skill observations, and create, run, diagnose, or iteratively improve Skill evaluations (evals) with the skill-up CLI. Use when the user asks to record explicitly attributed Skill usage or feedback; review observations or user-supplied traces/transcripts; turn an approved o…

  • text-match-rules

    Triggered when the user submits code or requests a code review. Automatically analyzes code quality, identifies potential bugs, security vulnerabilities, and performance issues, and provides improvement suggestions. Trigger phrases include "take a look at this code", "review this", "is there a prob…

  • trigger-detection

    Triggered when the user expresses boredom, low mood, frustration, irritation, or a need to relax. Responds with warm words of comfort and tells a joke to lighten the atmosphere. Trigger phrases include "I'm so bored", "feeling down", "so frustrated", "gloomy", "not happy", "I'm tired".

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

Claude CodeCodexOpenCode

依据开发者 README 和 repo 中的文件夹

安装

Pick a skill first

This repo has 22 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP

Let the AI install it
Upload to claude.ai

Go to the skill list ↑

The maker’s command installs the whole set of 22
安装 Node.js(如果还没有)

已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter

node -v
  • 显示版本号(例如 v26.13.1)= 已安装,可跳过这一步
  • 显示 "command not found"(Windows 显示 "is not recognized")= 还没安装,或刚装好但需要关掉终端再重新打开
怎么打开终端

Mac:按 ⌘ + Space,输入 Terminal 后按 Enter

Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”

还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令

打开 Node.js 下载页 ↗

装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v

安装一次,所有需要 Node.js 的工具都能用

已隐藏作者的命令 · 它不是从 GitHub 上的这个仓库安装 · 可改用本页其他已通过检查的方式

摘自开发者 README,会下载并运行开发者的代码

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

来自 GitHub

GitHub 星标
1,488
Stars are for the whole repo, not each skill
开发者
alibaba
许可证
Apache-2.0
最近代码更新
2026年11月17日
repo 中的 SKILL.md 文件(含译本和模板)
22
主题
agent-evaluation, agent-skills, ai-agents, harness-engineering, skill-evaluation