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

openwork Skill

代码仓库 ↗

同一项目也有 MCP 版本 →

作者:different-ai★ 24,546 (whole repo)14 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 14 skills

  • Connects Instruction files the AI reads
  • Account or key Not confirmed (README mentions a key or .env file)
  • Category 其他
Maker’s original description
The open-source alternative to Claude Cowork (powered by opencode)
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/different-ai-openwork.svg)](https://mcp.popnx.com/en/skills/different-ai-openwork)

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
openwork
llmfitclaude-videoVideoCaptionerclaude-cookbooks
作者different-aiAlexsJonesbradautomatesWEIFENG2333anthropics
Skill 数141114
GitHub 星标24,54639,01820,99916,54454,763
最近代码更新2026年11月16日2026年11月16日2026年9月25日2026年9月12日2026年11月5日
许可证–MITMITGPL-3.0MIT

different-ai 提供的 14 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 (14)

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 14 skills from https://github.com/different-ai/openwork: add-a-feature, connect-openwork-mcp, drive-desktop-cdp, dry-run-a-risky-change, fake-model-faults, install-openwork, open-a-pr, openwork-connect, run-tests, set-up-openwork-slack, set-up-openwork-team, verify-openwork, workspace-guide, write-a-spec, 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: add-a-feature = .opencode/skills/add-a-feature · connect-openwork-mcp = ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp · drive-desktop-cdp = .opencode/skills/drive-desktop-cdp · dry-run-a-risky-change = .opencode/skills/dry-run-a-risky-change · fake-model-faults = .opencode/skills/fake-model-faults · install-openwork = ee/apps/landing/public/.well-known/agent-skills/install-openwork · open-a-pr = .opencode/skills/open-a-pr · openwork-connect = integrations/agent-plugins/openwork-connect/skills/openwork-connect · run-tests = .opencode/skills/run-tests · set-up-openwork-slack = ee/apps/landing/public/.well-known/agent-skills/set-up-openwork-slack · set-up-openwork-team = ee/apps/landing/public/.well-known/agent-skills/set-up-openwork-team · verify-openwork = .opencode/skills/verify-openwork · workspace-guide = ee/apps/landing/public/.well-known/agent-skills/workspace-guide · write-a-spec = .opencode/skills/write-a-spec. 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 14 skills from https://github.com/different-ai/openwork: add-a-feature, connect-openwork-mcp, drive-desktop-cdp, dry-run-a-risky-change, fake-model-faults, install-openwork, open-a-pr, openwork-connect, run-tests, set-up-openwork-slack, set-up-openwork-team, verify-openwork, workspace-guide, write-a-spec, 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: add-a-feature = .opencode/skills/add-a-feature · connect-openwork-mcp = ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp · drive-desktop-cdp = .opencode/skills/drive-desktop-cdp · dry-run-a-risky-change = .opencode/skills/dry-run-a-risky-change · fake-model-faults = .opencode/skills/fake-model-faults · install-openwork = ee/apps/landing/public/.well-known/agent-skills/install-openwork · open-a-pr = .opencode/skills/open-a-pr · openwork-connect = integrations/agent-plugins/openwork-connect/skills/openwork-connect · run-tests = .opencode/skills/run-tests · set-up-openwork-slack = ee/apps/landing/public/.well-known/agent-skills/set-up-openwork-slack · set-up-openwork-team = ee/apps/landing/public/.well-known/agent-skills/set-up-openwork-team · verify-openwork = .opencode/skills/verify-openwork · workspace-guide = ee/apps/landing/public/.well-known/agent-skills/workspace-guide · write-a-spec = .opencode/skills/write-a-spec. 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 14 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

  • add-a-feature

    Decide whether work needs a feature flag (any change to product behavior users can see does), then declare it, roll it out (per organization, for everyone, cloud or self-hosted), revert or kill it. Use for any user-visible behavior change, and when finishing or removing a rollout.

  • connect-openwork-mcp

    Connect the OpenWork MCP Gateway (https://api.openworklabs.com/mcp/agent) to Claude Code, Codex, Gemini CLI, Cursor, VS Code, Claude Desktop, or ChatGPT so the agent can use the user's OpenWork organization skills, plugins, and connections.

  • drive-desktop-cdp

    Drive the running OpenWork app over CDP from the shell, headless by default (nothing opens on screen). Evaluate JS, take screenshots, open a new session, send a prompt with a chosen model, wait for the run to finish. Use when checking a UI change by hand in a world or pnpm dev, or when reproducing…

  • dry-run-a-risky-change

    Billing, plans, seats, permissions, access rules, auth, flag removals or data migrations that could lock real organizations out or change what they pay. Use before merging or deploying such a change to see exactly which production organizations it affects, prove the UI on production-shaped data, an…

  • fake-model-faults

    Make the desktop's model provider fail on demand (connection refused, DNS not found, socket reset, 429, 5xx, 401, 402, stalled or cut stream) with a local fault server and test providers. Use when reproducing or designing model error and retry states without a real outage.

  • install-openwork

    Install the free OpenWork desktop app on macOS, Windows, or Linux and get the user to a first task. Use when someone wants OpenWork, an open-source Claude Cowork alternative, on their own computer.

  • open-a-pr

    Open a PR, write or rewrite a PR description, "the PR body is too long", or check whether a PR description is readable. Use whenever a PR is created or its body is edited.

  • openwork-connect

    Search and use the skills, MCP connections, and connected services available through the user's OpenWork organization.

  • run-tests

    Run the tests, run one spec, run e2e locally or on Daytona, investigate a skipped spec. Use for executing @openwork/testkit agent-first verification.

  • set-up-openwork-slack

    Configure and verify the OpenWork Slack assistant for an approved private-alpha organization, using its existing Slack app and individual-account connector. Use when a user wants @openwork in Slack or needs help installing or linking it.

  • set-up-openwork-team

    Set up OpenWork for a team - sign up for OpenWork Cloud, create the organization, invite teammates, share models through the AI Gateway, and share a skill. Use when a team or company wants OpenWork with shared skills, models, or policies.

  • verify-openwork

    Prove an OpenWork change works on the real product before calling it done. Start the product, drive the change the way a user or client would, capture screenshots, and show the proof fails on dev and passes on your branch. Use before opening a PR, when a reviewer asks "show me", or when a core jour…

  • workspace-guide

    Workspace guide to introduce OpenWork and onboard new users.

  • write-a-spec

    Extend a core journey in evals/core or write a one-off proof in evals/proofs that proves a PR's change to a human reviewer. Use when a PR changes user-visible behaviour, when a reviewer asks "show me", or when the coverage decision says a journey is missing.

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 CodeCodexCursorOpenCode

依据开发者 README 和 repo 中的文件夹

安装

Pick a skill first

This repo has 14 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 ↑

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
24,546
Stars are for the whole repo, not each skill
开发者
different-ai
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11月16日
repo 中的 SKILL.md 文件(含译本和模板)
14