一键导入
cowork-getting-started
Best practices, checklists, and reusable prompts for delegating multi-step knowledge work in Claude Cowork to produce deliverables.
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。
菜单
Best practices, checklists, and reusable prompts for delegating multi-step knowledge work in Claude Cowork to produce deliverables.
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
Choose the simplest loop primitive (turn-based, /goal, /loop, /schedule) and make success criteria explicit and verifiable.
Verify any UI change end-to-end before declaring it done.
Plan and roll out Claude Code via a self-hosted apps gateway, using centralized SSO login, managed settings enforcement, and per-user usage attribution when running on Amazon Bedrock or Google Cloud.
Decide whether to run Claude via Microsoft Foundry hosted on Azure or hosted on Anthropic, based on Azure-native requirements vs. needing full API feature/model availability.
A practical playbook for designing and operating effective human–agent teams: working in public, defining roles and tools, setting a north star, and building trust through verification and gradual autonomy.
Configure and roll out workspace-owned “agent identities” for team-wide AI agents with least privilege, strong boundaries, and reliable auditing.
| name | cowork-getting-started |
| description | Best practices, checklists, and reusable prompts for delegating multi-step knowledge work in Claude Cowork to produce deliverables. |
Help you decide when to use Claude Cowork (vs chat or Claude Code) and how to frame requests so Cowork can reliably produce useful deliverables.
Use Claude Cowork when:
Prefer chat if what you want fits in a few exchanges (questions, explanations, brainstorming, gut checks).
See references/cowork-shaped-checklist.md.