在协作会话中引导你从零创建插件并生成可交付的 .plugin 文件
复制安装指令,让 AI 自动完成配置 · 推荐新手
请帮我安装 askskill 上的 "create-cowork-plugin" 技能: 1. 下载 https://raw.githubusercontent.com/anthropics/knowledge-work-plugins/main/cowork-plugin-management/skills/create-cowork-plugin/SKILL.md 2. 保存为 ~/.claude/skills/create-cowork-plugin/SKILL.md 3. 装好后重载技能,告诉我可以用了
请在 cowork 模式下带我从零创建一个插件,用于读取 CSV 文件并生成摘要。先帮我明确功能、输入输出,再逐步搭建结构,最后把可交付的 .plugin 文件放到 outputs 目录。
一套分步骤的协作创建过程,包括插件设计、结构搭建与最终生成的 .plugin 文件。
帮我设计并开发一个新插件,让团队可以输入会议纪要并自动提取待办事项。请在 cowork 会话中完成需求梳理、插件搭建和打包输出。
一个面向会议纪要处理的插件方案,以及可直接交付的插件文件。
我想快速做一个插件原型,功能是接收产品需求文本并输出测试用例草稿。请引导我从空白开始创建,并把最终 .plugin 文件生成到 outputs 目录。
一个从需求到原型实现的插件创建流程,以及可测试的 .plugin 成果文件。
Build a new plugin from scratch through guided conversation. Walk the user through discovery, planning, design, implementation, and packaging — delivering a ready-to-install .plugin file at the end.
A plugin is a self-contained directory that extends Claude's capabilities with skills, agents, hooks, and MCP server integrations. This skill encodes the full plugin architecture and a five-phase workflow for creating one conversationally.
The process:
.plugin fileNontechnical output: Keep all user-facing conversation in plain language. Do not expose implementation details like file paths, directory structures, or schema fields unless the user asks. Frame everything in terms of what the plugin will do.
Every plugin follows this layout:
plugin-name/
├── .claude-plugin/
│ └── plugin.json # Required: plugin manifest
├── skills/ # Skills (subdirectories with SKILL.md)
│ └── skill-name/
│ ├── SKILL.md
│ └── references/
├── agents/ # Subagent definitions (.md files)
├── .mcp.json # MCP server definitions
└── README.md # Plugin documentation
Legacy
commands/format: Older plugins may include acommands/directory with single-file.mdslash commands. This format still works, but new plugins should useskills/*/SKILL.mdinstead — the Cowork UI presents both as a single "Skills" concept, and the skills format supports progressive disclosure viareferences/.
Rules:
.claude-plugin/plugin.json is always requiredskills/, agents/) go at the plugin root, not inside .claude-plugin/Located at .claude-plugin/plugin.json. Minimal required field is name.
{
"name": "plugin-name",
"version": "0.1.0",
"description": "Brief explanation of plugin purpose",
"author": {
"name": "Author Name"
}
}
Name rules: kebab-case, lowercase with hyphens, no spaces or special characters.
Version: semver format (MAJOR.MINOR.PATCH). Start at 0.1.0.
Optional fields: homepage, repository, license, keywords.
Custom component paths can be specified (supplements, does not replace, auto-discovery):
{
"commands": "./custom-commands",
"agents": ["./agents", "./specialized-agents"],
"hooks": "./config/hooks.json",
"mcpServers": "./.mcp.json"
}
Detailed schemas for each component type are in references/component-schemas.md. Summary:
| Component | Location | Format |
|---|---|---|
| Skills | skills/*/SKILL.md | Markdown + YAML frontmatter |
| MCP Servers | .mcp.json | JSON |
| Agents (uncommonly used in Cowork) | agents/*.md | Markdown + YAML frontmatter |
| Hooks (rarely used in Cowork) | hooks/hooks.json | JSON |
| Commands (legacy) | commands/*.md | Markdown + YAML frontmatter |
This schema is shared with Claude Code's plugin system, but you're creating a plugin for Claude Cowork, a desktop app for doing knowledge work.
Cowork users will usually find skills the most useful. Scaffold new plugins with skills/*/SKILL.md — do not create commands/ unless the user explicitly needs the legacy single-file format.
…
围绕客户问题进行多来源调研与溯源,快速整理背景并支持准确回复。
用于演示技能如何引导用户完成多步骤插件工作流与操作流程。