Guide users through creating a new plugin from scratch in a cowork session. Use when users want to create a plugin, build a plugin, make a new plugin, develop a plugin, scaffold a plugin, start a plugin from scratch, or design a plugin. This skill requires Cowork mode with access to the outputs directory for delivering the final .plugin file.
From cowork-plugin-managementnpx claudepluginhub 8gg-git/knowledge-work-plugins --plugin cowork-plugin-managementThis skill uses the workspace's default tool permissions.
references/component-schemas.mdreferences/example-plugins.mdDesigns and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
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 commands, 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
├── commands/ # Slash commands (.md files)
├── agents/ # Subagent definitions (.md files)
├── skills/ # Skills (subdirectories with SKILL.md)
│ └── skill-name/
│ ├── SKILL.md
│ └── references/
├── .mcp.json # MCP server definitions
└── README.md # Plugin documentation
Rules:
.claude-plugin/plugin.json is always requiredcommands/, agents/, skills/) 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 |
|---|---|---|
| Commands | commands/*.md | Markdown + YAML frontmatter |
| 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 |
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 commands and skills the most useful.
~~ placeholdersDo not use or ask about this pattern by default. Only introduce
~~placeholders if the user explicitly says they want people outside their organization to use the plugin. You can mention this is an option if it seems like the user wants to distribute the plugin externally, but do not proactively ask about this with AskUserQuestion.
When a plugin is intended to be shared with others outside their company, it might have parts that need to be adapted to individual users.
You might need to reference external tools by category rather than specific product (e.g., "project tracker" instead of "Jira").
When sharing is needed, use generic language and mark these as requiring customization with two tilde characters such as create an issue in ~~project tracker.
If used any tool categories, write a CONNECTORS.md file at the plugin root to explain:
# Connectors
## How tool references work
Plugin files use `~~category` as a placeholder for whatever tool the user
connects in that category. Plugins are tool-agnostic — they describe
workflows in terms of categories rather than specific products.
## Connectors for this plugin
| Category | Placeholder | Options |
|----------|-------------|-----------------|---------------|
| Chat | `~~chat` | Slack, Microsoft Teams, Discord |
| Project tracker | `~~project tracker` | Linear, Asana, Jira |
Use ${CLAUDE_PLUGIN_ROOT} for all intra-plugin path references in hooks and MCP configs. Never hardcode absolute paths.
When you ask the user something, use AskUserQuestion. Don't assume "industry standard" defaults are correct. Note: AskUserQuestion always includes a Skip button and a free-text input box for custom answers, so do not include None or Other as options.
Goal: Understand what the user wants to build and why.
Ask (only what is unclear — skip questions if the user's initial request already answers them):
Summarize understanding and confirm before proceeding.
Output: Clear statement of plugin purpose and scope.
Goal: Determine which component types the plugin needs.
Based on the discovery answers, determine:
Present a component plan table, including component types you decided not to create:
| Component | Count | Purpose |
|-----------|-------|---------|
| Skills | 1 | Domain knowledge for X |
| Commands | 2 | /do-thing, /check-thing |
| Agents | 0 | Not needed |
| Hooks | 1 | Validate writes |
| MCP | 1 | Connect to service Y |
Get user confirmation or adjustments before proceeding.
Output: Confirmed list of components to create.
Goal: Specify each component in detail. Resolve all ambiguities before implementation.
For each component type in the plan, ask targeted design questions. Present questions grouped by component type. Wait for answers before proceeding.
Skills:
Commands:
Agents:
Hooks:
MCP Servers:
If the user says "whatever you think is best," provide specific recommendations and get explicit confirmation.
Output: Detailed specification for every component.
Goal: Create all plugin files following best practices.
Order of operations:
plugin.json manifestreferences/component-schemas.md for exact formats)README.md documenting the pluginImplementation guidelines:
references/. Frontmatter description must be third-person with specific trigger phrases.<example> blocks showing triggering conditions, plus a system prompt in the markdown body.hooks/hooks.json. Use ${CLAUDE_PLUGIN_ROOT} for script paths. Prefer prompt-based hooks for complex logic..mcp.json at plugin root. Use ${CLAUDE_PLUGIN_ROOT} for local server paths. Document required env vars in README.Goal: Deliver the finished plugin.
claude plugin validate <path-to-plugin-json>; fix any errors and warnings.plugin file:cd /path/to/plugin-dir && zip -r /tmp/plugin-name.plugin . -x "*.DS_Store" && cp /tmp/plugin-name.plugin /path/to/outputs/plugin-name.plugin
Important: Always create the zip in
/tmp/first, then copy to the outputs folder. Writing directly to the outputs folder may fail due to permissions.
Naming: Use the plugin name from
plugin.jsonfor the.pluginfile (e.g., if name iscode-reviewer, outputcode-reviewer.plugin).
The .plugin file will appear in the chat as a rich preview where the user can browse the files and accept the plugin by pressing a button.
references/, working examples in examples/.<example> blocks.${CLAUDE_PLUGIN_ROOT} for intra-plugin paths, never hardcoded paths.references/component-schemas.md — Detailed format specifications for every component type (commands, skills, agents, hooks, MCP, CONNECTORS.md)references/example-plugins.md — Three complete example plugin structures at different complexity levels