com um clique
plugin-creator
// Create, validate, and publish Claude Code plugins and marketplaces. Use this skill when building plugins with commands, agents, hooks, MCP servers, or skills.
// Create, validate, and publish Claude Code plugins and marketplaces. Use this skill when building plugins with commands, agents, hooks, MCP servers, or skills.
PERSONAL APP ARCHITECT - Strategic development orchestrator for personal productivity applications. Analyzes project context, makes architectural decisions for single-developer projects, delegates to specialized skills, and ensures alignment between user experience goals and technical implementation. Optimized for personal apps targeting 10-100 users.
Comprehensive data safety auditor for Vue 3 + Pinia + IndexedDB + PouchDB applications. Detects data loss risks, sync issues, race conditions, and browser-specific vulnerabilities with actionable remediation guidance.
A robust skill that analyzes your app's actual codebase, tech stack, configuration, and architecture to ensure ALL documentation is current and accurate. It never assumes—always verifies and compares the live system with every documentation file to detect code-doc drift and generate actionable updates.
Safe MASTER_PLAN.md management with backup, validation, and intelligent updates. Use when updating task tracking, adding features to roadmap, or modifying project documentation.
MASTER Vue.js application testing with strict enforcement of verification protocols. Systematically test functionality with Playwright, validate bug fixes, verify features work, and enforce zero-tolerance policies for false success claims. MANDATORY testing with visual evidence before any deployment or functionality claims.
Safely analyze and reorganize project structure with multi-stage validation, dry-run previews, and explicit user confirmation. Use when projects need cleanup, standardization, or better organization.
| name | plugin-creator |
| description | Create, validate, and publish Claude Code plugins and marketplaces. Use this skill when building plugins with commands, agents, hooks, MCP servers, or skills. |
This skill provides comprehensive guidance for creating Claude Code plugins following the official Anthropic format (as of December 2025).
A Claude Code plugin can contain any combination of:
/mycommand)my-plugin/
├── .claude-plugin/
│ └── plugin.json # REQUIRED - Plugin manifest
├── commands/ # Optional - Slash commands
│ └── my-command.md
├── agents/ # Optional - Subagents
│ └── my-agent.md
├── hooks/ # Optional - Hook definitions
│ └── hooks.json
├── skills/ # Optional - Bundled skills
│ └── my-skill/
│ └── SKILL.md
├── mcp/ # Optional - MCP server configs
└── README.md
The .claude-plugin/plugin.json file is required. Here's the complete schema:
{
"$schema": "https://anthropic.com/claude-code/plugin.schema.json",
"name": "my-plugin",
"version": "1.0.0",
"description": "Clear description of what this plugin does",
"author": {
"name": "Your Name",
"email": "you@example.com"
},
"license": "MIT",
"commands": [
{
"name": "mycommand",
"description": "What this command does",
"source": "./commands/my-command.md"
}
],
"agents": [
{
"name": "my-agent",
"description": "What this agent specializes in",
"source": "./agents/my-agent.md"
}
],
"hooks": {
"source": "./hooks/hooks.json"
},
"skills": [
"./skills/my-skill"
],
"mcp_servers": [
{
"name": "my-mcp",
"command": "npx",
"args": ["my-mcp-server"]
}
]
}
Commands are markdown files with YAML frontmatter:
---
name: deploy
description: Deploy the application to production
---
# Deploy Command
When the user runs /deploy, perform these steps:
1. Run the build process
2. Run all tests
3. Create a deployment package
4. Upload to the configured target
## Usage Examples
- `/deploy` - Deploy to default environment
- `/deploy staging` - Deploy to staging
- `/deploy production --skip-tests` - Deploy to production (use carefully)
Agents are specialized subagents with focused capabilities:
---
name: security-reviewer
description: Reviews code for security vulnerabilities
model: sonnet
tools:
- Read
- Grep
- Glob
---
# Security Review Agent
You are a security expert focused on identifying vulnerabilities.
## Your Responsibilities
1. Scan for OWASP Top 10 vulnerabilities
2. Identify hardcoded secrets
3. Check for input validation issues
4. Review authentication/authorization logic
## Output Format
Provide findings as:
- CRITICAL: Immediate security risk
- HIGH: Should fix before deployment
- MEDIUM: Fix in next sprint
- LOW: Consider improving
Skills use the official Agent Skills format:
---
name: my-skill
description: What this skill teaches Claude to do
---
# My Skill Name
## When to Use
Use this skill when the user needs help with [specific task].
## Instructions
1. Step one
2. Step two
3. Step three
## Examples
### Example 1: Basic Usage
[Concrete example]
### Example 2: Advanced Usage
[Another example]
## Best Practices
- Practice 1
- Practice 2
Hooks are defined in hooks.json:
{
"hooks": [
{
"event": "PreToolUse",
"matcher": "Edit|Write",
"command": ".claude-plugin/hooks/security-check.sh"
},
{
"event": "PostToolUse",
"matcher": "Bash",
"command": ".claude-plugin/hooks/log-commands.sh"
}
]
}
Hook events:
PreToolUse - Before a tool executesPostToolUse - After a tool completesSessionStart - When a Claude Code session beginsSessionEnd - When a session endsTo distribute multiple plugins, create a marketplace:
my-marketplace/
├── .claude-plugin/
│ └── marketplace.json
└── plugins/
├── plugin-a/
│ └── .claude-plugin/
│ └── plugin.json
└── plugin-b/
└── .claude-plugin/
└── plugin.json
{
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
"name": "my-marketplace",
"version": "1.0.0",
"description": "Collection of productivity plugins",
"owner": {
"name": "Your Name",
"email": "you@example.com"
},
"plugins": [
{
"name": "plugin-a",
"description": "What plugin A does",
"source": "./plugins/plugin-a",
"category": "development",
"tags": ["productivity", "automation"]
},
{
"name": "plugin-b",
"description": "What plugin B does",
"source": "./plugins/plugin-b",
"category": "productivity"
}
]
}
Official categories:
development - Developer toolsproductivity - Workflow automationsecurity - Security toolslearning - Educational contenttesting - Test automationdatabase - Database toolsdesign - UI/UX toolsmonitoring - Observabilitydeployment - CI/CD tools# Install from local path
/plugin install /path/to/my-plugin
# Or add as local marketplace
/plugin marketplace add /path/to/my-marketplace
/plugin install my-plugin@my-marketplace
# List installed plugins
/plugin list
# Enable/disable
/plugin enable my-plugin
/plugin disable my-plugin
# Uninstall
/plugin uninstall my-plugin
Before publishing, verify:
plugin.json is valid JSONsource paths exist.claude-plugin/marketplace.json/plugin marketplace add your-username/your-repo
/plugin install plugin-name@your-repo
Popular community marketplaces:
Submit via:
The anthropics/claude-code repo contains official plugins. To add:
plugins/marketplace.jsonRun this to scaffold a new plugin:
mkdir my-plugin && cd my-plugin
mkdir -p .claude-plugin commands agents skills
cat > .claude-plugin/plugin.json << 'EOF'
{
"name": "my-plugin",
"version": "1.0.0",
"description": "My awesome Claude Code plugin",
"author": {
"name": "Your Name"
},
"commands": []
}
EOF
cat > README.md << 'EOF'
# My Plugin
Description of your plugin.
## Installation
/plugin install /path/to/my-plugin
## Usage
Describe how to use your plugin.
EOF
echo "Plugin scaffolded! Edit .claude-plugin/plugin.json to add commands/agents."