nicholyx/ai-skills / .agents/skills/plugin-creator
plugin-creator
VerifiedComprehensive plugin development skill for Claude Code. Analyzes business requirements and creates complete plugins including MCP servers, skills, slash commands, or combinations thereof. Supports TypeScript, Python, and any other language. Provides architecture guidance, templates, and end-to-end implementation.
assets/templates/slash-command/example-command.md
View on GitHub# command-name
Brief description of what this command does.
## Prompt
Replace this with your command's prompt. This is what gets executed when the command runs.
### Arguments
If your command uses arguments, explain them here:
- `{{args}}` - Contains the arguments passed to the command
### Expected Usage
```
/command-name [arguments]
```
Examples:
- `/command-name value`
- `/command-name --option value`
- `/command-name` (no arguments)
### Command Logic
Write your command's execution logic here. This should be clear step-by-step instructions.
**Steps:**
1. **Parse Arguments** (if applicable)
- Extract parameters from {{args}}
- Validate required parameters
- Set defaults for optional parameters
2. **Execute Main Logic**
- Describe what the command does
- Include any tool calls (MCP, skills, etc.)
- Handle different scenarios
3. **Provide Feedback**
- Display results clearly
- Show progress for long operations
- Report errors helpfully
### Integration
If this command integrates with skills or MCP servers:
**Using Skills:**
```markdown
Use the [skill-name] skill for [purpose]
Reference [skill resource] for [information]
```
**Using MCP Tools:**
```markdown
Use the [tool-name] tool from [mcp-server] with:
- parameter1: value1
- parameter2: value2
```
### Error Handling
Handle errors gracefully:
**If [condition]:**
- Display: "[Clear error message]"
- Suggest: "[How to fix or correct usage]"
- Do not proceed
**If [another condition]:**
- Display: "[Another error message]"
- Provide: "[Alternative approach]"
### Examples
**Example 1: Basic Usage**
```
/command-name basic-argument
```
Expected output:
```
[What the user should see]
```
**Example 2: With Options**
```
/command-name --option value
```
Expected output:
```
[What the user should see]
```
### Notes
- Additional notes or warnings
- Performance considerations
- Best practices for using this command
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |