nicholyx/ai-skills / .agents/skills/plugin-creator/assets/templates/skill
skill-template
VerifiedTemplate for creating Claude Code skills. Replace this description with a clear explanation of what this skill does and when it should be used. Be specific about triggers and use cases.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 3.0 KB |
| SKILL.md | skill md | 2.7 KB |
| references/example_reference.md | markdown | 1.0 KB |
| scripts/example_script.py | script | 1.6 KB |
README.md
View on GitHub# Skill Template
Template for creating Claude Code skills with best practices built-in.
## Quick Start
1. **Copy this template**
```bash
cp -r skill-template/ my-new-skill/
cd my-new-skill/
```
2. **Customize SKILL.md**
- Update YAML frontmatter (name and description)
- Replace template sections with your content
- Add your workflows and examples
3. **Add bundled resources** (optional)
- Add scripts to `scripts/`
- Add references to `references/`
- Add assets to `assets/`
4. **Test your skill**
- Install in Claude Code skills directory
- Test with realistic scenarios
- Verify all examples work
5. **Package for distribution**
```bash
# Create skill package
zip -r my-skill.zip .
```
## Structure
```
skill-template/
├── SKILL.md # Main skill definition (required)
├── scripts/ # Executable helper scripts (optional)
│ └── example_script.py # Example script
├── references/ # Reference documentation (optional)
│ └── example_reference.md # Example reference
├── assets/ # Files used in output (optional)
│ └── templates/ # Template files
└── README.md # This file
```
## Customization Checklist
- [ ] Update `name` in YAML frontmatter
- [ ] Update `description` in YAML frontmatter
- [ ] Replace purpose section
- [ ] Add specific trigger conditions
- [ ] Add your workflows with steps
- [ ] Add concrete examples
- [ ] Add scripts if needed
- [ ] Add reference documents if needed
- [ ] Add asset templates if needed
- [ ] Test all examples work
- [ ] Remove example files you don't need
## Best Practices
### Frontmatter
- Use lowercase-with-dashes for skill name
- Write specific, clear description
- Use third person ("This skill should be used...")
### Workflows
- Use step-by-step format
- Include concrete examples
- Reference bundled resources where appropriate
- Show expected outcomes
### Bundled Resources
- **Scripts:** For code that would be rewritten repeatedly
- **References:** For detailed docs loaded as needed
- **Assets:** For files used in output
### Examples
- Use real, working examples
- Include expected outputs
- Cover common use cases
- Show error handling
## Example Transformation
**Before (Template):**
```markdown
---
name: skill-template
description: Template for creating Claude Code skills...
---
```
**After (Your Skill):**
```markdown
---
name: api-testing
description: Provides workflows for testing REST APIs including request execution, response validation, and test suite management. Use when testing API endpoints or creating API test automation.
---
# API Testing Skill
## Purpose
This skill provides comprehensive workflows for REST API testing...
```
## Resources
- [Skill Guide](../../references/skill_guide.md)
- [Best Practices](../../references/best_practices.md)
- [Architecture Patterns](../../references/architecture_patterns.md)
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: 472k | 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 |