// Create new Agent Skills interactively or from templates. Use when user wants to create, generate, scaffold, or build a new skill, or mentions creating skills, writing skills, skill templates, skill development.
| name | skill-creator |
| description | Create new Agent Skills interactively or from templates. Use when user wants to create, generate, scaffold, or build a new skill, or mentions creating skills, writing skills, skill templates, skill development. |
| allowed-tools | ["Read","Write","Edit"] |
Creates new Agent Skills through interactive wizard or template-based generation. A meta-skill for bootstrapping Claude Code capabilities.
Ask the user which mode they prefer:
Ask these questions in order:
~/.claude/skills/ (just for you).claude/skills/ (shared with team)Available templates in templates/:
| Template | Purpose | Best For |
|---|---|---|
pr-reviewer | Review pull requests against standards | Teams with code review workflows |
commit-helper | Generate commit messages from diffs | Projects with commit conventions |
api-caller | Call external APIs with auth | Integrations with external services |
code-analyzer | Analyze code quality and patterns | Codebases needing quality checks |
data-processor | Process CSV/JSON data files | Data transformation workflows |
Always generate:
SKILL.md - Complete with:
.claude-plugin/plugin.json - With:
README.md - With:
examples.md (if skill type includes it) - With:
Conditionally generate:
Before creating files, validate:
--- delimiters)Use Write tool to create files in the selected location.
For target location = "standalone", create full plugin structure:
skill-name/
├── SKILL.md
├── .claude-plugin/
│ └── plugin.json
├── README.md
└── examples.md
After creating files, tell the user:
What Skills are available? should list the new skillReviews pull requests against team standards. Checks for common issues, provides structured feedback format, integrates with git workflow.
Generates conventional commit messages from git diffs. Supports custom commit conventions, formats summaries and body, handles commit types.
Integrates with external APIs. Handles authentication (API keys, OAuth), rate limiting, error responses, request/response parsing.
Analyzes code quality. Detects anti-patterns, suggests improvements, generates quality reports, supports multiple languages.
Processes data files (CSV, JSON, YAML). Validates schemas, transforms data, handles large files, generates outputs.
Bash(python:*))When a skill needs helper scripts:
## Utility Scripts
This skill includes helper scripts for complex operations:
```bash
# Validate input
python scripts/validate.py input.txt
# Transform data
python scripts/transform.py input.csv output.json
### Skill with Reference
For technical/API skills, reference detailed docs:
```markdown
## Technical Reference
For complete API details, see [reference.md](reference.md).
If the skill needs environment setup:
## Requirements
Set these environment variables:
- `API_KEY`: Your service API key
- `ENDPOINT`: API endpoint URL
Install dependencies:
```bash
pip install requests pydantic
## Troubleshooting
### Skill Not Appearing
- Verify SKILL.md path is correct
- Check YAML frontmatter is valid
- Run `claude --debug` to see loading errors
### Description Not Triggering
- Add more specific trigger phrases
- Include keywords users would naturally say
- Test with different query phrasings
### Validation Errors
- Check name is kebab-case only
- Verify description length < 1024 chars
- Ensure YAML has proper `---` delimiters
## Examples
See [examples.md](examples.md) for complete walkthroughs of creating skills in each mode.
Publish Claude Code conversation threads as static HTML pages hosted on GitHub Gists, with shareable gistpreview links. Use when the user asks to share, publish, or delete a Claude Code thread.
Publish Claude Code conversation threads as static HTML pages hosted on GitHub Gists, with shareable gistpreview links. Use when the user asks to share, publish, or delete a Claude Code thread.
Run diagnostic git commands to assess a codebase's health before reading any code. Use this skill whenever the user asks you to understand a new codebase, audit a repo, assess technical debt, find risky code, check project health, figure out where to start reading, identify bus factor risks, or explore an unfamiliar repository. Also use it when the user asks 'what's going on in this repo', 'where are the problem areas', 'give me a health check', or 'what should I look at first'. If the user wants to understand a codebase at a strategic level before diving into code, this is the skill to use.
Generate Builder Methods hand-drawn line art illustrations (icons, scenes, periphery) with a single accent color (Coral/Teal/Indigo/Amber). Use for blog headers, thumbnails, course graphics, social posts, and on-brand UI/tech metaphors.
Assistant for creating, editing, and debugging reactive Python notebooks with marimo. Use when you need to build marimo notebooks, debug reactive execution, add interactive UI elements, or convert traditional notebooks to marimo format. Provides code patterns, utility functions, and best practices for marimo development.
AI-Powered Security Testing Toolkit - Professional penetration testing scripts for discovering vulnerabilities, analyzing application structure, and generating context-aware security tests. All scripts return structured JSON for agent consumption.