From claude-code-dev
Creates new Claude Code agent skills with proper folder structure, SKILL.md format, and optional examples/templates. Use when adding model-invoked skills for autonomous activation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-code-dev:create-skillThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Create new Claude Code agent skills that Claude invokes autonomously based on task context.
Create new Claude Code agent skills that Claude invokes autonomously based on task context.
Each skill lives in its own folder within skills/:
skills/
└── skill-name/
├── SKILL.md # Main skill definition (required)
├── examples/ # Example files (optional)
│ └── example.md
└── templates/ # Templates (optional)
└── template.md
---
name: skill-name
description: When and how Claude should use this skill. Be specific about triggers and use cases.
user-invocable: false
---
# Skill Title
Detailed instructions for how to apply this skill...
| Field | Description | Example |
|---|---|---|
name | Unique identifier (kebab-case) | python-best-practices |
description | When Claude should invoke this skill | Apply Python best practices when writing or reviewing Python code. Use for type hints, docstrings, and PEP compliance. |
| Field | Description | Default | Example |
|---|---|---|---|
user-invocable | Whether users can invoke skill with /skill-name | true | false for knowledge skills, true for action skills |
The description is critical - it tells Claude when to use the skill. Include:
description: Apply React best practices when creating or modifying React components. Use for hooks, state management, component structure, and performance optimization.
description: Enforce security best practices when writing code that handles user input, authentication, or sensitive data. Covers input validation, SQL injection prevention, and XSS protection.
description: Generate API documentation when creating or updating REST endpoints. Produces OpenAPI-compatible documentation with examples.
# Too vague - Claude won't know when to use it
description: Helps with Python code
# Too broad - will trigger too often
description: Use this for all coding tasks
The body should include:
---
name: conventional-commits
description: Apply conventional commit message format when the user is committing code or asking about commit messages. Enforces type prefixes, scope, and message structure.
user-invocable: false
---
# Conventional Commits
Format all commit messages following the Conventional Commits specification.
## Format
[optional scope]:
[optional body]
[optional footer(s)]
## Types
| Type | Description |
|------|-------------|
| `feat` | New feature |
| `fix` | Bug fix |
| `docs` | Documentation only |
| `style` | Formatting, no code change |
| `refactor` | Code restructuring |
| `perf` | Performance improvement |
| `test` | Adding tests |
| `chore` | Maintenance tasks |
## Examples
### Feature
feat(auth): add OAuth2 login support
### Bug Fix
fix(api): handle null response in user endpoint
### Breaking Change
feat(api)!: change response format for /users endpoint
BREAKING CHANGE: Response now returns array instead of object
## Rules
1. Type is required and lowercase
2. Description starts lowercase, no period at end
3. Use imperative mood ("add" not "added")
4. Keep first line under 72 characters
Skills can include reference materials:
skills/
└── api-design/
├── SKILL.md
├── examples/
│ ├── rest-example.md
│ └── graphql-example.md
└── templates/
└── openapi-template.yaml
Reference these in your SKILL.md:
See `examples/rest-example.md` for a complete REST API example.
Save skills to:
plugins/<plugin-name>/skills/<skill-name>/SKILL.md
npx claudepluginhub jpoutrin/product-forge --plugin claude-code-devGuides creation of Claude Code SKILL.md files with YAML frontmatter, progressive disclosure, and naming conventions. Use when authoring or auditing agent skills.
Guides creating Claude Code skills: clarify purpose, set file structure, configure frontmatter like disable-model-invocation, user-invocable, hooks. Triggers on 'create skill' requests.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.