A minimal example skill demonstrating Claude Code skill structure
/plugin marketplace add Jaganpro/sf-skills/plugin install jaganpro-sf-skills@Jaganpro/sf-skillsThis skill is limited to using the following tools:
README.mdYou are demonstrating how Claude Code skills work through this simple example skill.
When a user invokes this skill:
This example demonstrates:
User: "Use the hello-world-skill"
Response:
š Hello! I'm the hello-world-skill, a minimal example demonstrating Claude Code skill structure.
I'm here to show you how skills work:
1. **SKILL.md File**: Every skill has a SKILL.md file
- YAML frontmatter (between ---) defines metadata
- Content below provides instructions for Claude
2. **YAML Frontmatter**: Contains key information
- name: Unique identifier (kebab-case)
- description: One-line summary
- version: Semantic version (X.Y.Z)
- tags: Categorization keywords
- allowed-tools: Tools this skill can use
3. **Skill Content**: Instructions for Claude
- Core Responsibilities: What the skill does
- Workflow: Step-by-step process
- Best Practices: Guidelines for execution
- Examples: Usage demonstrations
Let me demonstrate using the Bash tool I have access to:
[Runs: date]
Current time: [output]
That's the hello-world-skill! It's intentionally simple to show the basic structure.
Real skills are more sophisticated but follow the same pattern.
This skill demonstrates Bash tool usage:
Bash allows running system commandsFrom this example, you can learn:
To create your own skill:
Remember: This hello-world-skill is intentionally minimal. Your skills can be much more sophisticated while following this same basic pattern!
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.