Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
/plugin marketplace add GGPrompts/TabzBeads/plugin install meta@tabz-beadsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
LICENSE.txtreferences/creation-process.mdreferences/requirements.mdreferences/skill-anatomy.mdscripts/init_skill.pyscripts/package_skill.pyscripts/quick_validate.pySkills are modular packages that extend Claude's capabilities with specialized knowledge, workflows, and tools. They transform Claude from a general-purpose agent into a domain specialist.
| Topic | Reference |
|---|---|
| Directory structure, SKILL.md format, bundled resources | references/skill-anatomy.md |
| Step-by-step creation process (Steps 1-6) | references/creation-process.md |
| File size limits, script requirements, best practices | references/requirements.md |
Skills use three-level loading:
SKILL.md should be < 200 lines. Move detailed content to references/.
Use imperative form: "To accomplish X, do Y" not "You should do X".
skill-name/
├── SKILL.md # Required: metadata + instructions
├── scripts/ # Optional: executable code
├── references/ # Optional: documentation loaded on-demand
└── assets/ # Optional: files used in output
Skills live in a plugin's skills/ directory - ONE level deep only:
my-plugin/
├── plugin.json
└── skills/
├── skill-a/ # ✅ Correct
│ └── SKILL.md
└── skill-b/ # ✅ Correct
└── SKILL.md
# ❌ WRONG - nested skills won't be discovered:
└── skills/
└── parent/
└── skills/ # Nesting breaks discovery!
└── child/
└── SKILL.md
Key rule: Never nest skills inside skills. Each skill is a direct child of skills/.
scripts/init_skill.py <name> --path <dir>scripts/package_skill.py <path>See references/creation-process.md for detailed steps.
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.