Assists in creating Agent Skills of varying complexity levels (simple, moderate, complex). Use when the user wants to create, design, or build a new Agent Skill, or when they need guidance on skill architecture, workflow design, schema validation, or template structure.
Guides you through building Agent Skills from requirements to validation using a structured 5-phase workflow. Triggers when users want to create a new skill or need help with skill architecture, workflow design, or template structure.
/plugin marketplace add leefowlercu/agent-kit/plugin install agent-skill-builder@leefowlercu-agent-kitThis skill inherits all available tools. When active, it can use any tool Claude has access to.
README.mdreferences/schemas/skill-requirements.schema.jsonreferences/schemas/skill-structure.schema.jsonreferences/templates/complex/SKILL.template.mdreferences/templates/complex/schema.template.jsonreferences/templates/complex/workflow-step.template.mdreferences/templates/moderate/SKILL.template.mdreferences/templates/moderate/reference.template.mdreferences/templates/simple/SKILL.template.mdreferences/workflow/01-gathering-requirements.mdreferences/workflow/02-determining-archetype.mdreferences/workflow/03-planning-structure.mdreferences/workflow/04-generating-skill-md.mdreferences/workflow/05-generating-workflow-references.mdreferences/workflow/06-generating-schemas.mdreferences/workflow/07-generating-scripts.mdreferences/workflow/08-validating-skill.mdreferences/workflow/09-iterating-on-feedback.mdscripts/validate-json.jsscripts/validate-skill.jsThis skill enables the creation of Agent Skills following established best practices and patterns. It provides a structured workflow for gathering requirements, determining appropriate complexity (archetype), planning structure, generating artifacts, and validating the resulting skill.
The skill supports three archetypes:
Before starting the workflow you MUST:
This workflow guides you through creating an Agent Skill from requirements to validation. The workflow is organized into five distinct phases:
Phase 1: Discovery - Gather requirements and analyze complexity needs.
Phase 2: Planning - Design the skill structure and file organization.
Phase 3: Implementation - Generate all skill artifacts.
Phase 4: Validation - Verify skill correctness and quality.
Phase 5: Iteration - Refine based on feedback and ensure readiness.
When executing this workflow you MUST:
Objective: Understand what the user needs to build
See Gathering Requirements Workflow Step Reference for detailed guidance.
Objective: Determine appropriate skill architecture
See Determining Archetype Workflow Step Reference for detailed guidance.
Phase 1 Approval Gate: Present complete requirements and archetype decision. Obtain explicit user approval before Phase 2.
Objective: Create approved blueprint for the skill
See Planning Structure Workflow Step Reference for detailed guidance.
Phase 2 Approval Gate: Present complete structure plan including file manifest and generation order. Obtain explicit user approval before Phase 3.
Objective: Generate core skill definition
See Generating SKILL.md Workflow Step Reference for detailed guidance.
Objective: Generate supporting documentation
See Generating Workflow References Step Reference for detailed guidance.
See Generating Schemas Workflow Step Reference for detailed guidance.
Objective: Generate executable components
See Generating Scripts Workflow Step Reference for detailed guidance.
Phase 3 Approval Gate: Present all generated artifacts for review. Obtain explicit user approval before Phase 4.
Objective: Verify skill correctness
See Validating Skill Workflow Step Reference for detailed guidance.
Phase 4 Approval Gate: Present validation results. Obtain explicit user approval before Phase 5.
Objective: Incorporate user feedback
See Iterating on Feedback Workflow Step Reference for detailed guidance.
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.