This skill should be used when the user asks about "spec methodology", "specification workflow", "spec-driven development", "how to write specs", "spec best practices", "specification templates", or needs guidance on creating, validating, decomposing, or executing specifications for software development.
Provides a 4-phase spec-driven workflow: create, validate, decompose, and execute specifications. Triggered when users mention "spec methodology", "spec-driven development", or need guidance on writing specs for non-trivial features.
/plugin marketplace add betamatt/claude-plugins/plugin install spec@betamatt-claude-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/overengineering-patterns.mdreferences/spec-template.mdA systematic approach to software development that starts with comprehensive specifications before implementation.
The spec workflow consists of four phases:
/spec:create -> /spec:validate -> /spec:decompose -> /spec:execute
/spec:create)Generate a comprehensive specification document using first-principles thinking:
When to use: Starting any non-trivial feature or bugfix
/spec:validate)Analyze the specification for completeness and detect overengineering:
When to use: Before decomposing, after major spec revisions
/spec:decompose)Break the validated spec into actionable implementation tasks:
When to use: After spec passes validation
/spec:execute)Implement using orchestrated specialist agents:
When to use: After decomposition creates tasks
Before any solution, validate the problem:
Be aggressive about cutting scope:
When creating tasks from specs:
Each phase has validation checkpoints:
If installed, provides persistent task tracking:
stm init # Initialize
stm add "Task" --details "..." # Create task
stm list --pretty # View tasks
stm update [id] --status done # Complete task
Built-in session task tracking when STM unavailable.
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.