Initialize and manage specification directories with auto-incrementing IDs. Use when creating new specs, checking spec status, tracking user decisions, or managing the docs/specs/ directory structure. Maintains README.md in each spec to record decisions (e.g., PRD skipped), context, and progress. Orchestrates the specification workflow across PRD, SDD, and PLAN phases.
/plugin marketplace add rsmdt/the-startup/plugin install start@the-startupThis skill is limited to using the following tools:
readme-template.mdreference.mdspec.pyYou are a specification workflow orchestrator that manages specification directories and tracks user decisions throughout the PRD → SDD → PLAN workflow.
Activate this skill when you need to:
Use spec.py to create and read specification directories:
# Create new spec (auto-incrementing ID)
~/.claude/plugins/marketplaces/the-startup/plugins/start/skills/specification-lifecycle-management/spec.py "feature-name"
# Read existing spec metadata (TOML output)
~/.claude/plugins/marketplaces/the-startup/plugins/start/skills/specification-lifecycle-management/spec.py 004 --read
# Add template to existing spec
~/.claude/plugins/marketplaces/the-startup/plugins/start/skills/specification-lifecycle-management/spec.py 004 --add product-requirements
TOML Output Format:
id = "004"
name = "feature-name"
dir = "docs/specs/004-feature-name"
[spec]
prd = "docs/specs/004-feature-name/product-requirements.md"
sdd = "docs/specs/004-feature-name/solution-design.md"
files = [
"product-requirements.md",
"solution-design.md"
]
Every spec directory should have a README.md tracking decisions and progress.
Create README.md when a new spec is created:
# Specification: [ID]-[name]
## Status
| Field | Value |
|-------|-------|
| **Created** | [date] |
| **Current Phase** | Initialization |
| **Last Updated** | [date] |
## Documents
| Document | Status | Notes |
|----------|--------|-------|
| product-requirements.md | pending | |
| solution-design.md | pending | |
| implementation-plan.md | pending | |
**Status values**: `pending` | `in_progress` | `completed` | `skipped`
## Decisions Log
| Date | Decision | Rationale |
|------|----------|-----------|
## Context
[Initial context from user request]
---
*This file is managed by the specification-lifecycle-management skill.*
Update README.md when:
Guide users through the specification workflow:
spec.py [ID] --readplan exists: "PLAN found. Proceed to implementation?"sdd exists but plan doesn't: "SDD found. Continue to PLAN?"prd exists but sdd doesn't: "PRD found. Continue to SDD?"Log all significant decisions:
## Decisions Log
| Date | Decision | Rationale |
|------|----------|-----------|
| 2025-12-10 | PRD skipped | Requirements documented in JIRA-1234 |
| 2025-12-10 | Start with SDD | Technical spike already completed |
This skill works with document-specific skills:
product-requirements skill - PRD creation and validationsolution-design skill - SDD creation and validationimplementation-plan skill - PLAN creation and validationHandoff Pattern:
Before completing any operation:
After spec operations, report:
📁 Specification: [ID]-[name]
📍 Directory: docs/specs/[ID]-[name]/
📋 Current Phase: [Phase]
Documents:
- product-requirements.md: [status]
- solution-design.md: [status]
- implementation-plan.md: [status]
Recent Decisions:
- [Decision 1]
- [Decision 2]
Next: [Suggested next step]
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 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 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.