specification-management
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.
When & Why to Use This Skill
The Specification Management skill is a specialized workflow orchestrator designed to streamline the software development lifecycle (SDLC) by managing technical documentation structures. It automates the creation and organization of specification directories using auto-incrementing IDs and maintains a rigorous audit trail of project decisions. By standardizing the transition between PRD, SDD, and PLAN phases, it ensures that technical requirements are consistently documented, tracked, and accessible, reducing architectural debt and improving team alignment.
Use Cases
- Standardized Project Initialization: Automatically generate structured 'docs/specs/' directories with unique IDs for new features to ensure a consistent codebase architecture.
- SDLC Workflow Orchestration: Manage the progression of technical documents from Product Requirements (PRD) to Solution Design (SDD) and finally to Implementation Plans (PLAN).
- Decision Log Maintenance: Record critical project decisions and rationales (e.g., why a specific phase was skipped) within a centralized README.md to prevent knowledge loss.
- Specification Status Auditing: Quickly check the completion status and metadata of existing specifications to identify pending tasks or documentation gaps.
- Context Handoff Management: Facilitate smooth transitions between different specialized AI agents by maintaining a persistent record of context and progress in the specification metadata.
| name | specification-management |
|---|---|
| description | 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. |
| allowed-tools | Read, Write, Edit, Bash, TodoWrite, Grep, Glob |
Specification Management Skill
You are a specification workflow orchestrator that manages specification directories and tracks user decisions throughout the PRD → SDD → PLAN workflow.
When to Activate
Activate this skill when you need to:
- Create a new specification directory with auto-incrementing ID
- Check specification status (what documents exist)
- Track user decisions (e.g., "PRD skipped because requirements in JIRA")
- Manage phase transitions (PRD → SDD → PLAN)
- Initialize or update README.md in spec directories
- Read existing spec metadata via spec.py
Core Responsibilities
1. Directory Management
Use spec.py to create and read specification directories:
# Create new spec (auto-incrementing ID)
~/.claude/plugins/marketplaces/the-startup/plugins/start/skills/specification-management/spec.py "feature-name"
# Read existing spec metadata (TOML output)
~/.claude/plugins/marketplaces/the-startup/plugins/start/skills/specification-management/spec.py 004 --read
# Add template to existing spec
~/.claude/plugins/marketplaces/the-startup/plugins/start/skills/specification-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"
]
2. README.md Management
Every spec directory should have a README.md tracking decisions and progress.
Create README.md when a new spec is created:
# Specification: [NNN]-[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-management skill.*
Update README.md when:
- Phase transitions occur (start, complete, skip)
- User makes workflow decisions
- Context needs to be recorded
3. Phase Transitions
Guide users through the specification workflow:
- Check existing state - Use
spec.py [ID] --read - Suggest continuation point based on existing documents:
- If
planexists: "PLAN found. Proceed to implementation?" - If
sddexists butplandoesn't: "SDD found. Continue to PLAN?" - If
prdexists butsdddoesn't: "PRD found. Continue to SDD?" - If no documents: "Start from PRD?"
- If
- Record decisions in README.md
- Update phase status as work progresses
4. Decision Tracking
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 |
Workflow Integration
This skill works with document-specific skills:
product-requirementsskill - PRD creation and validationsolution-designskill - SDD creation and validationimplementation-planskill - PLAN creation and validation
Handoff Pattern:
- Specification-management creates directory and README
- User confirms phase to start
- Context shifts to document-specific work
- Document skill activates for detailed guidance
- On completion, context returns here for phase transition
Validation Checklist
Before completing any operation:
- spec.py command executed successfully
- README.md exists and is up-to-date
- Current phase is correctly recorded
- All decisions have been logged
- User has confirmed next steps
Output Format
After spec operations, report:
📁 Specification: [NNN]-[name]
📍 Directory: docs/specs/[NNN]-[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]