spec-management
Central authority for specification-driven development. Use when working with requirements, specifications, acceptance criteria, or any spec-driven workflow. Provides navigation to specialized skills and delegates to docs-management for official documentation.
Full skill instructions
Central hub for specification-driven development workflows. This skill provides navigation to specialized skills for different specification formats and workflows.
Keywords: specifications, requirements, acceptance criteria, spec-driven development, SDD, EARS, Gherkin, Kiro, Spec Kit, BDD, user stories, feature specifications, canonical spec
Use this skill when:
What do you want to do?
/spec:speckit:run or see speckit-workflow skill/spec:specify command/spec:convert commandThe canonical specification model (ADR-115) supports multiple providers:
| Provider | Format | Best For |
|---|---|---|
| ears | EARS syntax | Precise, unambiguous requirements |
| gherkin | .feature files | BDD tests with Reqnroll |
| kiro | AWS Kiro | IDE integration with steering files |
| speckit | GitHub Spec Kit | AI agent prompts, 5-phase workflow |
| adr | MADR format | Architecture decisions |
| userstory | Agile format | Product backlog items |
| canonical | YAML/JSON | Direct canonical format |
The GitHub Spec Kit workflow guides feature development:
| Phase | Artifact | Purpose |
|---|---|---|
| 0 | .constitution.md | Project principles and constraints |
| 1 | feature.md | Specification from requirements |
| 2 | design.md | Implementation approach |
| 3 | tasks.md | Task breakdown |
| 4 | Code | Guided implementation |
Full workflow: Use /spec:speckit:run or invoke the speckit-workflow skill.
All providers transform to/from the canonical model:
id: "SPEC-001"
title: "Feature Title"
type: feature | bug | chore | spike | tech-debt
context:
problem: "Description of the problem"
motivation: "Business value"
requirements:
- id: "REQ-001"
text: "EARS-formatted requirement"
priority: must | should | could | wont
ears_type: ubiquitous | state-driven | event-driven | unwanted | complex | optional
acceptance_criteria:
- id: "AC-001"
given: "Precondition"
when: "Action"
then: "Expected outcome"
traceability:
adr_refs: ["ADR-115"]
requirement_refs: ["FR-001"]
metadata:
status: draft
created: "YYYY-MM-DD"
provider: canonical
bounded_context: "WorkManagement"
Full schema: See canonical-spec-format skill or schemas/canonical-spec.schema.json
| Command | Purpose |
|---|---|
/spec:specify | Phase 1: Generate specification from requirements |
/spec:plan | Phase 2: Generate implementation plan |
/spec:tasks | Phase 3: Generate task breakdown |
/spec:implement | Phase 4: Guide implementation |
/spec:validate | Validate specification against schema |
/spec:refine | AI-assisted specification refinement |
/spec:audit | Audit specification quality |
/spec:convert | Convert between formats |
| Command | Purpose |
|---|---|
/spec:ears:author | Interactive EARS pattern authoring |
/spec:ears:convert | Convert to/from EARS format |
/spec:gherkin:author | Interactive Gherkin scenario authoring |
/spec:gherkin:convert | Convert to/from .feature files |
/spec:kiro:sync | Sync with AWS Kiro specifications |
/spec:speckit:run | Execute full Spec Kit 5-phase workflow |
/spec:adr:create | Create ADR from specification context |
/spec:userstory:author | Author user stories with acceptance criteria |
/spec:constitution | Create or update project constitution |
/spec:status | Show specification status dashboard |
This skill delegates to specialized skills for detailed guidance:
| Topic | Delegate To |
|---|---|
| EARS patterns | ears-authoring skill |
| Gherkin/BDD | gherkin-authoring skill |
| AWS Kiro | kiro-integration skill |
| Spec Kit workflow | speckit-workflow skill |
| Quality criteria | requirements-quality skill |
| Canonical format | canonical-spec-format skill |
| Official Claude Code docs | docs-management skill |
This plugin integrates with project infrastructure:
| Resource | Purpose |
|---|---|
schemas/canonical-spec.schema.json | Canonical specification JSON Schema |
prompts/specify.prompt.md | Generation template for Phase 1 |
templates/EARS-REQUIREMENT-TEMPLATE.md | EARS pattern reference |
docs/adr/ADR-115-* | Specification Provider Abstraction |
Detailed Documentation:
Last Updated: 2025-12-24
Use when designing digital asset management systems, media libraries, upload pipelines, or asset metadata schemas. Covers media storage patterns, file organization, metadata extraction, and media APIs for headless CMS.
Explore entire codebase with Gemini's large context window. Use when starting on unfamiliar codebases or mapping dependencies across large projects.
Extract requirements from existing documents including PDFs, Word docs, meeting transcripts, specifications, and web content. Identifies requirement candidates, categorizes them, and outputs in pre-canonical format.
Use when designing data pipelines, choosing between ETL and ELT approaches, or implementing data transformation patterns. Covers modern data pipeline architecture.
Validate state and merge branch to main for production deployment. Use as final ZTE step after all checks pass.
Central authority for Claude Agent SDK (TypeScript and Python SDKs). Covers SDK installation, authentication (Anthropic key, Bedrock, Vertex), sessions and resumption, forking sessions, streaming vs single mode, custom tools, permissions (allowedTools, disallowedTools, permissionMode), MCP integr...
Multi-technique business analysis orchestration using BABOK. Coordinates 14 techniques across strategic analysis, problem solving, planning, and design into comprehensive analysis packages.
Comprehensive Windows 11 system diagnostics via PowerShell. Diagnoses crashes, freezes, reboots, BSOD, disk health, memory issues, hardware errors, and performance problems. Use when troubleshooting Windows stability issues, analyzing Event Viewer logs, checking disk/memory health, investigating ...
Create a Git commit with agent attribution for ADW workflows. Use after implementing changes to create semantically formatted commits.
CQRS pattern implementation and query optimization
Vector database selection, embedding storage, approximate nearest neighbor (ANN) algorithms, and vector search optimization. Use when choosing vector stores, designing semantic search, or optimizing similarity search performance.
Apply systematic test case design techniques including equivalence partitioning, boundary value analysis, decision tables, and state transition testing.
Generate, edit, and beat-sync AI video with leading models in one workspace.
The world's fastest calendar for remote work
Transform Your Design with AI Designer by ImgCreator.ai
Revolutionizing Video Production with AI-Powered Creativity
Extend an image past the frame and let AI fill the new aspect ratio.
Discover your celebrity doppelgänger with StarByFace!
ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.
Opus.ai: Revolutionize Your Web Experience