Spec Driven Development Plugin
Plugin Verified ActiveSpecification Driven Development workflow commands and agents, based on Github Spec Kit and OpenSpec. Uses specialized agents for effective context management and quality review.
To enable consistent and high-quality code generation by providing a structured, agent-driven workflow that automates the process from task specification to implementation.
Features
- Specification Driven Development workflow
- Multi-agent orchestration for complex tasks
- LLM-as-Judge for automated quality verification
- Task refinement, architecture synthesis, and decomposition
- Parallel execution of implementation steps
Use Cases
- Developing new features following a structured process
- Ensuring code quality through automated verification
- Breaking down complex tasks into manageable, parallelizable steps
- Generating detailed task specifications and architecture blueprints
Non-Goals
- Replacing direct coding entirely
- Handling tasks without clear specifications
- Providing a generic code generation tool without a structured workflow
Workflow
- Add Task: Create draft task file
- Plan Task: Refine task through research, analysis, architecture, decomposition, parallelization, and verification
- Implement Task: Execute refined steps with automated quality checks
Practices
- Specification Driven Development
- Agent Orchestration
- LLM-as-Judge Verification
- Test-Driven Development principles
Documentation
- info:Configuration & parameter referenceThe README mentions customization via command parameters but does not detail them or their defaults. Further information is likely in linked customization guides.
Installation
First, add the marketplace
/plugin marketplace add NeoLabHQ/context-engineering-kit/plugin install sdd@context-engineering-kitContains 5 extensions
Skill (5)
creates draft task file in .specs/tasks/draft/ with original user intent
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
Generate ideas in one shot using creative sampling
Implement a task with automated LLM-as-Judge verification for critical steps
Refine, parallelize, and verify a draft task specification into a fully planned implementation-ready task
Quality Score
VerifiedTrust Signals
Similar Extensions
Uc Taskmanager
100SDD WORK-PIPELINE Agent — Requirements analysis & development 6-agent full pipeline with DAG-based orchestration and sliding window context management
Kanban
100Markdown-based Kanban board managed by Claude Code. Cards live as .md files — no database, no server.
Ag2 Agent Builder
100Build AG2 (AutoGen) multi-agent systems with slash commands: scaffold agents, wire workflows, create tools, and review code
Testing Handbook Skills
99Skills from the Trail of Bits Application Security Testing Handbook (appsec.guide)
Planning With Files
99Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Works with Claude Code, Kiro, Clawd CLI, Gemini CLI, Cursor, Continue, Hermes, and 17+ AI coding assistants. Now with Arabic, German, Spanish, and Chinese (Simplified & Traditional) support.
Ruvlo SPARC
97SPARC methodology — Specification, Pseudocode, Architecture, Refinement, Completion phases with gate checks