boss
BMAD 全自动项目编排 Skill。从需求到部署的完整研发流水线,编排多个专业 Agent(PM、架构师、UI 设计师、Tech Lead、Scrum Master、开发者、QA、DevOps)自动完成完整研发周期。当用户说 'boss mode'、'/boss'、'全自动开发'、'从需求到部署'、'帮我做一个'、'build this'、'ship it'、'全流程'、'自动化开发'、'一键开发'、'start a project'、'new feature' 时使用。适用于新项目搭建或现有代码库添加功能。
Why use this skill?
Transform your software workflow with Boss, an OpenClaw agent skill that automates the entire lifecycle from requirements to deployment using the BMAD method.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/echovic/boss-skillWhat This Skill Does
Boss is a comprehensive, full-stack AI orchestration engine for OpenClaw designed to automate the entire software development lifecycle (SDLC) using the BMAD (Boss Method for Agile Development) framework. Instead of performing a single task, the Boss skill acts as a project conductor, delegating specific software engineering roles—including Project Managers, Architects, Designers, Tech Leads, QA Engineers, and DevOps—to different specialized agents. The skill manages the transition between requirements gathering, architecture design, task breakdown, development, rigorous testing, and automated deployment. It operates on a principle of artifact-driven development, ensuring every stage generates verifiable documentation and code outputs before proceeding to the next gate.
Installation
To integrate the Boss agent into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/echovic/boss-skill
Ensure your workspace has appropriate write permissions, as the skill needs to create a .boss/ directory to store project artifacts and progress tracking files.
Use Cases
- New Feature Implementation: Automatically add a new module to an existing repository with full test coverage.
- Greenfield Projects: Rapidly bootstrap a new application, from initial design specs to a live, deployed instance.
- Standardized Development: Enforce a consistent R&D workflow across teams by forcing the use of standardized artifacts like PRDs, architectural diagrams, and QA reports.
- Rapid Prototyping: Use the
--quickflag to bypass user confirmations for ultra-fast, end-to-end scaffolding.
Example Prompts
- "Boss mode: build a secure user authentication API service for my existing node project."
- "/boss start a project to create a task management dashboard with React and FastAPI, make sure to include full unit tests."
- "Ship it! I need a new feature to handle image uploads for the current app, please handle everything from design to deployment."
Tips & Limitations
- Artifacts are key: The skill relies heavily on the generated markdown files in the
.boss/directory. If the agent stalls, check the latest generatedtasks.mdto see where the workflow is paused. - Quality Gates: Do not bypass the quality gate checks (
references/quality-gate.md) in a production environment. The QA agent is designed to catch failures before the DevOps agent triggers a deployment. - Context awareness: The agent performs best when provided with specific constraints in the initial prompt regarding tech stacks or specific library preferences. For existing projects, ensure the agent has read access to your codebase to allow for accurate structure exploration.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-echovic-boss-skill": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution
Related Skills
spec-flow
Spec-driven development workflow. Interactive phase-by-phase confirmation from proposal to implementation. Trigger: 'spec-flow', 'spec mode', 'need a plan', 'structured development', 'write a spec', 'feature spec', 'technical spec', '需求文档', '技术方案', '任务拆解', '规格驱动', '写个方案', '做个规划', '结构化开发', 'plan this feature', 'break this down', 'design doc'. Creates .spec-flow/ directory with proposal, requirements, design, and tasks.
learning-system
AI 领域系统学习体系。管理知识图谱、深度学习笔记、实战复盘和关联网络。触发场景:学习计划、知识图谱更新、深度研究某个 AI 主题、实战复盘总结、调研后沉淀知识、每周学习回顾。当用户说'学了什么'、'总结一下'、'沉淀知识'、'复盘'、'更新图谱'、'深入研究'、'写笔记'、'学习回顾'、'review what I learned'、'update knowledge map'、'deep dive'、'recap'、'what did I learn' 时使用。当改完代码/读完论文/做完调研后需要提炼和归纳时使用。