AI 概览 · 由大模型根据 SKILL.md 与仓库数据生成 · 2026年11月20日
BMAD 系列 Agent Skill 集合:覆盖需求、设计、开发与评审
仓库定位为更好的 Agentic 开发环境,内含一组以 SKILL.md 形式组织的 BMAD 系列 Agent Skill,覆盖需求发现、头脑风暴、架构与 UX 设计、开发构建、代码评审和冲刺变更评估等环节。采集资料未给出具体输入输出与执行步骤,实际能力需回到源文件确认。
包含 Skill
33
可以单独安装
GitHub Star
39
仓库累计 Star
代码更新
2026年11月19日
最近一次推送
核心亮点
1流程覆盖广
从需求、设计到开发与评审都有对应技能
2组织方式统一
均以 SKILL.md 形式放在技能目录下
3角色化分工
产品、分析、架构、开发等角色各有独立技能
能做什么
- 对已有输出做深度质疑与改进,支持苏格拉底式、第一性原理等方法
- 整理资料研究结果并形成结构化报告
- 梳理界面方案与视觉表达,辅助设计协作
- 拆解开发任务,覆盖编码、调试与评审环节
- 评估冲刺阶段重大变更的影响并给出变更提案
适用场景
让助手用第一性原理方法重新审视一段方案
在需求阶段调用产品角色技能梳理 PRD
开发前用架构技能梳理模块划分
提交前用代码评审技能做一轮检查
冲刺中评估需求变更对文档的影响
用之前和用之后
- 助手给出的方案缺少深入质疑,容易停留在表面可调用深度质疑类技能,从多个角度重新审视并改进输出
- 需求、设计、开发各环节零散推进,缺少统一入口按环节选择对应技能,形成较清晰的流程分工
它是怎么工作的
第 1 步
明确任务
第 2 步
调用对应技能
第 3 步
复核输出
快速上手
安装与复制命令见“安装方式”。
- 1
打开仓库查看技能目录结构
- 2
挑选与当前任务匹配的技能文件
- 3
阅读该技能的说明与触发条件
- 4
在支持的 AI 编程环境中按说明调用
- 5
对输出结果自行复核后再采用
适合谁
- 使用 AI 编程助手做项目开发的工程师
- 需要梳理需求与文档的产品人员
- 关注设计方案的 UX 与架构人员
局限
- 采集资料未提供各技能的输入输出与执行步骤
- 部分技能说明为英文,中文用户需自行理解
- 技能效果依赖所用 AI 环境是否支持该技能格式
使用前注意
- · 采集资料将各技能风险等级标为 high,使用前请核验具体行为
- · 技能会推动模型改写或评审输出,重要结论建议人工复核
包含的 Skills · 33
- Bmad Advanced ElicitationAgentPush the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.claude/skills/bmad-advanced-elicitation/SKILL.md
- Bmad Agent AnalystAgentBusiness analyst for market research, competitive analysis, and requirements. Use when the user asks to talk to Mary or requests the business analyst.claude/skills/bmad-agent-analyst/SKILL.md
- Bmad Agent ArchitectAgentSystem architect and technical design leader. Use when the user asks to talk to Winston or requests the architect.claude/skills/bmad-agent-architect/SKILL.md
- Bmad Agent DevAgentSenior software engineer who implements stories and code changes. Use when the user asks to talk to Amelia or requests the developer agent.claude/skills/bmad-agent-dev/SKILL.md
- Bmad Agent PmAgentProduct manager for PRD creation and requirements discovery. Use when the user asks to talk to John or requests the product manager.claude/skills/bmad-agent-pm/SKILL.md
- Bmad Agent Ux DesignerAgentUX designer and UI specialist. Use when the user asks to talk to Sally or requests the UX designer.claude/skills/bmad-agent-ux-designer/SKILL.md
- Bmad ArchitectureAgentWork out and record the architecture decisions that keep separately built parts of a system consistent, in a short architecture document. Creates, updates, or validates one; works from a spec, a raw idea, or an existing codebase. Use when t.claude/skills/bmad-architecture/SKILL.md
- Bmad BrainstormingAgentFacilitate a brainstorming session using diverse creative techniques. Use when the user says 'help me brainstorm' or 'help me ideate'.claude/skills/bmad-brainstorming/SKILL.md
- Bmad Build AutoAgentOne iteration of an unattended development loop. Use when invoked by name.claude/skills/bmad-build-auto/SKILL.md
- Bmad BuildAgentTurns implementation work into working code, reviewed and verified. Use when the user delegates a feature, story, bug fix, or meaningful change; a bare story or issue link counts. Skip obvious, low-risk mechanical maintenance such as small .claude/skills/bmad-build/SKILL.md
- Bmad Code ReviewAgentReview code changes with several independent reviewers in parallel, then triage and present the findings. Use when the user says "run code review" or "review this code".claude/skills/bmad-code-review/SKILL.md
- Bmad Correct CourseAgentAssess the impact of a significant change during sprint execution across the PRD, epics, architecture, and UX documents, and produce a sprint change proposal. Use when the user says "correct course" or "propose sprint change".claude/skills/bmad-correct-course/SKILL.md
- Bmad CustomizeAgentAuthors and updates customization overrides for installed BMad skills. Use when the user says 'customize bmad', 'override a skill', 'change agent behavior', or 'customize a workflow'.claude/skills/bmad-customize/SKILL.md
- Bmad Deep ReconAgentResearch a topic to support a decision, three ways: draft a research prompt for the user to run in their own tool (ChatGPT, Gemini, Grok, Perplexity, …), turn a finished research report into a short summary with cited sources that other ski.claude/skills/bmad-deep-recon/SKILL.md
- Bmad EvalAgentRuns the evals of a BMad skill through the agent harness the user works in and reports what they show: baseline against the bare model, variant against a stripped or prior version, quality against a rubric, and trigger accuracy of the descr.claude/skills/bmad-eval/SKILL.md
- Bmad Forge IdeaAgentTest a half-formed idea in a questioning conversation, with different personas probing its weak points, until the user can act on it or drop it with confidence. Optionally writes a short brief for planning skills to build on. Use when the u.claude/skills/bmad-forge-idea/SKILL.md
- Bmad Party ModeAgentOrchestrates lively group discussions between installed BMAD agents or custom personas, and helps author custom parties. Use when the user requests party mode, a roundtable, or multiple agent perspectives — or wants to create/configure a pa.claude/skills/bmad-party-mode/SKILL.md
- Bmad PrdAgentCreate, update, or validate a PRD. Use when the user wants help producing, editing, or validating a PRD.claude/skills/bmad-prd/SKILL.md
- Bmad PrfaqAgentTest a product concept with Amazon's Working Backwards method: write the press release for the finished product first, then answer hard customer and stakeholder questions, ending in a complete PRFAQ document. Use when the user requests to '.claude/skills/bmad-prfaq/SKILL.md
- Bmad Product BriefAgentCreate, update, or validate a product brief. Use when the user wants help producing, editing, or validating a brief.claude/skills/bmad-product-brief/SKILL.md
- Bmad Project ContextAgentSet up, adopt, refresh, or audit a repository's agent instructions (the AGENTS.md block) so AI agents work well in that repo. Also records observed agent mistakes as pitfalls. Use when invoked by name.claude/skills/bmad-project-context/SKILL.md
- Bmad Qa Generate E2e TestsAgentGenerate automated API and end-to-end tests for implemented features. Use when the user says "create qa automated tests for [feature]".claude/skills/bmad-qa-generate-e2e-tests/SKILL.md
- Bmad RetrospectiveAgentReview a finished epic folder in the ticket tree against the evidence it left behind — the epic file, each ticket plan, diffs, commits — and produce a retrospective with sourced findings, action items, and an acceptance decision. Use when t.claude/skills/bmad-retrospective/SKILL.md
- Bmad ReviewAgentRuns one or more installed review lenses — adversarial critique, edge cases, verification gaps, structure, prose — and reports triaged findings. Use when, and only when, the user asks you to review a diff, a pull request, or an artifact — c.claude/skills/bmad-review/SKILL.md
- BmadAgentAnswers BMad questions and recommends the next skill from what is installed. Use when the user asks bmad for help, what to do next or where to start; to set up, update, repair, doctor, migrate or check the status of the installation, or add.claude/skills/bmad/SKILL.md
- Bmad SpecAgentCondense any input — an idea, brief, PRD, transcript, or mixed notes — into a short spec: one kernel file plus supporting files that downstream skills build from. Also updates and validates existing specs. Use when the user says "create a s.claude/skills/bmad-spec/SKILL.md
- Bmad TicketAgentCreate and manage tickets — initiatives, epics, stories, bugs. Use when the user says "create a new initiative", "slice this initiative", "split this epic up", "break this into stories", "incept this epic", "make a ticket", "refine this tic.claude/skills/bmad-ticket/SKILL.md
- Bmad ToolsmithAgentSmithy the Toolsmith builds, converts, reviews, packages, validates and migrates BMad skills, agents and modules. Use when the user wants a skill, agent, persona, command or module made, changed, reviewed or packaged; a prompt or rule from .claude/skills/bmad-toolsmith/SKILL.md
- Bmad UxAgentCapture the user's UX vision in two documents: DESIGN.md for how the product looks and EXPERIENCE.md for how it behaves. Use when the user says "lets create UX design" or "create UX specifications" or "help me plan the UX".claude/skills/bmad-ux/SKILL.md
- Bmad WalkthroughAgentGuide a human review of a commit, PR, file, or directory. Use when invoked by name.claude/skills/bmad-walkthrough/SKILL.md
- Bmod Core ToolsAgentRequired bmod metadata. Never invoke this skill..claude/skills/bmod-core-tools/SKILL.md
- Bmod MethodAgentRequired bmod metadata. Never invoke this skill..claude/skills/bmod-method/SKILL.md
- Bmod ToolsmithAgentRequired bmod metadata. Never invoke this skill..claude/skills/bmod-toolsmith/SKILL.md
公开来源
相关 Skills
查看更多ECC
314 Skills编程智能体技能集 · affaan-m
覆盖 Agent 评估、安全、架构审查、支付接入和网关测试等场景,可用于梳理任务流程、执行专项检查并形成结构化产出。
ponytail
6 Skills精简编程技能集 · DietrichGebert
覆盖任务拆解、代码评审、快捷参考与简化债务标记整理,适合在开发和交付过程中调用相应 Skill 辅助处理具体任务。
impeccable
20 SkillsAgent 设计语言 · pbakaus
为编码代理提供一套设计表达方式,可在开发过程中打磨界面、评审设计并检查交付前的粗糙产出,适合前端与设计协作场景。
security-audit-skill
JavaScript代码安全审计技能 · cloudflare
用于资料研究、事实整理和结构化报告写作,适合需要按流程开展安全审计并整理结果的场景。
