agent-team

Compatibility shell for the legacy umbrella agent-team skill. Use only when older prompts still reference `agent-team`; route the request to the dedicated scenario skill instead of treating this file as the primary execution surface.

专精于前端项目架构设计和工程化的角色，负责项目搭建、架构设计、代码质量把控。掌握现代前端工具链（Vite、Turborepo、Vitest等）和设计模式最佳实践。 Use when the user asks for frontend-architect-related work such as: 项目初始化和搭建（vite）, 前端架构设计和技术决策, eslint、commitlint、vscode 配置, 代码审核和 core review, vitest 单元测试配置, 组件库 e2e 测试配置, 工具库打包配置（tsdown）, 技术栈选型和最佳实践.

Go CLI 核心代码开发者，负责 agent-team 项目 internal/ 和 cmd/ 目录下的所有 Go 代码改动 Use when the user asks for go-backend-related work such as: go 代码开发 (internal/ + cmd/), cobra cli 命令实现, yaml 数据模型设计与存储, 单元测试编写, 代码重构.

Growth marketing role for project promotion across social media platforms, content creation, and community engagement Use when the user asks for growth-marketer-related work such as: social media content creation, x/twitter thread writing, launch announcement drafting, developer community outreach, content calendar planning, copywriting for technical audiences, hashtag and seo strategy, basic legal compliance review for published content.

McKinsey-style business consultant for hypothesis-driven problem solving, structured analysis, and strategic recommendations Use when the user asks for mckinsey-consultant-related work such as: business problem structuring, mece issue tree decomposition, hypothesis formation and testing, market sizing and estimation, competitive analysis, strategic recommendation development, executive summary and report writing, data-driven insight synthesis, stakeholder communication frameworks.

产品总监角色，精通产品战略、用户研究、优先级排序、路线图规划、SaaS 指标分析、研讨会引导和团队领导力发展，覆盖从发现到交付的完整产品管理生命周期 Use when the user asks for pd-related work such as: 产品战略与定位, 用户研究与客户发现, 优先级排序与路线图, saas 指标与财务分析, 用户故事与 epic 管理, 竞品分析与市场评估, 研讨会引导与协作, pm 到 director/vp/cpo 职业发展教练, 定价策略, 创新冲刺与验证实验.

Senior Pencil UI/UX Designer specializing in design systems, responsive interfaces, and accessible applications with mandatory Pencil MCP integration Use when the user asks for pencil-designer-related work such as: design system creation, web/mobile ui design, component design, responsive design, accessibility compliance (wcag), design asset generation, pencil mcp workflows.

Full-stack product manager covering strategy, discovery, execution, go-to-market, market research, data analytics, marketing growth, and PM toolkit Use when the user asks for product-manager-related work such as: product strategy & vision, market research & competitive analysis, product discovery & feature prioritization, prd & user story creation, sprint planning & retrospectives, go-to-market strategy, data analytics & a/b testing, pricing & monetization, okr & metrics definition, stakeholder management.

测试编写与集成验证工程师，负责 agent-team 项目的单元测试、CLI 命令测试和端到端集成验证 Use when the user asks for qa-tester-related work such as: go 单元测试编写, cli 命令测试, 端到端集成测试, 构建验证 (go build/vet/test), 测试覆盖率分析.

规则文件与 Provider 文件编写者，负责 .agents/rules/*.md、CLAUDE.md、AGENTS.md、GEMINI.md 的内容编写与维护 Use when the user asks for rules-writer-related work such as: markdown 规则文件编写 (.agents/rules/), provider 文件编写 (claude.md/agents.md/gemini.md), 规则索引维护, 上下文管理规则设计, 任务协议文档编写.

资深 UniApp 开发工程师，专精于 UnoCSS 原子化 CSS、Vite 工程化、UniApp 跨平台开发和 UCharts 数据可视化，具有丰富的小程序/H5/App 全场景交付经验 Use when the user asks for uniapp-dev-related work such as: uniapp 跨平台开发（h5/微信小程序/app）, unocss 原子化 css 配置与自定义规则, vite 构建配置与插件开发, ucharts 图表组件开发与数据可视化, vue 3 组件设计与应用架构, 前端性能优化与最佳实践, 类型安全（typescript）与工程化实践.

资深 Vite-React 开发工程师，专精于 UnoCSS 原子化 CSS、Vite 工程化、Vitest 测试、React 现代开发模式和 TanStack 全家桶（Router/Query/Form/Table），具有丰富的 SPA 应用交付经验 Use when the user asks for vite-react-dev-related work such as: react 组件开发与架构设计, vite 构建配置与插件开发, unocss 原子化 css 配置与自定义规则, tanstack router/query/form/table 集成开发, vitest 单元测试与集成测试, typescript 类型安全实践, 前端性能优化与最佳实践.

Create or update role-specific skill packages with deterministic files. Supports output to skills/ (open-source publishing) or .agent-team/teams/ (team use). Triggers: 创建角色, 新建 role, create role, 更新 role scope, edit role, update role, add role skill, 修改角色配置. Use when the user asks to create, update, or edit frontend/backend/product (or custom) role skills with auto-generated role fields, guided brainstorming fallback, and curated skills selection.

Use when users explicitly ask to brainstorm, shape requirements, compare approaches, or produce a planning/design document before implementation. Turn rough ideas into validated brainstorming/design docs through focused dialogue, role-based analysis, and explicit user approval. Do not trigger this skill for straightforward implementation requests that do not need dedicated design exploration.

Read-only catalog browsing skill for searching and viewing role catalog information. Use when the user wants to list, search, inspect, or review catalog repositories and statistics.

Project bootstrap and migration entry for initializing agent-team in a repository or migrating legacy project state.

Read-only local role browsing skill for controller, worker, and human sessions. Use when the user wants to list available local roles without creating roles or managing repositories.

Role source management skill for finding, adding, listing, checking, updating, and removing role repositories. Use when the user is managing where roles come from rather than browsing the catalog.

Rule refresh skill for syncing built-in rule templates and generated rule artifacts. Use when the user asks to sync rules or fix rule drift.

Skill cache maintenance skill for checking, updating, and cleaning installed skill artifacts. Use when the user asks to inspect or refresh skill cache state.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Read-only task inspection skill for controller, worker, and human sessions. Use when the user wants to view task status, inspect a task, or list tasks without changing lifecycle state.

Scenario-first task lifecycle entry for controller and human sessions. Use when the user asks to create, assign, complete, archive, or inspect task flow through `agent-team task` commands.

Controller-side worker dispatch entry for opening workers, checking targeted worker status, and replying to workers with existing `agent-team worker` and `agent-team reply` commands.

Read-only worker inspection skill for controller and human sessions. Use when the user wants to view worker status without opening a worker or sending a reply.

Worker-first recovery entry for resuming the current assignment from file artifacts. Use when a worker needs to recover task context, continue work, or re-anchor after a pause.

Governance-only workflow plan entry for controller and human sessions. Use when the user asks to generate, approve, activate, or close workflow plans through `agent-team workflow plan`.

Decompose requirement, design, or brainstorming documents into reviewable task drafts with one function per task and one file per task, then create `agent-team` task packages only after explicit approval. Use when turning a document into tasks, splitting oversized tasks, validating task boundaries, or preparing approved task files for `agent-team task create`.

Session context cleanup and file re-anchoring strategy for controller and worker sessions. Use when the session is drifting, phases change, or resumed work needs index-first recovery from files.

Acceptance-first TDD workflow for solo implementation work. Use when handling a coding change directly and you want to follow a disciplined sequence: read context, define acceptance criteria, write failing tests when feasible, implement, verify, and conclude with passed, failed, or skipped with reason.

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

This skill should be used when establishing comprehensive QA testing processes for any software project. Use when creating test strategies, writing test cases following Google Testing Standards, executing test plans, tracking bugs with P0-P4 classification, calculating quality metrics, or generating progress reports. Includes autonomous execution capability via master prompts and complete documentation templates for third-party QA team handoffs. Implements OWASP security testing and achieves 90% coverage targets.

Expert guidance for writing secure, reliable, and performant Claude Code hooks - validates design decisions, enforces best practices, and prevents common pitfalls. Use when creating, reviewing, or debugging Claude Code hooks.

Worker-first reporting entry for sending completion, blocker, or decision-needed messages back to main through `agent-team reply-main`.