AI coding相关harness

负责系统设计、可扩展性和技术决策的软件架构专家。当规划新功能、重构大型系统或进行架构决策时，应主动使用。

使用 Vercel Agent Browser（首选）及 Playwright 备选的端到端测试专家。主动用于生成、维护和运行 E2E 测试。管理测试流程、隔离不稳定测试、上传工件（截图、视频、追踪），并确保关键用户流程正常运行。

需求分析、需求洞察、idea转产品需求、产品功能设计、产品原型设计、PRD编写

文档同步：End-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, README.md, docs/) and agent memory against the code so nothing rots. 会话结束后对项目文档和记忆进行洁癖级审查与同步。MUST trigger when the user says: "sync up", "tidy up docs", "update memory", "clean up docs", "/sync", "/neat", "同步一下", "整理文档", "整理一下", "更新记忆", "梳理一下", "收尾", "这个阶段做完了", "新人能直接上手", or any phrase suggesting a dev milestone where knowledge needs reconciliation. Also trigger when the user reports stale docs, conflicting memories, or wants a clean handoff to teammates or other agents. Bare "整理" / "tidy" with prior dev context counts — do not under-trigger. Cross-platform: works on Claude Code, OpenAI Codex, OpenCode, and OpenClaw.

Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.

“当 OpenSpec 变更完成并准备归档时使用。通过 OpenSpec CLI 自动同步规范和归档。由 /soc-build 完成后直接触发。”

当一个 OpenSpec 变更的 tasks.md 已准备好进行实现时使用。为每个任务派发子智能体，自动更新任务状态。

在任何创意工作前必须使用——创建特性、构建组件、添加功能或修改行为。通过对话头脑风暴需求，然后通过 CLI 生成 OpenSpec proposal。