netease-lcap

Watch PR checks and merge when successful

全量分析现有代码仓库，逆向生成为 Codewave (LCAP) 规范模板，输出 spec.md + menus.md + TypeScript 实体/枚举文件。

分析代码仓库，自动识别功能模块并生成编号规格说明文档。多智能体架构：研究→规划→写作。

在任务生成后对 spec.md、plan.md 和 tasks.md 执行非破坏性的跨产物一致性和质量分析。

根据用户需求为当前功能生成自定义检查清单。

通过提出最多 5 个高度针对性的澄清问题来识别当前功能规格中未充分说明的区域，并将答案编码回规格中。

创建或更新项目宪章以定义项目的核心原则和不可协商规则。

通过处理并执行 tasks.md 中定义的所有任务来执行实现计划

Manage Wave settings and get guidance on settings.json, hooks, environment variables, permissions, MCP servers, memory, skills, subagents, plugins, and plugin marketplaces. Use this when the user wants to view, update, or learn how to configure Wave.

Reviews code for best practices and potential issues.

A test skill from the complex plugin.

根据自然语言描述创建或更新功能规格说明。生成 specs/NNN-name.md，包含用户故事、验收标准和功能需求。

Review the current diff for correctness bugs and reuse/simplification/efficiency cleanups at the given effort level (low/medium: fewer, high-confidence findings; high/max: broader coverage, may include lower-confidence findings)

Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.

Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report

Analyze the codebase and create an AGENTS.md file to guide future agents.