dss-time Repo Onboarding（仓库理解）
Use the section matching the user's language. 使用与用户输入语言一致的章节。
Execution Contract
Default to fast; bounded natural-language invocation is allowed.
Complete one primary task by default. Continue an authorized end-to-end workflow within each Skill's permissions; Router remains recommendation-only. Pause for new material decisions or scope, not authorization already given.
Validate according to actual risk; security, production, migrations, releases and other high-risk work use audit. Read references/execution-modes.en.md only when mode selection is unclear.
Repo Onboarding
Use this skill to understand an unfamiliar repository before editing code.
Safety Boundary
- Read-only by default.
- Do not modify files.
- Do not run commands unless the environment and user request allow it.
- Separate facts from assumptions.
Workflow
- Inspect repository metadata and top-level structure.
- Identify the language, framework, package manager, and build tools.
- Read important README, manifest, config, CI, test, and plugin files.
- Identify entry points, core modules, scripts, and validation commands.
- Identify risky areas such as public interfaces, shared utilities, authentication, data migrations, generated files, release scripts, or build config.
- Produce a practical onboarding map and reading order.
Output Format
- Project summary
- Technology stack
- Directory map
- Entry points and core flow
- How to run and validate
- Recommended reading order
- Risk areas
- Recommended next step
Use tables where they improve scanability. Include evidence for commands and file roles.
执行契约
默认使用 fast；允许边界明确的自然语言隐式调用。
默认完成一个主任务。用户已授权完整流程时，在各 Skill 权限内连续完成；Router 仍只推荐。新重大决策或超出授权时暂停，不重复索取已有授权。
按实际风险选择验证；安全、生产、迁移、发布等高风险工作使用 audit。模式不明确时才读取 references/execution-modes.zh-CN.md。
仓库理解
用于在修改代码前理解一个陌生仓库。
安全边界
- 默认只读。
- 不修改文件。
- 除非环境和用户明确允许，否则不运行命令。
- 区分事实和推断。
工作流程
- 检查仓库元数据和顶层目录结构。
- 识别语言、框架、包管理器和构建工具。
- 阅读重要的 README、manifest、配置、CI、测试和插件文件。
- 识别入口文件、核心模块、脚本和验证命令。
- 识别风险区域，例如公共接口、共享工具、认证、数据迁移、生成文件、发布脚本或构建配置。
- 输出实用的仓库理解地图和新人阅读顺序。
输出格式
- 项目总结
- 技术栈
- 目录地图
- 入口文件和核心流程
- 运行与验证方式
- 推荐阅读顺序
- 风险区域
- 下一步建议
能提升可读性时使用表格。命令和文件职责需要给出证据。