面试题库

7 天 Agent Skills：把经验做成可复用能力

D4 带脚本的 skill：可执行附件、依赖与沙箱、跨平台，以及文档处理类 skill 的拆解

• 什么逻辑该写成脚本放进 skill 的 scripts 目录，什么该留在 SKILL.md 正文里？Which logic belongs in a skill's scripts directory and which belongs in the SKILL.md body?

  国内高频海外高频基础#agent-skills#scripts

  分析过程 · 先想清楚再作答

  1. 这题在考分工感。答「复杂的写脚本」等于没答，因为复杂是个没有边界的词。面试官要听的是可判定的信号。
  2. 给三条信号，命中任意一条就写脚本：同一段逻辑在执行轨迹里被重新发明了第三次；结果必须逐字一致（校验、格式转换、哈希）；一条命令复杂到第一次很难敲对。
  3. 把第二条展开成分工原则，这是本题的核心句：**确定性任务交给代码，判断性任务留给模型**。让模型「按指令做」意味着每次都有偏移的可能，让它跑脚本意味着结果确定。
  4. 再给反面：只是调一个现成工具加两三个参数，直接在正文写这条命令就行，不必建 scripts 目录。很多生态有免安装的一次性运行方式，用它们时**版本必须钉死**，否则上游一发版你的 skill 行为就变了。
  5. 补一条成本视角：脚本是长期资产，要维护、要跟模板同步、要有人看得懂。三条信号一条都不命中的时候，写正文更划算。
  6. 可预期的追问是「怎么发现模型在重新发明轮子」。答案是读执行轨迹而不是只看最终产出——同一个辅助函数在几次运行里反复出现，就是该沉淀成脚本的信号。

  How to reason about it · think before answering

  1. This tests a sense of division of labor. Saying complex logic goes in scripts says nothing, because complex has no boundary. The interviewer wants decidable signals.
  2. Give three: the same logic gets reinvented a third time across execution traces; the result must be byte-identical (validation, format conversion, hashing); or a command is complex enough to be hard to get right first try.
  3. Expand the second into the core principle: deterministic work goes to code, judgment work stays with the model. Following instructions leaves room for drift; running a script does not.
  4. Give the other side: invoking an existing tool with two or three flags belongs inline in the body. Many ecosystems offer install-free one-off runners, and versions must be pinned or an upstream release silently changes your skill's behavior.
  5. Add the cost view: a script is a long-lived asset that must be maintained and kept in sync. When none of the three signals fire, prose is cheaper.
  6. Expected follow-up: how do you notice reinvention? Read execution traces rather than final outputs; the same helper appearing across runs is the signal.

  答题要点

  • 三条信号命中任一条就写脚本：重复发明第三次、结果必须逐字一致、命令复杂到难以一次敲对。
  • 分工原则是确定性任务交给代码，判断性任务留给模型。
  • 只加两三个参数调现成工具的，直接在正文写命令，但版本要钉死。
  • 脚本是长期资产，有维护成本，三条都不命中就写正文。
  • 发现重复发明要靠读执行轨迹，不是看最终产出。

  Key points

  • Write a script when any of three fire: third reinvention, byte-identical results required, or a command hard to get right first try.
  • Deterministic work to code, judgment work to the model.
  • A tool invocation with a couple of flags stays inline, with the version pinned.
  • Scripts are long-lived assets with maintenance cost; if no signal fires, write prose.
  • Spot reinvention by reading execution traces, not final outputs.
• 给 Agent 用的命令行脚本，接口设计上和给人用的有什么不同？How does designing a command-line script for an agent differ from designing one for a human?

  国内高频海外高频进阶#agent-skills#scripts#cli-design

  分析过程 · 先想清楚再作答

  1. 题眼是「不同」。能列出五条通用 CLI 最佳实践的人很多，能说清哪几条是因为「使用者是模型」才成立的人少。
  2. 先给根本差异：人会读文档、会试错、会凭经验猜；Agent 只能读你打印的那几行字然后决定下一步。**它的全部信息就是你的输出**。
  3. 由此推出五条。绝对不能交互，这是硬要求不是最佳实践，Agent 在非交互终端里回答不了提示，会一直挂到超时。
  4. 帮助信息就是接口文档，但要短——这段输出原样进上下文，跟别的东西抢位置，这是给人用的 CLI 完全不必考虑的约束。
  5. 错误信息决定它下一次会不会做对：写清哪一项错了、期望什么、实际是什么、可选值有哪些。**错误信息本质上是给模型的提示词**，这一句是拿分点。
  6. 剩下两条：输出结构化并把数据与诊断分流到标准输出与标准错误；输出体量要可控，因为很多 Agent 环境会静默截断超长输出。再补幂等、有意义的退出码、危险操作给预演开关。
  7. 可预期的追问是「怎么验证接口设计得好」。答案是把帮助输出和一条错误信息单独发给一个没看过这个 skill 的人，他能照着敲对改对，模型大概率也能。

  How to reason about it · think before answering

  1. The hinge is the difference. Many can list CLI best practices; few can say which ones exist specifically because the caller is a model.
  2. State the root difference: humans read docs, experiment and guess from experience; an agent has only the lines you printed before deciding the next move.
  3. From that: never prompt interactively. This is a hard requirement, not a nicety, because agents run in non-interactive shells and will hang until timeout.
  4. Help output is the interface documentation, but it must be short, since it enters the context window and competes with everything else. A human CLI never faces this constraint.
  5. Error messages decide the next attempt: say what failed, what was expected, what was received, and which values are allowed. Error messages are effectively prompts for the model.
  6. Then: structured output with data on stdout and diagnostics on stderr, and bounded output size because many harnesses truncate silently. Add idempotency, meaningful exit codes, and a dry-run flag for destructive work.
  7. Expected follow-up: how do you validate the design? Hand the help text and one error message to someone who has never seen the skill; if they can act on it, the model probably can too.

  答题要点

  • 根本差异：Agent 的全部信息就是你打印的输出，它不会读文档也不会试错。
  • 绝不能交互，否则在非交互终端里会挂到超时。
  • 帮助信息就是接口文档，但必须短，因为它原样占用上下文。
  • 错误信息要写清哪项错、期望什么、实际什么、可选值有哪些，它本质是给模型的提示词。
  • 结构化输出并分流标准输出与标准错误，输出体量要可控，危险操作给预演开关。

  Key points

  • The agent's only information is what you printed; it does not read docs or experiment.
  • Never prompt interactively; a non-interactive shell will hang until timeout.
  • Help text is the interface documentation and must be short because it consumes context.
  • Error messages must state the field, the expectation, the actual value and the allowed set; they are prompts for the model.
  • Emit structured data on stdout and diagnostics on stderr, bound output size, and offer a dry-run for destructive operations.