面试题库

7 天 Agent Skills：把经验做成可复用能力

D1 Skills 是什么：SKILL.md 规范、目录结构与三阶段渐进式加载

• Agent Skills 解决的是什么问题？它和把所有规范写进一个大的提示词文件有什么区别？What problem do Agent Skills solve, and how are they different from putting every convention into one big instruction file?

  国内高频海外高频基础#agent-skills#context-engineering

  分析过程 · 先想清楚再作答

  1. 这题的区分度在你有没有说出「按需」两个字。只答「skill 是可复用的提示词」的人，等于没答，因为那句话对提示词模板同样成立。
  2. 先给分工：工具补的是能力缺口，模型本来做不到的事；技能补的是经验缺口，模型做得到但不知道你们这儿怎么做。这一刀切下去，后面的论证才站得住。
  3. 再给机制差异：常驻指令文件每次会话全量进上下文，skill 平时只露 name 与 description，命中才展开正文。前者的成本是固定的，后者的成本是按需的。
  4. 接着算代价：二十条规范写满六千 token 的系统提示，五十轮会话要重复计费三十万 token；更贵的是注意力被不相干的规则稀释，做第三件事时被第十七条干扰。
  5. 最后给判据，这是面试官真正想听的一句：这条经验是不是每次都用得上？是就写进常驻指令文件，不是就做成 skill。
  6. 可预期的追问是「那提示词模板呢」。答案是谁来挑：模板是你手动选的，skill 是模型读着 description 自己选的，触发权在模型手里。

  How to reason about it · think before answering

  1. The discriminator is whether you say on demand. Answering skills are reusable prompts says nothing, because that is equally true of a prompt template.
  2. Start with the split: tools fill a capability gap the model cannot cross on its own; skills fill an experience gap where the model can do the task but not the way your team does it.
  3. Then the mechanism: a persistent instruction file enters context in full every session, while a skill exposes only name and description until something matches and its body is loaded.
  4. Quantify the cost: twenty conventions at six thousand tokens of system prompt bill three hundred thousand tokens over a fifty-turn session, and the attention dilution costs more than the money.
  5. Close with the rule of thumb interviewers want: if the guidance applies every single time, it belongs in the persistent instruction file; otherwise make it a skill.
  6. Expected follow-up: what about prompt templates? The difference is who chooses. You pick a template; the model picks a skill by reading descriptions.

  答题要点

  • 工具补能力缺口，技能补经验缺口，这是两件事，不要混着答。
  • 常驻指令文件成本固定且每轮重发，skill 的正文只在命中时才进上下文。
  • 把不相干的规范全塞进系统提示，除了花钱还会稀释注意力，让模型被无关规则干扰。
  • 判据是「是不是每次都用得上」：是就常驻，不是就做成 skill。
  • 和提示词模板的关键差别是触发权在模型手里，靠的是 description。

  Key points

  • Tools close capability gaps, skills close experience gaps. Do not blur the two.
  • A persistent instruction file costs the same tokens every turn; a skill body only enters context when it matches.
  • Dumping unrelated conventions into the system prompt both costs money and dilutes attention.
  • The test is whether the guidance applies every time: if yes it stays resident, if no it becomes a skill.
  • Unlike a prompt template, a skill is selected by the model itself from its description.

D3 设计方法：从重复任务提炼、检查清单式与参考手册式、四种反模式与触发测试

• 什么样的任务适合做成 skill，什么样的不适合？给我一套能当场用的判断标准。Which tasks are worth turning into a skill and which are not? Give me a test I can apply on the spot.

  国内高频海外高频基础#agent-skills#skill-design

  分析过程 · 先想清楚再作答

  1. 这题最容易答成「重复的、复杂的任务」，那是所有人都会说的话，没有区分度。面试官想听的是一套能证伪的判据，以及每一条判据背后的道理。
  2. 给三条，并且强调三条都要成立：重复（干过至少三次且还会干）、有纠正（模型第一次做时你打断过它）、结果可检验（做完能判断对错）。
  3. 逐条解释为什么。「有纠正」是最硬的一条，因为它同时证明模型确实不会、你确实会——没有纠正记录的 skill 写出来大概率是「妥善处理错误」这类正确的废话。
  4. 「可检验」这条常被忽略但很关键：它决定的不是这个 skill 能不能写，而是**你能不能迭代它**。对错要三个月后才知道的任务，你写完只能凭感觉觉得有用。
  5. 然后给反面：不满足这三条会怎样——不重复的没人用，没纠正的是废话，不可检验的没法改进。这一句把判据从清单变成了论证。
  6. 可预期的追问是「那范围多大合适」。答案是像拆函数一样：一个内聚的工作单元，且能与别的 skill 组合。两个总是一起激活的 skill 本来就是一个；描述里忍不住写「等等」说明范围太大了。

  How to reason about it · think before answering

  1. The lazy answer is repetitive and complex tasks, which anyone can say. The interviewer wants a falsifiable test plus the reasoning behind each part.
  2. Give three criteria and insist all three must hold: repetition (done at least three times and will recur), correction (you interrupted the model the first time), and checkable results (you can tell afterwards whether it was right).
  3. Explain each. Correction is the strongest, because it simultaneously proves the model does not know and that you do. Without correction history you produce generic filler like handle errors appropriately.
  4. Checkability is the one people skip, and it decides not whether you can write the skill but whether you can iterate on it. If correctness only surfaces in three months, you are guessing.
  5. Then state the failure modes: without repetition nobody uses it, without correction it is filler, without checkability you cannot improve it.
  6. Expected follow-up: how wide should one skill be? Scope it like a function: one coherent unit that composes with others. Two skills always activated together were one skill; if the description needs and so on, the scope is too wide.

  答题要点

  • 三条判据全部成立才动手：重复、有纠正、结果可检验。
  • 有纠正是最硬的一条，它同时证明模型不会而你会。
  • 可检验决定的不是能不能写，而是能不能迭代。
  • 范围按内聚工作单元切，总是一起激活的两个 skill 应该合并。
  • 描述里出现「等等」「以及相关的」，说明范围已经太大，该拆。

  Key points

  • All three must hold before you start: repetition, correction, checkable results.
  • Correction is the strongest signal because it proves both the gap and your expertise.
  • Checkability decides whether you can iterate, not whether you can write it.
  • Scope to one coherent unit; two skills that always activate together should be merged.
  • If the description needs and so on, the scope is already too wide.

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.