说清 · 把话说到 Claude 照做Say It Clearly · Phrase It So Claude Just Does It.
同一个问题，换种说法，答案差很远。最便宜的一次升级不是换模型，是把话说清楚 —— 把它当聪明但缺背景的新员工，给理由、给例子、给格式。这套说法横跨后面每一面。Same question, different phrasing, very different answer. The cheapest upgrade isn't a new model — it's saying it clearly: treat it as a brilliant new hire who lacks context, and give reasons, examples, and a format. This craft pays off on every surface ahead.
6 分钟 · 初稿 2026.066 Min · Drafted 2026.06
同一个问题，换种说法，答案差很远。最便宜的一次升级，不是换更强的模型、也不是切到新的一面，是把话说清楚 —— 这件事横跨后面每一章。Same question, different phrasing, very different answer. The cheapest upgrade isn't a stronger model or a new surface — it's saying it clearly, and that cuts across every chapter ahead.这一章不教你「提示词模板大全」那一套。它只给三件落地的事：把背景说出口、给理由别给禁令、给例子给角色给格式。学会了，你在网页、Projects、Cowork、终端每一面都更听话。This chapter isn't a 'prompt template megapack.' It gives three things you can act on: say the context out loud, give reasons not bans, and supply examples, a role, and a format. Learn it, and every surface — web, Projects, Cowork, the terminal — listens better.
— I
把它当聪明但缺背景的新员工Treat It as a Brilliant New Hire Who Lacks Context.
它不缺脑子，缺的是你脑子里没说出口的背景。It isn't short on brains — it's short on the context you never said out loud.Anthropic 自己的说法：把 Claude 想成一个绝顶聪明、但对你的规矩和流程一无所知的新同事。1注 1Note 1Claude API Docs · Prompting best practices —— 当前模型的提示工程总参考：清晰直接、给动机、用示例、XML 标签分区、给角色、明确输出格式。截至 2026-07。Claude API Docs · Prompting best practices — the reference for prompting current models: be clear and direct, give motivation, use examples, separate with XML tags, give a role, specify output format. As of 2026-07.它不会读心。有个一句话的检验：把你写的那段话，拿给一个不了解这件事的同事看 —— 他要回你几个问题，Claude 就会在那几处含糊。2注 2Note 2Claude API Docs · Prompt engineering overview —— 「把你的提示拿给一个不了解任务的同事看，他困惑，Claude 多半也困惑」即出自这套指南。Claude API Docs · Prompt engineering overview — the 'show your prompt to a colleague who lacks context; if they're confused, Claude likely is too' rule of thumb comes from this guide.Anthropic's own framing: think of Claude as a brilliant new colleague who knows nothing about your norms and workflows.1注 1Note 1Claude API Docs · Prompting best practices —— 当前模型的提示工程总参考：清晰直接、给动机、用示例、XML 标签分区、给角色、明确输出格式。截至 2026-07。Claude API Docs · Prompting best practices — the reference for prompting current models: be clear and direct, give motivation, use examples, separate with XML tags, give a role, specify output format. As of 2026-07. It can't read your mind. There's a one-line test: show what you wrote to a colleague who doesn't know the task — wherever they'd ask you a question, Claude will be just as unsure.2注 2Note 2Claude API Docs · Prompt engineering overview —— 「把你的提示拿给一个不了解任务的同事看，他困惑，Claude 多半也困惑」即出自这套指南。Claude API Docs · Prompt engineering overview — the 'show your prompt to a colleague who lacks context; if they're confused, Claude likely is too' rule of thumb comes from this guide.
缺背景No context
帮我润色一下这段。Polish this for me.
说清背景、约束、格式Context, constraints, format
把这段改简洁，读者是没技术背景的客户，保留所有数字和专有名词，控制在 200 字内。Tighten this for a non-technical client, keep every number and proper noun, under 200 words.
多花的是十几个字，省下的是三轮来回。它不是不够聪明，是你没把背景说出口。The cost is a dozen extra words; the saving is three rounds of back-and-forth. It isn't that it's not smart enough — it's that you didn't say the context out loud.
— II
给理由，别只给禁令Give the Reason, Not Just the Ban.
说该做什么、并说为什么，比堆一串「不要」更管用。Saying what to do — and why — beats stacking a list of 'don'ts.'两条合成一条。其一，给它你的理由，它能举一反三到你没列到的情况。官方那个例子很传神：与其说「不要用省略号」，不如说「这段会被语音朗读，省略号读不出来」—— 它就懂了，凡是朗读读不出的标点都避开，而不只是省略号。1注 1Note 1Claude API Docs · Prompting best practices —— 当前模型的提示工程总参考：清晰直接、给动机、用示例、XML 标签分区、给角色、明确输出格式。截至 2026-07。Claude API Docs · Prompting best practices — the reference for prompting current models: be clear and direct, give motivation, use examples, separate with XML tags, give a role, specify output format. As of 2026-07.其二，说该做什么，别说不该做什么：「用要点列出」比「不要写成大段」更容易照做。1注 1Note 1Claude API Docs · Prompting best practices —— 当前模型的提示工程总参考：清晰直接、给动机、用示例、XML 标签分区、给角色、明确输出格式。截至 2026-07。Claude API Docs · Prompting best practices — the reference for prompting current models: be clear and direct, give motivation, use examples, separate with XML tags, give a role, specify output format. As of 2026-07.Two rules in one. First, give it your reason and it generalizes to cases you didn't list. The official example lands it: instead of 'no ellipses,' say 'this will be read aloud by text-to-speech, which can't pronounce ellipses' — now it avoids every punctuation that won't read aloud, not just ellipses.1注 1Note 1Claude API Docs · Prompting best practices —— 当前模型的提示工程总参考：清晰直接、给动机、用示例、XML 标签分区、给角色、明确输出格式。截至 2026-07。Claude API Docs · Prompting best practices — the reference for prompting current models: be clear and direct, give motivation, use examples, separate with XML tags, give a role, specify output format. As of 2026-07. Second, say what to do, not what not to do: 'use bullet points' is easier to follow than 'don't write big paragraphs.'1注 1Note 1Claude API Docs · Prompting best practices —— 当前模型的提示工程总参考：清晰直接、给动机、用示例、XML 标签分区、给角色、明确输出格式。截至 2026-07。Claude API Docs · Prompting best practices — the reference for prompting current models: be clear and direct, give motivation, use examples, separate with XML tags, give a role, specify output format. As of 2026-07.
只给禁令Bans only
不要用省略号。不要太正式。No ellipses. Not too formal.
给理由 + 正向Reason + positive
这段会被 TTS 朗读，省略号读不出来 —— 用句号断句。读者是老朋友，写得像聊天、用「你」。This is read aloud by TTS, which can't say ellipses — break with periods. The reader's an old friend, so write like a chat, using 'you.'
— III
给例子、给角色、给格式Give Examples, a Role, a Format.
三个最省力的杠杆：一个角色、几个例子、一个明确的格式。The three lowest-effort levers: a role, a few examples, a clear format.角色：一句话给它一个身份就够 —— 「你是一位挑剔的文案编辑」—— 语气和侧重立刻收窄。1注 1Note 1Claude API Docs · Prompting best practices —— 当前模型的提示工程总参考：清晰直接、给动机、用示例、XML 标签分区、给角色、明确输出格式。截至 2026-07。Claude API Docs · Prompting best practices — the reference for prompting current models: be clear and direct, give motivation, use examples, separate with XML tags, give a role, specify output format. As of 2026-07.例子：贴 3–5 个「长这样」的样例，比任何形容词都稳，它会照着你的格式、语气、结构来；官方建议把例子用 <example> 这类标签框起来，跟指令分开。1注 1Note 1Claude API Docs · Prompting best practices —— 当前模型的提示工程总参考：清晰直接、给动机、用示例、XML 标签分区、给角色、明确输出格式。截至 2026-07。Claude API Docs · Prompting best practices — the reference for prompting current models: be clear and direct, give motivation, use examples, separate with XML tags, give a role, specify output format. As of 2026-07.Role: one sentence is enough — 'you are a picky copy editor' — and tone and focus snap into place.1注 1Note 1Claude API Docs · Prompting best practices —— 当前模型的提示工程总参考：清晰直接、给动机、用示例、XML 标签分区、给角色、明确输出格式。截至 2026-07。Claude API Docs · Prompting best practices — the reference for prompting current models: be clear and direct, give motivation, use examples, separate with XML tags, give a role, specify output format. As of 2026-07.Examples: paste 3–5 'looks like this' samples; they beat any adjective, and it follows your format, tone, and structure. Anthropic suggests wrapping them in tags like <example> so they stay separate from instructions.1注 1Note 1Claude API Docs · Prompting best practices —— 当前模型的提示工程总参考：清晰直接、给动机、用示例、XML 标签分区、给角色、明确输出格式。截至 2026-07。Claude API Docs · Prompting best practices — the reference for prompting current models: be clear and direct, give motivation, use examples, separate with XML tags, give a role, specify output format. As of 2026-07.格式：明说你要散文还是要点、要不要小标题、多长。当一条消息里既有指令又有要处理的材料时，用标签把两者切开（<instructions> 和 <context>），它就不会把材料误当成指令。1注 1Note 1Claude API Docs · Prompting best practices —— 当前模型的提示工程总参考：清晰直接、给动机、用示例、XML 标签分区、给角色、明确输出格式。截至 2026-07。Claude API Docs · Prompting best practices — the reference for prompting current models: be clear and direct, give motivation, use examples, separate with XML tags, give a role, specify output format. As of 2026-07.还有一条几乎总成立：长材料放最上面、你的问题放最后。1注 1Note 1Claude API Docs · Prompting best practices —— 当前模型的提示工程总参考：清晰直接、给动机、用示例、XML 标签分区、给角色、明确输出格式。截至 2026-07。Claude API Docs · Prompting best practices — the reference for prompting current models: be clear and direct, give motivation, use examples, separate with XML tags, give a role, specify output format. As of 2026-07.Format: spell out prose vs bullets, headers or not, how long. When one message holds both instructions and material to work on, split them with tags (<instructions> and <context>) so it won't mistake the material for instructions.1注 1Note 1Claude API Docs · Prompting best practices —— 当前模型的提示工程总参考：清晰直接、给动机、用示例、XML 标签分区、给角色、明确输出格式。截至 2026-07。Claude API Docs · Prompting best practices — the reference for prompting current models: be clear and direct, give motivation, use examples, separate with XML tags, give a role, specify output format. As of 2026-07. And one rule that almost always holds: put long material at the top, your question last.1注 1Note 1Claude API Docs · Prompting best practices —— 当前模型的提示工程总参考：清晰直接、给动机、用示例、XML 标签分区、给角色、明确输出格式。截至 2026-07。Claude API Docs · Prompting best practices — the reference for prompting current models: be clear and direct, give motivation, use examples, separate with XML tags, give a role, specify output format. As of 2026-07.
提示词Prompt说清模板The clear-ask template
角色：你是<一句话身份>。
背景：<它不知道、但影响答案的关键背景>。
要做：<具体动作>，因为<理由>。
格式：<散文 / 要点>，<长度上限>，先结论后展开。
像这样：<贴 1-3 个「长这样」的例子>。Role: you are <a one-line identity>.
Context: <key background it can't know but that changes the answer>.
Do: <specific action>, because <reason>.
Format: <prose / bullets>, <length cap>, conclusion first.
Like this: <paste 1-3 'looks like this' examples>.
角色：你是一位挑剔的科技产品文案编辑。
背景：这是一封发给已付费 Pro 用户的续费提醒邮件，读者反感营销腔。
要做：把下面这段草稿改得更短更直接，因为现在读着像群发广告。
格式：要点，不超过 5 条，先给改后版本再说改了什么。
像这样：把「我们非常高兴地通知您」改成「你的 Pro 下周到期」。Role: you are a picky copy editor for tech products.
Context: this is a renewal-reminder email to paying Pro users who hate marketing-speak.
Do: make the draft below shorter and more direct, because it currently reads like a mass ad.
Format: bullets, no more than 5, give the rewrite first then say what changed.
Like this: turn 'We are thrilled to inform you' into 'Your Pro plan ends next week.'
反过来，不是每次都得写长 prompt。任务一复杂、你自己也没想全时，与其硬写一份面面俱到的指令，不如让它先问你：The flip side: you don't always need a long prompt. When a task is complex and you haven't thought it all through, instead of forcing a comprehensive brief, have it ask you first:
提示词Prompt让它先问、先计划、先列风险Make it ask, plan, flag — first
这是个略复杂的任务，别急着做。先按这三步来：
1. 把你不清楚的地方列成问题问我，一次问完。
2. 给我一个分几步做的计划，等我点头。
3. 顺手说一句最大的风险或最容易出错的地方。
我确认完，你再动手。
任务：<把你的任务贴这里>。This is a somewhat complex task — don't rush in. Do these three first:
1. List what's unclear to you as questions and ask me, all at once.
2. Give me a step-by-step plan and wait for my go-ahead.
3. Add one line on the biggest risk or the easiest thing to get wrong.
Once I've confirmed, then start.
Task: <paste your task here>.
这是个略复杂的任务，别急着做。先按这三步来：
1. 把你不清楚的地方列成问题问我，一次问完。
2. 给我一个分几步做的计划，等我点头。
3. 顺手说一句最大的风险或最容易出错的地方。
我确认完，你再动手。
任务：把我们这季度的 12 份用户访谈整理成一份带主题归类的洞察报告。This is a somewhat complex task — don't rush in. Do these three first:
1. List what's unclear to you as questions and ask me, all at once.
2. Give me a step-by-step plan and wait for my go-ahead.
3. Add one line on the biggest risk or the easiest thing to get wrong.
Once I've confirmed, then start.
Task: turn our 12 user interviews from this quarter into an insight report grouped by theme.
把这章用到你最常用的那段提示上：Apply this to the prompt you use most:
01
挑一段你每周都用、却总要改两轮的 promptPick a weekly prompt that always takes two rounds to fix
找一段你反复用、但每次都要追加说明才对的提示词。Find a prompt you reuse but always have to follow up on before it's right.
02
按「角色 + 背景 + 理由 + 格式 + 例子」重写一遍Rewrite it with role + context + reason + format + example
用上面的模板补全那五样，尤其把你心里默认、却从没打出来的背景写出来。Fill the five slots from the template above — especially the background you assume but never type.
03
新旧各跑一遍，数追问次数Run old vs new, count the follow-ups
同一个任务，旧 prompt 和新 prompt 各发一次，记下各自要追加几句才拿到能用的结果。差额就是「说清」的价值。Send both on the same task and note how many follow-ups each needs before the result is usable. The gap is what 'saying it clearly' is worth.
把背景说出口，
它就不用猜.
Say the context out loud,
and it stops guessing.
Aklman Library
— 讨论Discussion
讨论Discussion.
评论区初始化中…Initializing comments…
01 / 01
没有匹配结果No matches.
换个关键词，或按 Esc 回到页面Try another keyword, or press Esc to return