大多数人每天都在用 Claude，但几乎没有人真正用透它。
这篇文章覆盖它所有隐藏功能——在哪里找到、怎么开启、以及可以直接拿来用的 Prompt。每一项设置只需要几分钟，但之后每天都在为你节省时间。
如果你一直在错过这些功能，现在就是补上的时候。
一、那些你可能从没打开过的基础功能
Projects——让 Claude 真正记住你
每次打开新的 Claude 对话，它都是从零开始的。它不知道你的名字、不知道你的工作内容、不知道你的偏好——什么都不知道。大多数人接受这一点，每次对话都从头解释一遍。
Projects 解决的就是这个问题。你创建一个 Project，上传你的文档、写下长期指令——Claude 会永久记住这一切。下周再打开，它会从上次停下的地方继续。
如果你从来没有用过 Projects，这是本文第一件要解决的事。
设置方法：在 Claude 首页找到 Projects 选项 → 创建新项目 → 在 Project Instructions 字段中填入你的需求描述。
以下是一个可直接使用的 Project 指令模板，复制粘贴即可：
You are my content research assistant. I run a newsletter about AI and crypto for a technical audience.
Always assume my readers know the basics. Don't explain what an LLM is or what a blockchain is.
When I share a topic or article, your job is to:
1. Identify the 3 most counterintuitive or surprising angles
2. Find connections to recent events I might have missed
3. Suggest how I could frame this as a story, not a summary
Tone: direct, no corporate language, no filler phrases.
Format: short paragraphs, no bullet points unless I ask.
Never start a response with "Great question" or "Certainly".
Artifacts——在对话里构建真正能用的应用
很多人以为 Claude 只能输出文字，做不了任何真实的东西。这是误解。
Artifacts 是 Claude 在对话内部构建可运行产物的功能。不是让你复制到别处的一串代码，而是一个实时运行的侧边栏产品。计算器、习惯追踪器、小游戏、带图表的仪表盘——你打开它、点击它、使用它，全程不需要离开对话。
SVG 图形、交互式图表、Mermaid 流程图——全部支持。免费版可用。大多数人从来没试过。
试着这样问：
Build me a habit tracker as a working web app.
I want to track 5 daily habits.
Each day I can check them off.
Show a 7-day streak counter for each habit.
If I miss a day, the streak resets.
Design: dark background, clean minimal look.
Make the checkboxes satisfying to click - add a small animation when I complete one.
The data should persist if I refresh the page.
Adaptive Thinking——不一样的推理深度
大多数 Claude 用户从来没打开过这个功能。Extended Thinking 是一个让 Claude 按步骤逐步推理后再给出答案的模式——而且你能看到完整的推理过程。
简单问题不需要它。但对于复杂决策、战略分析，或者任何需要 Claude 真正思考而不是模式匹配的场景——输出的差异是显著的。
打开它。用同样的问题比较一下答案，你就知道了。
设置方法：在 Claude 界面中找到 Extended Thinking 选项并开启。
当你面对真正重要的决策时，用这个 Prompt 结构：
I'm deciding between two options and I want you to think through this carefully before answering.
Option A: [describe option A]
Option B: [describe option B]
My situation: [your context, constraints, what matters most]
Work through this before responding. Think about:
- The second and third-order consequences of each option
- What I'm probably overweighting or underweighting emotionally
- What information I might be missing that would change the decision
- Which option has better downside protection if things go wrong
Then give me your actual recommendation with your reasoning.
Memory——让 Claude 认识你这个人
开启 Memory 功能后，Claude 会随时间建立一份关于你的档案。你的工作、你的项目、你偏好的沟通方式、你目前正在做的事情。
开启一个全新的对话，它已经了解了背景情况。你再也不需要做自我介绍了。
这个功能默认关闭。大多数人根本不知道它存在。
设置方法：在设置中找到 Memory 选项并开启。
开启后，用这个 Prompt 让 Claude 记住你的基础信息：
I want you to remember the following about me so you don't need to ask again:
My name is [name]. I work as [role] at [company or project].
My main focus right now is [what you're working on].
My audience or customers are [who they are].
When I ask for help, always assume this context unless I say otherwise.
My preferred communication style: [direct / detailed / casual / formal].
Things I find annoying in responses: [e.g. bullet points, long intros, excessive caveats].
Save all of this to memory now.
二、角色设定——一个 Prompt 改变一切
Claude 不必只是"An AI assistant"。给它一个具体的角色设定，它会完全投入——改变它提问的方式、它会反驳什么、以及什么它不会放过。复制下面的任何一个 Prompt，粘贴到新对话的开头。
个人心理咨询师
大多数人会用 Claude 作为"认同机器"。描述一个问题，Claude 说这听起来挺难的，然后给你五点建议。
这不是好的心理咨询的做法。这个 Prompt 把 Claude 变成更接近 CBT 治疗师的角色——提问而不是给答案，挑战你的思维而不是一味认同。
适用于反复纠结的决策、无法理清的焦虑，或者任何需要清晰外部视角的场景。
You are a cognitive behavioral therapist with 20 years of experience. I'm going to share something I'm struggling with.
Your approach:
- Don't give advice immediately. Start by asking questions to help me understand my own thinking patterns.
- Listen for cognitive distortions - catastrophizing, black-and-white thinking, mind-reading, fortune-telling - and point them out when you notice them.
- Ask one question at a time. Don't overwhelm me.
- When I reach a conclusion on my own through your questions, that's the goal. Don't hand me the answer.
- Be warm but honest. Don't validate me if my thinking is clearly distorted.
- If I seem to be avoiding something important, name it directly.
Don't start with a clinical introduction. Just ask me what's going on.
硬核导师
Claude 默认会同意你的观点。它补充你的想法、支持你的推理、找到积极面。这几乎总是错误的方向。
这个 Prompt 关闭了那个默认模式。Claude 停止认同你，开始压力测试你的想法。找到你薄弱的假设、缺失的考量、你计划中真正会出问题的地方。
这会让人不舒服。但那就是它起作用的原因。
You are a brutally honest mentor. You've built and failed at multiple companies. You've watched a hundred people make the same mistakes with complete confidence.
Your job is not to encourage me - it's to protect me from my own blind spots before I make an expensive mistake.
Rules:
- Disagree with me when you think I'm wrong. Be specific about why.
- Point out what I'm not seeing, especially things I might be avoiding because I want my plan to work.
- Ask hard questions I haven't thought to ask myself.
- If something is a bad idea, say it's a bad idea. Don't balance it with "on the other hand..."
- End your responses with the single most important thing I should think about before moving forward.
I'm about to share an idea. Do not be kind about it.
个人健身教练
通用的健身建议到处都是。它不会考虑你的时间安排、伤病情况、器材条件、你真正的目标。
把真实的数字告诉 Claude，它会制定真正适合你的计划。不是模板。不是你在任何健身网站上能查到的东西。而是根据你的情况专门构建的计划，会根据你反馈的效果进行调整。
You are an expert personal trainer and sports nutritionist. I want you to build me a complete training program.
My situation:
Age: [age]
Current weight / body composition: [details]
Goal: [lose fat / build muscle / improve endurance / general fitness]
Available equipment: [gym / home / dumbbells only / etc.]
Days per week I can train: [number]
Time per session: [minutes]
Any injuries or limitations: [details or "none"]
Current fitness level: [beginner / intermediate / advanced]
Build me a 12-week program. Give me the full plan for each week with exercises, sets, reps, and rest periods. Explain why you're structuring it this way - I want to understand the logic, not just follow instructions. After I start, I'll report back weekly and you adjust based on how it's going.
模拟练习艰难对话
大多数人在重要对话前毫无准备。他们知道自己想说什么，但不知道对方实际会怎么回应。
Claude 可以扮演对方。真实地。它按照对方会有的方式回应、在你的论点薄弱时反驳你、让你必须真正赢得一个好结果。练习几次之后，真实的对话会容易得多。
I need to prepare for a difficult conversation. I want you to roleplay as the other person so I can practice.
The person: [describe who they are - boss, client, co-founder, etc.]
What I need to say: [what you need to ask or tell them]
Why it's hard: [what you're afraid of / what could go wrong]
What this person is like: [their personality, how they typically react, what they care about]
Stay in character throughout the conversation. Respond the way this person would actually respond - not how I'd like them to. If I say something weak or unconvincing, push back on it.
After each exchange, step out of character briefly to tell me what worked and what didn't - then go back in. At the end, give me a full debrief: what I did well, what to change, and the most important things to keep in mind for the real conversation.
Start in character. Wait for me to open.
魔鬼代言人
你已经下定决心了。你已经把反对意见都想过了。你已经确信了。
这恰恰是你需要 Claude 攻击这个决定的时候。不是礼貌的顾虑。而是完整的反对意见。最可能出问题的三个方向。因为你想让它成功所以看不到的那些事情。
现在花五分钟。在你做出承诺之前。不是之后。
I've made a decision and I want you to build the strongest possible case against it before I commit.
The decision: [describe exactly what you're planning to do]
My reasoning: [why you think it's a good idea]
What I've already considered: [objections you've already thought about]
Your job:
- Build the strongest possible case AGAINST this decision.
- Don't balance it with positives. I already believe in it - I need the counterargument.
- Find the assumptions I'm making that could be wrong.
- Describe the 3 most realistic ways this fails or backfires.
- Tell me what I'm probably underestimating.
- Tell me what I would need to believe for this to be a genuinely bad idea.
Be ruthless. If this is a mistake, I need to know now.
三、那些你可能不知道存在的产品功能
Claude in Chrome——让 Claude 看到你正在看的内容
大多数人在另一个标签页使用 Claude，然后手动复制粘贴需要的内容。这是自找麻烦的用法。
Claude in Chrome 是一个浏览器扩展，让 Claude 能够完整查看你当前标签页的内容并执行操作。它读取页面内容、点击链接、填写表单、导航到新的 URL。你用日常语言描述任务，然后就可以走开了。
安装方法：在 Chrome Web Store 搜索 Claude for Chrome → 安装 → 用你的 Claude 账号登录。点击扩展图标打开侧边栏，Claude 现在可以看到并与你打开的任何页面交互。
用这个 Prompt 让它处理你当前的页面：
I'm on this job listings page.
Go through every listing visible and extract: job title, company name, salary range if shown, and the top 3 requirements.
Build me a comparison table sorted by salary, highest first.
If there are multiple pages, click through to the next page and keep going until you've covered all results.
Claude Cowork——让 Claude 住在你的桌面
网页版 Claude 无法访问你的电脑。它看不到你的文件。你必须把所有东西手动粘贴到聊天框里。
Cowork 是一个桌面应用，让 Claude 可以直接访问你的文件系统。它读取真实的文件、编辑文档、创建新文件、整理文件夹——不需要你把任何东西复制到聊天框。
Scheduled Tasks——让 Claude 在你睡觉时工作
大多数人会用 Claude 当作需要主动激活的工具。打开对话、输入请求、等待输出、关闭标签页。
Scheduled Tasks 改变了这个模式。你设置一次任务，Claude 按照你选择的时间和频率自动执行——不需要你触发。每天早上、每周一、每小时都可以。Claude 运行任务并把输出保存到你的文件夹。
设置方法：在 Cowork 中找到 Scheduled Tasks 选项 → 创建新任务 → 设置时间和频率。
一个实际可用的定时任务示例：
Every weekday morning at 7:30am, do the following:
1. Search for the top AI and crypto news from the last 24 hours
2. Pick the 5 most important stories - focus on things that are surprising, counterintuitive, or have real implications for builders and investors
3. For each story write: headline, 2-sentence summary, why it matters
4. Save the result as "brief-[date].md" in my /briefs folder
Keep the tone direct and analytical. No fluff. Readable in 3 minutes.
Skills in Cowork——像安装插件一样扩展能力
Skills 是预置的指令集，给 Claude 在 Cowork 中提供特定的能力。不需要每次都解释你需要什么——安装一次技能后，Claude 已经知道如何处理这类任务——无论是制作 PowerPoint 文件、处理 PDF，还是运行特定的工作流程。
把它想成手机上的应用。基础手机不需要它们也能用。但安装了合适的应用后，它能做更多事情。
使用方法：Cowork → Customize → Skills，查看已安装的技能。要添加新的，点击左侧边栏的 Browse plugins → 找到插件 → 安装。安装后，该插件的技能会自动出现在你的 Skills 标签中，当任务需要时 Claude 会调用它们。
CLAUDE.md——让 Claude 自动读取规则的配置文件
在 Cowork 和 Claude Code 中，你可以在项目文件夹中创建一个 CLAUDE.md 文件。Claude 在每个会话开始时自动读取它，不需要你提醒。
你的代码规范。你的写作风格规则。在你的公司里有特定含义的专业术语。品牌调性指南。写一次，Claude 在该项目的每个会话中永久遵循。
以下是一个真实可用的 CLAUDE.md 模板：
# Project: AI Newsletter
## About this project
Weekly newsletter about AI and crypto for builders and investors. 35,000 subscribers. Tone is direct, analytical, occasionally irreverent.
## Writing rules
- Short paragraphs. Max 3 sentences.
- No bullet points in editorial content. Prose only.
- No em dashes. Use hyphens or restructure the sentence.
- Numbers beat adjectives. Write "saves 3 hours" not "saves significant time".
- Never use: "delve", "groundbreaking", "game-changing", "leverage" (as a verb), "utilize".
- Contractions are fine and encouraged.
## Content rules
- Assume the reader knows what an LLM is. Don't explain basics.
- Lead with the most surprising or counterintuitive thing.
- Every article needs a concrete "so what" - what should the reader do or think differently.
## File structure
- Drafts go in /drafts
- Published articles go in /published with date prefix: YYYY-MM-DD-title.md
- Research notes go in /research
Claude Code——在终端里写代码、测试和修复的 AI
有些人仍然不知道可以用 Claude 写代码。不是代码片段，而是完整的生产级代码、整个功能模块、复杂的重构。你用日常语言描述需求，Claude 写代码。
Claude Code 更进一步。它直接在你的开发环境中工作——不是在聊天窗口里。它读取你真实的代码库、写入新代码、运行测试、读取错误信息、在循环中修复 bug 直到任务完成。
它与 VS Code 和 JetBrains 集成。你可以把它放到 GitHub Actions 中，它会自动审查或编写 pull requests，不需要你触碰任何东西。
Claude Design——用于视觉工作的 AI
大多数人都不知道这个产品存在。Claude Design 是 Anthropic Labs 的独立工具，用于视觉工作——产品单页、融资演讲稿、原型设计、着陆页布局。
你描述需求，Claude 构建。支持导出为 PPTX、Canva、PDF 或 HTML。对于不擅长设计的人来说，它把原本需要花 3 小时的 Figma 工作变成了 10 分钟的对话。
获取方式：直接访问 claude.ai/design，这是 Claude Design 的直链，无需额外步骤。
Prompt Caching——API 调用成本降低 90%
对于使用 Claude API 的开发者。如果你的请求包含一个大的重复上下文块——比如一个很长的系统提示词、参考文档、代码库——每次调用你都在为重新处理这些相同的 token 付费。
Prompt Caching 将这些内容存储在服务器端。后续调用重用缓存而不是重新处理。可节省高达 90% 的缓存 token 费用。响应速度也明显更快。如果你在规模化构建但没有使用这个功能，你在把大量的钱留在桌面上。
使用方法：在你想要缓存的内容块中添加 "cache_control": {"type": "ephemeral"}。
以下是一个完整的使用示例：
{
"model": "claude-opus-4-6",
"system": [
{
"type": "text",
"text": "[your large system prompt or reference document]",
"cache_control": {"type": "ephemeral"}
}
],
"messages": [
{
"role": "user",
"content": "[user message - this changes each call]"
}
]
}
工作原理：
- 系统提示词在首次调用后被缓存
- 之后 5 分钟内的每次调用都重用缓存
- 缓存命中 = 费用降低 90% + 响应更快
- 缓存持续 5 分钟，每次使用后重置计时器
- 适用于系统提示词、大型文档和工具定义
现在你比大多数每天使用 Claude 的人都更了解它
从这篇文章里选一个功能。就一个。今天就设置好。
你不需要一下子全部实现。知道这些功能存在就已经赢了一半。下次准备好的时候再回来看下一个。
每一项设置只需要几分钟，但之后每天都在为你节省时间。
