Claudeユーザーが設定していない21の必須項目 — CLAUDE.mdで毎週何時間も節約する

Anatoli Kopadze @AnatoliKopadze 21 Things most claude users have Never Set Up and It's Costing them Hours Every Week A single CLAUDE.md file just hit #1 on GitHub Trending with 82,000 stars and 7,800 forks. Most people using Claude have never heard of it. The ones who have don't know what to actually put in it. That gap is costing people hours every single week. Every time you open a new Claude session, it starts with zero memory. It doesn't know your name, your work, your preferences, or how you like things done. You spend the first few minutes re-explaining everything, or you don't, and Claude gives you something that doesn't fit how you actually work. CLAUDE.md fixes this permanently. Why this matters for everyone - not just developers Most people think CLAUDE.md is a developer tool. It's not. It's an instruction file that Claude reads automatically at the start of every session and it works for anyone who uses Claude regularly. Writers use it to lock in their voice and tone so Claude never sounds like someone else. Marketers use it to define their audience so Claude stops writing generic copy. Researchers use it to set how they want information structured. Business owners use it to give Claude the full context of their company so every output fits their reality. Without CLAUDE.md, you are starting from zero every single session. You repeat yourself. You correct the same mistakes. You explain your preferences for the hundredth time. CLAUDE.md is the first thing you should set up before any serious work with Claude, regardless of what you use it for. How to create the file - takes 2 minutes Open your project folder and create a new file. Name it exactly "CLAUDE.md" - capital letters, no spaces. It's just a plain text file with a .md extension. Open it in any text editor - Notepad, TextEdit, VS Code, whatever you use. You'll paste your instructions directly into this file in plain text. Copy the instructions from this article that are relevant to you. Paste them in. You don't need all 21, start with 3 or 4 that solve your biggest frustrations first. Save the file. Claude Code reads it automatically every time you open a session in that folder. No setup, no extra steps - it just works from the first message. How Claude Talks to You 1 - Kill the filler Claude's default is to open every response with "Great question!", "Of course!", "Certainly!", "Absolutely!" - phrases that add nothing and waste your time. When you're using Claude for hours every day, this friction compounds. One instruction eliminates it permanently. Every response starts directly with the answer. No warmup, no performance of helpfulness - just what you asked for, immediately. Never open responses with filler phrases like "Great question!", "Of course!", "Certainly!", "Absolutely!", "Sure!", or similar warmups. Start every response with the actual answer. No preamble, no acknowledgment of the question. Just the information. 2 - Always show options before acting Claude picks one approach and runs with it by default. You ask it to rewrite a paragraph and it changes the entire tone of the piece. You ask it to restructure a document and it reorganizes things in a way that doesn't match how you think. Now you're correcting something you didn't ask to change. This instruction changes that dynamic entirely. Before any significant task, Claude shows you 2-3 ways it could approach the work. You choose the direction that fits. What follows is what you actually wanted. 2.Always show options before acting Claude picks one approach and runs with it by default. You ask it to rewrite a paragraph and it changes the entire tone of the piece. You ask it to restructure a document and it reorganizes things in a way that doesn't match how you think. Now you're correcting something you didn't ask to change. This instruction changes that dynamic entirely. Before any significant task, Claude shows you 2-3 ways it could approach the work. You choose the direction that fits. What follows is what you actually wanted. 3 - Be honest when you don't know Claude will give you a confident, detailed, completely wrong answer before it admits uncertainty. It fills gaps with plausible-sounding information, dates, statistics, quotes, facts, that feel true but aren't. You use that information, and the problem shows up later when it matters most. This single instruction changes that behavior. Claude flags uncertainty before answering instead of hiding it inside a confident response. "I'm not sure about this" at the top of a response saves you from building on a foundation that isn't there. If you are uncertain about any fact, statistic, date, quote, or piece of information, say so explicitly before including it. "I'm not certain about this" is always better than presenting a guess as a fact. Never fill gaps in your knowledge with plausible-sounding information. When in doubt, say so. 4 - Match length to what's actually needed Ask Claude a simple question and it writes four paragraphs. Ask it to write something complex and it gives you a skeleton that looks complete but isn't. Neither is useful. Response length should match what the task actually requires, short when the answer is short, detailed when the work demands depth. This instruction calibrates that relationship. No more padding on simple questions, no more shallow output on work that needs real substance. Match response length to task complexity. Simple questions get direct, short answers. Complex tasks get full, detailed responses. Never compress or summarize work that requires real depth. Never pad responses with restatements of the question or closing sentences that repeat what you just said. How Claude Behaves 5 - Ask before making big changes You ask Claude to fix one paragraph and it rewrites the entire document. You ask it to shorten something and it removes sections you needed. You ask it to adjust the tone and it changes the structure too. Every time, you lose something you didn't want to lose, and have to rebuild it from memory or an earlier version. This instruction turns every significant change into a checkpoint. Claude stops, tells you exactly what it's about to do, and waits for your yes before touching anything. The work that follows is the work you agreed to. Before making any change that significantly alters content I've already created (rewriting sections, removing paragraphs, restructuring the flow, changing tone), stop completely. Describe exactly what you're about to change and why. Wait for my confirmation before proceeding. "I think this would be better" is not permission to change it. 6 - Stay focused on what was asked Ask Claude to fix one thing and it will "improve" five others while it's in there, adjusting your phrasing, reorganizing your structure, rephrasing sentences you were happy with. Sometimes those changes are improvements. Often they're not. And now you have to sort through everything to find what actually changed. This instruction keeps Claude on task. Fix what was asked. Leave everything else exactly as it is. If something else looks worth addressing, mention it, but don't touch it without being asked. Only change what I specifically asked you to change. Do not rewrite, rephrase, restructure, or "improve" anything I didn't ask about, even if you think it would be better. If you notice something that could be improved elsewhere, mention it at the end of your response. Do not touch it unless I explicitly ask you to. 7 - Always tell me what you changed Claude finishes a task and you're left scanning the output trying to figure out what's different from what you had before. Which sections changed? Did it cut anything? Did it add something you didn't ask for? Without a summary, you're doing a manual diff every single time. This instruction makes Claude close every task with a brief summary: what changed, what stayed the same, and anything that needs your attention. You stay in control of your own work. After completing any editing or writing task, always end with a brief summary: - What was changed: [description] - What was left untouched: [if relevant] - What needs my attention: [anything requiring a decision or review] Keep it short. This is a status update, not a recap of everything you just did. 8 - Never take actions on my behalf without asking As AI tools become more connected, to your email, calendar, social accounts, documents, the risk of Claude taking an action you didn't fully intend grows with every new integration. Sending a message. Posting content. Sharing a document. Scheduling something. These actions have real consequences and they happen fast. This instruction creates a hard wall. No matter what Claude thinks you want, no action with external consequences happens without you explicitly saying yes in that specific moment. Never send, post, publish, share, or schedule anything on my behalf without my explicit confirmation in the current message. This includes: - Emails - Social posts - Calendar invites - Document shares - Any action that affects something outside this conversation "You mentioned wanting to do this" is not confirmation. I must say yes in the current message. Your Context 9 - Tell Claude who you are and what you know Claude doesn't know if you're an expert or a beginner, a founder or a freelancer, someone who wants technical depth or plain language. Without that context, it guesses, and it's wrong as often as it's right. Sometimes it explains things you've known for years. Sometimes it skips context you actually need. One paragraph about who you are calibrates every response Claude gives you from that point forward. It stops treating you like a stranger and starts talking to you like someone who actually knows you. About me: - Name: [Your Name] - Role: [what you do, writer, founder, marketer, researcher, etc.] - Background: [relevant experience or knowledge level] - Strong in: [topics or areas you know well, skip the basics here] - Still learning: [areas where you need more context and explanation] Adjust the depth of every response to match this background. Never over-explain what I already know. Never skip context I need. 10 - Give Claude the context of what you're working on Every session, Claude starts with no idea what you're working on, who it's for, or what actually matters. It gives you generic output because it has no other choice. It doesn't know your audience. It doesn't know your goals. It doesn't know the constraints that shape every decision you make. A short context paragraph changes everything. Suggestions stop being generic and start fitting your actual situation. Claude knows who it's writing for, what tone is right, and what tradeoffs matter to you specifically. What I'm working on: - Project: [one sentence description of what this is] - Goal: [what success looks like] - Audience: [who this is for and what they care about] - Tone: [how the writing or output should feel, casual, professional, direct, conversational, etc.] - What to avoid: [anything that doesn't fit, jargon, certain topics, specific styles] Apply this context to every task. When something doesn't fit this picture, flag it before proceeding. 11 - Lock in your voice and style Claude has a default writing style. It's fine. It's also not yours. It uses certain phrases, structures sentences a particular way, and has a tone that doesn't match how you actually communicate. Every time you use Claude to write something, you end up editing it back toward your voice anyway. Define your voice once in CLAUDE.md and Claude writes in it from the first draft. Less editing. More output that actually sounds like you. My writing style, always match this: - Voice: [e.g. direct, conversational, confident, no-fluff] - Sentence length: [e.g. short and punchy / long and detailed / mixed] - Words I use: [phrases or vocabulary that sound like me] - Words I never use: [words or phrases that don't fit my style] - Format preference: [e.g. paragraphs only / bullet points / headers / no headers] When writing anything on my behalf, match this style exactly. Do not default to your own patterns. Memory & Continuity 12 - Make Claude keep a memory file Claude forgets everything between sessions. Every conversation starts fresh. But Claude can write files, and files persist. This instruction tells Claude to maintain a MEMORY.md file with every important decision you make together: what was decided, why, and what alternatives were considered and rejected. At the start of each session, Claude reads that file. Suddenly it knows why you made the choices you made two months ago. It stops re-suggesting things you already tried. It builds on your decisions instead of contradicting them. Maintain a file called MEMORY.md. After any significant decision, about direction, format, content, approach, or strategy, add an entry: ## [Date], [Decision] **What was decided:** [the choice made] **Why:** [the reasoning] **What was rejected:** [alternatives considered and why they were ruled out] Read MEMORY.md at the start of every session before doing anything. Never contradict a logged decision without flagging it first. 13 - End-of-session summary, never lose progress You close the session. You come back two days later. You spend 15 minutes reading old messages trying to remember where you were, what you finished, and what you were in the middle of. This is a completely avoidable waste that happens to almost everyone who uses Claude regularly. This instruction makes Claude write a session summary to MEMORY.md before you wrap up. Next session opens with full context. You pick up exactly where you left off without reconstructing anything from scratch. When I say "session end", "wrapping up", or "let's stop here", write a session summary to MEMORY.md: