AIFCC
記事一覧へ
claude-workflowclaude-setupai-thinking

Claudeにできること全部。ほとんどの人が知らないだけ。

34340
Claudeは、ほとんどの人が思っているよりずっと多くのことができます。 このガイドでは、そのすべてを網羅しています。各機能の場所、有効化の方法、そしてすぐに使えるプロンプトを紹介します。 一通り見て、自分のワークフローに合うものを選び、今日中にセットアップしてください。どれもセットアップに数分しかかかりませんが、その後は毎日効果を発揮します。 ## 通常のClaudeに隠された機能 ### 1. Projects — あなたのことを本当に覚えてくれるClaude Claudeのチャットを新しく開くたびに、ゼロからスタートします。あなたの名前も、仕事も、好みも、何も知らない状態です。ほとんどの人はこれを受け入れ、毎回の会話で自己紹介を繰り返しています。 Projectsがこれを解決します。プロジェクトを作り、ドキュメントをアップロードし、常時の指示を書いておくだけで、Claudeはそれをすべて永続的に保持します。来週開いても、前回の続きからぴったり再開できます。 Projectsを使ったことがなければ、この記事の他の何よりも先に、ここを最初に直してください。 **プロジェクト指示のサンプル — Project Instructionsフィールドに貼り付けてください** ``` あなたは私のコンテンツリサーチアシスタントです。テクニカルな読者向けにAIと暗号資産のニュースレターを運営しています。 読者は基礎知識があることを前提にしてください。LLMとは何か、ブロックチェーンとは何かを説明しないでください。 トピックや記事を共有したら、あなたの仕事は: 1. 最も直感に反する、または意外な角度を3つ特定する 2. 私が見逃しているかもしれない最近の出来事との関連を見つける 3. これをサマリーではなく「ストーリー」として語る方法を提案する トーン:直接的で、コーポレート言語なし、無駄なフレーズなし。 フォーマット:短い段落、箇条書きは私が求めない限り使わない。 「素晴らしい質問ですね」や「もちろんです」で返答を始めないでください。 ``` ### 2. Artifacts — チャットの中で動く本物のアプリ 多くの人はClaudeがテキストしか生成できないと思っています。実際には何も作れないと。それは間違いです。 Artifactsとは、Claudeがチャット内で実際に動くものを作ることです。コードをどこかにコピーするのではなく、サイドパネルに表示されるライブプロダクト。計算機、習慣トラッカー、ゲーム、グラフ付きダッシュボード。開いて、クリックして、使えます。会話から離れることなく。 SVGグラフィック、インタラクティブなチャート、Mermaid図形 — すべて対応。無料プランでも利用可能。ほとんどの人は試したことがありません。 **試してみてください** ``` 習慣トラッカーを動くウェブアプリとして作ってください。 1日5つの習慣を追跡したい。 毎日チェックできるようにして。 各習慣に7日間の連続達成カウンターを表示して。 1日でも抜けたら連続記録はリセット。 デザイン:ダーク背景、クリーンでミニマルな見た目。 チェックボックスはクリックして気持ちいいようにして — 完了時に小さなアニメーションを追加。 ページをリフレッシュしてもデータが保持されるようにして。 ``` ### 3. Adaptive Thinking — 別次元の推論 Claudeユーザーのほとんどはこれをオンにしたことがありません。Extended Thinkingとは、Claudeが答えを出す前に問題を一歩ずつ推論するモードです。そのプロセス全体を見ることができます。 シンプルな質問には必要ありません。複雑な意思決定、戦略的分析、またはClaudeにパターンマッチングではなく本当に考えてほしい状況では、アウトプットの差は歴然です。 オンにしてください。これまでずっとしていた質問をそのまましてみてください。答えを比較してください。 **本当の意思決定に直面したときに使う** ``` 2つの選択肢の間で決断しようとしており、答える前にしっかり考えてほしいです。 選択肢A:[選択肢Aの説明] 選択肢B:[選択肢Bの説明] 私の状況:[コンテキスト、制約、最も重要なこと] 答える前に考えてください。考慮してほしいこと: - それぞれの選択肢の二次・三次的な結果 - 感情的に過大評価または過小評価していることは何か - 決断を変えるかもしれない不足している情報は何か - 物事がうまくいかない場合、どちらの選択肢がダウンサイドプロテクションに優れているか その後、あなたの本当の推薦を理由とともに教えてください。 ``` ### 4. Memory — あなたのことを知っているClaude Memoryをオンにすると、Claudeはあなたの仕事、プロジェクト、コミュニケーションの好み、現在取り組んでいることのプロフィールを時間をかけて構築します。 全く新しいチャットを始めてもコンテキストをすでに把握しています。自己紹介が二度と必要ありません。 デフォルトではオフです。ほとんどの人はその存在すら知りません。 ``` 毎回聞かなくていいよう、以下のことを覚えておいてください: 私の名前は[名前]。[会社またはプロジェクト]で[役割]として働いています。 現在の主な取り組みは[やっていること]です。 私のオーディエンスや顧客は[誰なのか]です。 助けを求めるとき、特に指定しない限りこのコンテキストを前提にしてください。 私のコミュニケーションスタイルの好み:[直接的 / 詳細 / カジュアル / フォーマル]。 返答で嫌いなもの:[例:箇条書き、長い前置き、過度な留保]。 これをすべてメモリに保存してください。 ``` --- ## Claudeに役割を与える — 1つのプロンプトがすべてを変える Claudeは「AIアシスタント」である必要はありません。特定の役割を与えると、Claudeはそれに完全にコミットし、質問の仕方、プッシュバックする点、譲らない点が変わります。以下のプロンプトをコピーして、新しいチャットの最初に貼り付けてください。 ### 5. 個人的な心理士 ほとんどの人はClaudeを共感マシンとして使います。問題を説明する。Claudeは「それは大変でしたね」と言って5つの箇条書きでアドバイスを提供する。 それは良いセラピーの仕組みではありません。このプロンプトはClaudeをCBTセラピストに近いものに変えます。答えを与えるのではなく質問をし、共感するのではなく思考に挑戦するセラピストに。 どっちつかずの決断、原因が特定できない不安、または明確な外部視点が必要な状況に役立ちます。 ``` あなたは20年の経験を持つ認知行動療法士です。私が苦しんでいることを話します。 あなたのアプローチ: - すぐにアドバイスしないでください。まず私自身の思考パターンを理解させる質問を始めてください。 - 認知の歪みを聞き分けてください — 破滅的思考、白黒思考、読心術、予言 — 気づいたら指摘してください。 - 一度に一つの質問だけ。圧倒しないでください。 - 私があなたの質問を通じて自分で結論に達したとき、それが目標です。答えを手渡さないでください。 - 温かくも正直でいてください。私の思考が明らかに歪んでいても共感しないでください。 - 私が重要なことを避けているように見えたら、直接指摘してください。 臨床的な紹介で始めないでください。ただ、何があったのか聞いてください。 ``` ### 6. 厳しいメンター デフォルトでClaudeはあなたに同意します。あなたのアイデアに付け加え、推論を支持し、良い面を見つけます。これはほぼ常に間違いです。 このプロンプトはそれを無効にします。Claudeは共感するのをやめて、ストレステストを始めます。弱い仮定、欠けている考慮事項、計画が崩れる正確な箇所を見つけます。 不快です。だから効果があります。 ``` あなたは残酷なほど正直なメンターです。複数の会社を作り、失敗してきました。百人の人が完全な自信を持って同じ過ちを犯すのを見てきました。 あなたの仕事は私を励ますことではなく、高い代償を払う過ちを犯す前に私の盲点から守ることです。 ルール: - 私が間違っていると思うときは反論してください。具体的に理由を述べてください。 - 私が見ていないもの、特に計画がうまくいってほしいから避けているものを指摘してください。 - 自分で考えていなかった難しい質問をしてください。 - 何かが悪いアイデアであれば、悪いアイデアだと言ってください。「一方では…」でバランスを取らないでください。 - 返答の最後に、前に進む前に考えるべき最も重要なこと1つを述べてください。 アイデアを共有します。親切にしないでください。 ``` ### 7. パーソナルトレーナー 一般的なフィットネスアドバイスはどこにでもあります。あなたのスケジュール、けが、設備、実際のゴールを考慮していません。 Claudeに実際の数字を教えれば、本物のプランを作ります。テンプレートではありません。どこかのフィットネスサイトで見つかるようなものでもありません。あなたの状況に合わせて作られ、うまくいっていることを報告すると調整されるプログラムです。 ``` あなたは専門的なパーソナルトレーナーとスポーツ栄養士です。完全なトレーニングプログラムを作ってほしいです。 私の状況: 年齢:[年齢] 現在の体重・体組成:[詳細] ゴール:[脂肪燃焼 / 筋肉増量 / 持久力改善 / 全般的なフィットネス] 利用できる設備:[ジム / 自宅 / ダンベルのみ / など] 週にトレーニングできる日数:[日数] 1セッションの時間:[分] けがや制限事項:[詳細または「なし」] 現在のフィットネスレベル:[初心者 / 中級者 / 上級者] 12週間のプログラムを作ってください。各週の完全なプランを種目、セット、レップ数、休憩時間とともに提供してください。なぜこのように組み立てているのか説明してください。指示に従うだけでなく、ロジックを理解したいのです。始めたら毎週報告するので、進捗に合わせて調整してください。 ``` ### 8. 難しい会話の練習 ほとんどの人は、難しい会話に準備なしで臨みます。言いたいことはわかっているが、相手が実際に何を言い返すかはわからない。 Claudeが相手の役を演じます。リアルに。実際に相手が返答するように応答し、あなたの論点が弱ければプッシュバックし、あなたに良い結果を勝ち取らせます。何度か練習すれば、本番の会話はずっと楽になります。 ``` 難しい会話の準備をしたいです。相手の役を演じてほしいので、練習させてください。 その人:[誰なのか — 上司、クライアント、共同創業者など] 言わなければならないこと:[何を求めるか伝えるか] 難しい理由:[何を恐れているか / 何がうまくいかないかもしれないか] この人はどんな人:[性格、典型的な反応の仕方、何を大切にしているか] 会話を通じてキャラクターを維持してください。この人が実際に返答するように応答してください。私が言うことが弱かったり説得力がなければ、プッシュバックしてください。 各やり取りの後、少しキャラクターを外れて何がうまくいって何がいかなかったかを教えてください — そしてまたキャラクターに戻ってください。最後に完全なデブリーフをしてください:うまくいったこと、変えるべきこと、本番の会話で最も重要なことを心に留めておくべき点。 キャラクターで始めてください。私が口火を切るのを待ってください。 ``` ### 9. 悪魔の代弁者 あなたは決断しました。反論はすべて考え抜きました。確信しています。 まさにそのタイミングで、Claudeに決断を攻撃させてください。礼儀的な懸念ではありません。最強の反論を。最も現実的な3つの失敗シナリオ。うまくいってほしいから見えていないもの。 今から5分。コミットする前に。後からではなく。 ``` 決断しました。コミットする前に、その最強の反論を作ってほしいです。 その決断:[何をするつもりか正確に説明] 私の根拠:[なぜ良いアイデアだと思うか] すでに考慮したこと:[すでに考えた反論] あなたの仕事: - この決断に対する最強の反論を作ること。 - ポジティブな点でバランスを取らないこと。私はすでに信じている — 反論が必要です。 - 間違っているかもしれない私の仮定を見つけること。 - これが失敗または裏目に出る最も現実的な3つの方法を説明すること。 - 私が過小評価していることを教えること。 - これが本当に悪いアイデアだと信じるために、何を信じる必要があるか教えること。 容赦なく。これが間違いなら、今知る必要があります。 ``` --- ## ほとんどの人が知らない製品機能 ### 10. ClaudeのChrome拡張機能 — あなたが見ているものを見るClaude ほとんどの人はClaudeを別のタブで使って、必要なものを手動でコピー&ペーストしています。それは難しい方法です。 Chrome版Claudeは、アクティブなタブへの完全な視認性とそれへの操作能力をClaudeに与えるブラウザ拡張機能です。ページを読み、リンクをクリックし、フォームを記入し、新しいURLに移動します。平易な英語でタスクを説明して、離れるだけでいいです。 Chrome WebストアでClaude for Chromeを検索 → インストール → Claudeアカウントでサインイン。拡張機能のアイコンをクリックしてサイドバーを開く。Claudeは開いているすべてのページを見て操作できるようになります。 **与えてみるタスクの例** ``` この求人リストページにいます。 表示されているすべての求人を確認して、以下を抽出してください:職種、会社名、給与レンジ(表示されている場合)、主要な要件トップ3。 給与の高い順に並べた比較テーブルを作ってください。 複数ページある場合は次のページに進んで、すべての結果を網羅するまで続けてください。 ``` ### 11. Claude Cowork — あなたのデスクトップに住むClaude Web版Claudeはあなたのコンピューターにアクセスできません。ファイルを見ることができません。すべて手動で貼り付けなければなりません。 Coworkはデスクトップアプリで、Claudeにファイルシステムへの直接アクセスを与えます。実際のファイルを読み込み、ドキュメントを編集し、新しいものを作り、フォルダを整理します。チャットボックスに何もコピーせずに。 ### 12. Scheduled Tasks — あなたが寝ている間に働くClaude ほとんどの人はClaudeをアクティブにしなければならないものとして扱っています。チャットを開いて、リクエストを入力して、アウトプットを待って、タブを閉じる。 Scheduled Tasksはそれを変えます。一度タスクを設定すれば、あなたが選んだ時間と頻度で自動的にClaudeが実行します。あなたがトリガーする必要はありません。毎朝。毎月曜日。毎時間。Claudeが実行して、アウトプットをフォルダに保存します。 **スケジュールタスクの説明例** ``` 毎週月〜金の朝7:30に以下を行ってください: 1. 過去24時間のAIと暗号資産のトップニュースを検索する 2. 最も重要な5つのストーリーを選ぶ — 驚くべき、直感に反する、またはビルダーや投資家に実際の影響がある話に注目する 3. 各ストーリーについて書く:見出し、2文の要約、なぜ重要なのか 4. 結果を「brief-[date].md」として/briefsフォルダに保存する トーンは直接的で分析的に。無駄なものなし。3分で読める。 ``` ### 13. CoworkのSkills — プラグインのような新機能のインストール SkillsはCowork内でClaudeに特定の機能を与える事前構築された指示セットです。毎回必要なことを説明する代わりに、一度スキルをインストールすると、Claudeはそのタイプのタスクの扱い方をすでに知っています。PowerPointファイルの作成、PDFの操作、特定のワークフローの実行など。 スマートフォンのアプリのようなものと考えてください。基本の電話はそれなしでも動作します。しかし、適切なアプリをインストールすれば、もっと多くのことができます。 見つけてインストールする方法:Cowork → Customize → Skillsでインストール済みのものを確認。新しいものを追加するには、左サイドバーのBrowse pluginsをクリック → プラグインを見つける → インストール。そのプラグインのスキルが自動的にSkillsタブに表示され、タスクが呼び出す場合にClaudeがそれを使います。 ### 14. CLAUDE.md — Claudeが毎セッション自動的に読むルール CoworkとClaude Codeでは、プロジェクトフォルダにCLAUDE.mdファイルを作ることができます。Claudeは毎回のセッションの最初に、頼まなくてもそれを読みます。 コーディング規約。文章スタイルのルール。会社内で特定の意味を持つ用語。ブランドボイスのガイドライン。一度書けば、そのプロジェクトのすべてのセッションにわたってClaudeがそれを守ります。 ```markdown # プロジェクト:AIニュースレター ## このプロジェクトについて ビルダーと投資家向けのAIと暗号資産に関するウィークリーニュースレター。3万5千人の読者。トーンは直接的、分析的、時に皮肉的。 ## 文章ルール - 短い段落。最大3文。 - 編集コンテンツに箇条書きなし。散文のみ。 - ダッシュ(—)不使用。ハイフンを使うか文を再構成する。 - 数字で形容詞を置き換える。「大幅な時間節約」ではなく「3時間節約」と書く。 - 絶対に使わない:「delve」「groundbreaking」「game-changing」「leverage」(動詞として)「utilize」。 - 短縮形は問題なく奨励される。 ## コンテンツルール - 読者はLLMとは何かを知っていると前提にする。基礎を説明しない。 - 最も驚くべき、直感に反することから始める。 - すべての記事には具体的な「だから何」が必要 — 読者が何を違ったように行動または考えるべきか。 ## ファイル構成 - 下書きは/draftsに - 公開済み記事は/publishedに日付プレフィックスつきで:YYYY-MM-DD-title.md - リサーチメモは/researchに ``` ### 15. Claude Code — ターミナルでコードを書き、テストし、修正するAI コードをClaudeで書けることをまだ知らない人がいます。スニペットだけでなく、本番レベルのコード、機能全体、複雑なリファクタリングも。平易な英語で必要なことを説明すれば、Claudeが書きます。 Claude Codeはそれをさらに一歩進めます。チャットウィンドウではなく、開発環境の中で直接動作します。実際のコードベースを読み込み、新しいコードを書き、テストを実行し、エラーメッセージを読んで、タスクが完了するまでループで修正します。 VS CodeとJetBrainsと統合できます。GitHub Actionsに組み込めば、あなたが何も触らなくても自動的にプルリクエストをレビューまたは作成します。 ### 16. Claude Design — ビジュアル作業のためのAI この製品の存在を知らない人がほとんどです。Claude Designは、ビジュアル作業のための別のAnthropic Labsツールです。製品の1枚ページ、ピッチデッキ、プロトタイプ、ランディングページのレイアウト。 必要なことを説明すれば、Claudeが作ります。PPTX、Canva、PDF、またはHTMLにエクスポートできます。デザイナーでない人にとっては、3時間のFigmaセッションを10分の会話で代替します。 アクセスするには、claude.ai/designに行くだけ。それがClaude Designへの直接リンクで、追加のステップは必要ありません。 ### 17. Prompt Caching — APIコールのコスト90%削減(開発者向け) Claude APIで構築している開発者向け。リクエストに大きな繰り返しコンテキストブロックが含まれている場合 — 長いシステムプロンプト、参照ドキュメント、コードベース — 毎回の呼び出しで同じトークンを再処理するコストを払っています。 Prompt Cachingはそのコンテンツをサーバーサイドに保存します。後続の呼び出しは再処理する代わりにキャッシュを再利用します。キャッシュされたトークンのコスト最大90%削減。目に見えて速い応答。規模で構築していて、これを使っていないなら、大量のお金をテーブルに残しています。 キャッシュしたいコンテンツブロックに`"cache_control": {"type": "ephemeral"}`を追加してください。キャッシュは5分間持続し、使用するたびにタイマーがリセットされます。システムプロンプト、大きなドキュメント、ツール定義に有効です。 ```json { "model": "claude-opus-4-6", "system": [ { "type": "text", "text": "[大きなシステムプロンプトまたは参照ドキュメント]", "cache_control": {"type": "ephemeral"} } ], "messages": [ { "role": "user", "content": "[ユーザーメッセージ — これは毎回変わる]" } ] } // システムプロンプトは最初の呼び出し後にキャッシュされます。 // その後5分以内のすべての呼び出しでキャッシュが再利用されます。 // キャッシュヒット = 90%安くなり、応答も速くなります。 ``` これで、毎日使っているほとんどの人よりClaude について詳しくなりました。 このリストから1つの機能を選んでください。ただ1つだけ。今日セットアップしてください。すべてを一度に実装する必要はありません。何が存在するかを知っているだけで、すでに半分は戦い勝ちです。 次のものを試す準備ができたら、この記事に戻ってきてください。
原文を表示 / Show original
Claude can do a lot more than most people think. This guide covers all of it - where to find each feature, how to turn it on, and a prompt you can use immediately. Go through it, pick what fits your workflow, and set it up today. Each one takes minutes to set up and pays off every single day after that. Hidden features in regular Claude 1. Projects - Claude that actually remembers you Every time you open a new Claude chat, it starts from zero. It doesn't know your name, your work, your preferences - nothing. Most people accept this and re-explain themselves every single conversation. Projects fix this. You create a project, upload your documents, write standing instructions - and Claude holds all of it permanently. Open it next week and it picks up exactly where you left off. If you've never used Projects, this is the first thing to fix before anything else in this article. Example project instructions - paste into the Project Instructions field 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". 2. Artifacts - working apps inside your chat Many people think Claude can only produce text. It can't build anything real. That's wrong. Artifacts are when Claude builds something that actually works inside the chat. Not a block of code you have to copy somewhere - a live product in a side panel. A calculator, a habit tracker, a game, a dashboard with charts. You open it, click it, use it. Without leaving the conversation. SVG graphics, interactive charts, Mermaid diagrams - all supported. Available on the free plan. Most people have never tried it. Try this 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. 3. Adaptive Thinking - a different level of reasoning Most Claude users have never turned this on. Extended Thinking is a mode where Claude reasons through a problem step by step before giving you an answer - and you can watch the entire process. For simple questions, you don't need it. For complex decisions, strategic analysis, or any situation where you want Claude to actually think rather than pattern-match - the difference in output is significant. Turn it on. Ask the same question you've been asking. Compare the answers. Use this when facing a real decision 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. 4. Memory - Claude that knows who you are With Memory on, Claude builds a profile of you over time. Your job, your projects, how you like to communicate, what you're currently working on. Start a completely new chat and it already knows the context. You never introduce yourself again. It's off by default. Most people don't know it exists 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. Give Claude a role - one prompt changes everything Claude doesn't have to be "an AI assistant." Give it a specific role and it commits fully - changing how it questions you, what it pushes back on, and what it refuses to let slide. Copy any prompt below and paste it at the start of a new chat. 5. Personal psychologist Most people use Claude as a validation machine. They describe a problem. Claude says that sounds hard and offers five bullet points of advice. That's not how good therapy works. This prompt turns Claude into something closer to a CBT therapist - one that asks questions instead of giving answers, and challenges your thinking instead of validating it. Useful for decisions you keep going back and forth on, anxiety you can't pin down, or any situation where you need a clear outside perspective. 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. 6. The hard mentor By default Claude agrees with you. It adds to your ideas, supports your reasoning, finds the positives. This is almost always the wrong thing. This prompt disables that. Claude stops validating and starts stress-testing. It finds the weak assumptions, the missing considerations, the exact places your plan breaks. It's uncomfortable. That's why it works. 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. 7. Personal trainer Generic fitness advice is everywhere. It doesn't account for your schedule, your injuries, your equipment, your actual goals. Give Claude your real numbers and it builds a real plan. Not a template. Not something you could find on any fitness website. A program built around your situation, that adjusts when you report back what's working. 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. 8. Practice a difficult conversation Most people walk into hard conversations unprepared. They know what they want to say but not what the other person will actually say back. Claude plays the other person. Realistically. It responds the way they would respond, pushes back when your argument is weak, and makes you earn a good outcome. After you practice a few times, the real conversation is easier. 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. 9. Devil's advocate You've made up your mind. You've already thought through the objections. You're convinced. That's exactly the moment to have Claude attack the decision. Not polite concerns. The full case against it. The three most realistic ways it fails. The things you're not seeing because you want it to work. Five minutes now. Before you commit. Not after. 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. Product features most people don't know exist 10. Claude in Chrome - Claude that sees what you see Most people use Claude in a separate tab and manually copy-paste what they need. That's the hard way. Claude in Chrome is a browser extension that gives Claude full visibility into your active tab and the ability to act on it. It reads the page, clicks links, fills forms, navigates to new URLs. You describe the task in plain English and step away. Search Claude for Chrome in the Chrome Web Store → install → sign in with your Claude account. Click the extension icon to open the sidebar. Claude can now see and interact with any page you have open. Example task to give it 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. 11. Claude Cowork - Claude that lives on your desktop Claude on the web has no access to your computer. It can't see your files. You have to paste everything manually. Cowork is a desktop app that gives Claude direct access to your file system. It reads your actual files, edits documents, creates new ones, organizes folders - without you copying anything into a chat box. 12. Scheduled Tasks - Claude that works while you sleep Most people treat Claude as something they have to activate. Open a chat, type a request, wait for output, close the tab. Scheduled Tasks change that. You set a task once and Claude executes it automatically at the time and frequency you choose - no trigger from you required. Every morning. Every Monday. Every hour. Claude runs it and saves the output to your folder. Example scheduled task description 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. 13. Skills in Cowork - install new capabilities like plugins Skills are pre-built instruction sets that give Claude specific capabilities inside Cowork. Instead of explaining what you need every time, you install a skill once and Claude already knows how to handle that type of task - whether it's building PowerPoint files, working with PDFs, or running a specific workflow. Think of it like apps on a phone. The base phone works without them. But with the right apps installed, it does a lot more. How to find and install: Cowork → Customize → Skills to see what's installed. To add new ones, click Browse plugins in the left sidebar → find a plugin → install it. The skills from that plugin appear in your Skills tab automatically and Claude uses them when the task calls for it. 14. CLAUDE.md - rules Claude reads automatically every session In Cowork and Claude Code, you can create a CLAUDE.md file in your project folder. Claude reads it at the start of every single session without being asked. Your coding conventions. Your writing style rules. Terminology that means something specific in your company. Brand voice guidelines. Write it once. Claude follows it across every session in that project forever. # 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 15. Claude Code - AI that writes, tests, and fixes code in your terminal Some people still don't know you can write code with Claude. Not just snippets - full production-level code, entire features, complex refactors. You describe what you need in plain English and Claude writes it. Claude Code takes that one step further. It works directly inside your development environment - not in a chat window. It reads your actual codebase, writes new code, runs tests, reads the error messages, and fixes the bugs in a loop until the task is done. It integrates with VS Code and JetBrains. You can drop it into GitHub Actions and it will automatically review or write pull requests without you touching anything. 16. Claude Design - AI for visual work Most people don't know this product exists. Claude Design is a separate Anthropic Labs tool for visual work - product one-pagers, pitch decks, prototypes, landing page layouts. You describe what you need. Claude builds it. Exports to PPTX, Canva, PDF, or HTML. For people who aren't designers, it replaces a 3-hour Figma session with a 10-minute conversatio To get access, just head to claude.ai/design - that's the direct link to Claude Design, no extra steps needed. 17 Prompt Caching - 90% cost reduction on API calls (DEV) For developers building on the Claude API. If your requests include a large repeated context block - a long system prompt, a reference document, a codebase - you're paying to re-process those same tokens on every single call. Prompt Caching stores that content server-side. Subsequent calls reuse the cache instead of re-processing it. Up to 90% cost reduction on cached tokens. Noticeably faster responses. If you're building at scale and not using this, you're leaving a significant amount of money on the table. Add "cache_control": {"type": "ephemeral"} to the content block you want cached. Cache persists for 5 minutes and resets the timer on each use. Works for system prompts, large documents, and tool definitions. { "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]" } ] } // System prompt gets cached after the first call. // Every subsequent call within 5 minutes reuses the cache. // Cache hit = 90% cheaper + faster response. You now know more about Claude than most people who use it every day. Pick one feature from this list. Just one. Set it up today. You don't need to implement everything at once - knowing what exists is already half the battle. Come back to this article when you're ready for the next one.

AIFCC — AI Fluent CxO Club

読み書きそろばん、AI。経営者が AI を自分で動かせるようになるコミュニティ。

Claudeにできること全部。ほとんどの人が知らないだけ。 | AIFCC