jpskill.com
💼 ビジネス コミュニティ 🟡 少し慣れが必要 👤 経営者・事業責任者・マーケ

💼 Recursive Context Pruning Token Budgeting

recursive-context-pruning-token-budgeting

AIが不要な情報を削除し、トークン使用

⏱ 求人原稿の改善 半日 → 15分

📺 まず動画で見る(YouTube)

▶ 【自動化】AIガチ勢の最新活用術6選がこれ1本で丸分かり!【ClaudeCode・AIエージェント・AI経営・Skills・MCP】 ↗

※ jpskill.com 編集部が参考用に選んだ動画です。動画の内容と Skill の挙動は厳密には一致しないことがあります。

📜 元の英語説明(参考)

Optimizes AI agent performance by pruning redundant context, managing token usage, and enforcing ultra-concise, direct-to-value responses.

🇯🇵 日本人クリエイター向け解説

一言でいうと

AIが不要な情報を削除し、トークン使用

※ jpskill.com 編集部が日本のビジネス現場向けに補足した解説です。Skill本体の挙動とは独立した参考情報です。

⚡ おすすめ: コマンド1行でインストール(60秒)

下記のコマンドをコピーしてターミナル(Mac/Linux)または PowerShell(Windows)に貼り付けてください。 ダウンロード → 解凍 → 配置まで全自動。

🍎 Mac / 🐧 Linux
mkdir -p ~/.claude/skills && cd ~/.claude/skills && curl -L -o recursive-context-pruning-token-budgeting.zip https://jpskill.com/download/3372.zip && unzip -o recursive-context-pruning-token-budgeting.zip && rm recursive-context-pruning-token-budgeting.zip
🪟 Windows (PowerShell)
$d = "$env:USERPROFILE\.claude\skills"; ni -Force -ItemType Directory $d | Out-Null; iwr https://jpskill.com/download/3372.zip -OutFile "$d\recursive-context-pruning-token-budgeting.zip"; Expand-Archive "$d\recursive-context-pruning-token-budgeting.zip" -DestinationPath $d -Force; ri "$d\recursive-context-pruning-token-budgeting.zip"

完了後、Claude Code を再起動 → 普通に「動画プロンプト作って」のように話しかけるだけで自動発動します。

💾 手動でダウンロードしたい(コマンドが難しい人向け)
  1. 1. 下の青いボタンを押して recursive-context-pruning-token-budgeting.zip をダウンロード
  2. 2. ZIPファイルをダブルクリックで解凍 → recursive-context-pruning-token-budgeting フォルダができる
  3. 3. そのフォルダを C:\Users\あなたの名前\.claude\skills\(Win)または ~/.claude/skills/(Mac)へ移動
  4. 4. Claude Code を再起動

⚠️ ダウンロード・利用は自己責任でお願いします。当サイトは内容・動作・安全性について責任を負いません。

🎯 このSkillでできること

下記の説明文を読むと、このSkillがあなたに何をしてくれるかが分かります。Claudeにこの分野の依頼をすると、自動で発動します。

📦 インストール方法 (3ステップ)

  1. 1. 上の「ダウンロード」ボタンを押して .skill ファイルを取得
  2. 2. ファイル名の拡張子を .skill から .zip に変えて展開(macは自動展開可)
  3. 3. 展開してできたフォルダを、ホームフォルダの .claude/skills/ に置く
    • · macOS / Linux: ~/.claude/skills/
    • · Windows: %USERPROFILE%\.claude\skills\

Claude Code を再起動すれば完了。「このSkillを使って…」と話しかけなくても、関連する依頼で自動的に呼び出されます。

詳しい使い方ガイドを見る →
最終更新
2026-05-17
取得日時
2026-05-17
同梱ファイル
1

💬 こう話しかけるだけ — サンプルプロンプト

  • Recursive Context Pruning Toke で、私のビジネスを分析して改善案を3つ提案して
  • Recursive Context Pruning Toke を使って、来週の会議用の資料を作って
  • Recursive Context Pruning Toke で、現状の課題を整理してアクションプランに落として

これをClaude Code に貼るだけで、このSkillが自動発動します。

📖 Claude が読む原文 SKILL.md(中身を展開)

この本文は AI(Claude)が読むための原文(英語または中国語)です。日本語訳は順次追加中。

Recursive Context Pruning & Token Budgeting

Overview

This skill implements a "Gatekeeper" logic to prevent context window bloat and unnecessary token expenditure. It ensures the agent only processes relevant data shards and adheres to an Atomic Precision protocol—delivering functional answers with zero conversational filler. By recursively summarizing state and stripping "bridge phrases," it maximizes the longevity and speed of long-running development workflows.

When to Use This Skill

  • Use when building multi-step agents to prevent repetition and "memory drift" in long conversations.
  • Use when working with large document sets or codebases to avoid dumping entire files into the prompt.
  • Use when you need purely functional output (code/logic) without "Sure! Here is your..." intros.

How It Works

Step 1: Metadata Sharding

Scan the available data for headers, summaries, and key indicators. Create a "map" of the context rather than injecting the full source. Never pull the entire file into the prompt unless a specific, narrowed fragment is requested.

Step 2: Token Budget Allocation

Calculate a "Safe Response Limit" based on the current context window. Allocate 30% for current logic processing, 20% for immediate output, and 50% for a future context buffer.

Step 3: Atomic Output Filtering

Strip all "Bridge Phrases" (e.g., "I've updated the code," "Based on your request," "Sure"). Start the response immediately with the solution or the code block.

Step 4: Ambiguity Check

Before executing Step 3, scan for missing critical variables (e.g., specific file names or environment types). If the prompt is too ambiguous, bypass the atomic output and generate exactly one concise question to resolve the blocker.

Step 5: Abstractive Compression

Summarize the current turn into a "compressed state string" (e.g., [Project: Feasify | State: Auth-Fixed | Remaining-Tasks: 2]) to discard redundant conversational data before the next prompt.

Examples

Example 1: Filtered Code Output (No Filler)

User: "Update the Firebase config to use environment variables."
const firebaseConfig = {
  apiKey: process.env.VITE_FIREBASE_API_KEY,
  authDomain: process.env.VITE_FIREBASE_AUTH_DOMAIN,
  projectId: process.env.VITE_FIREBASE_PROJECT_ID
};

Example 2: Essential Clarification

User: "Deploy the function."
"Specify environment: production or staging?"

Best Practices

  • Direct Start: Place the code or answer at the very first character of the response.
  • Summarize-as-you-go: Turn 10 pages of discussion into 5 bullet points for the next turn.
  • Omit Signatures: Never end with "Let me know if you need more help."
  • No Bridge Phrases: Avoid "Here is the code," "Sure," or "I can help with that."
  • No Guessing: If input is missing, ask immediately rather than wasting tokens on a generic guess.

Limitations

  • This skill does not replace environment-specific validation, testing, or expert review.
  • Extreme brevity can occasionally hide important nuances; use concise inline comments (// crucial step) for critical notes.

Security & Safety Notes

  • Never prune safety headers, environment-specific security constraints, or system-level instructions during the compression stage.
  • Maintain original system instructions at the "Root" of the context to prevent context-loss-based jailbreaks.

Common Pitfalls

  • Problem: The response is so brief it lacks the context needed for implementation. Solution: Use concise inline code comments instead of separate paragraphs of text.

  • Problem: The agent loses the overarching goal due to over-compression. Solution: Always pin the "Primary Objective" to the top of every pruned prompt.

Related Skills

  • @atomic-precision-response - Specifically for removing conversational filler.
  • @context-sharding - For managing large-scale documentation mapping.