MCP HubMCP Hub
スキル一覧に戻る

core-context-management-size-limits-mandatory

vamseeachanta
更新日 Today
10 閲覧
3
2
3
GitHubで表示
その他general

について

この必須スキルは、コンテキスト効率を維持するためにClaude設定ファイル(CLAUDE.mdの各種バリアント)のサイズ制限を強制します。コンプライアンスを確認する検証スクリプトを提供し、これらのファイルに必要なコンテンツカテゴリを指定します。開発者はこれを使用して、効果的なAI支援のためにClaudeワークスペース設定が最適な範囲内に収まることを保証します。

クイックインストール

Claude Code

推奨
メイン
npx skills add vamseeachanta/workspace-hub
プラグインコマンド代替
/plugin add https://github.com/vamseeachanta/workspace-hub
Git クローン代替
git clone https://github.com/vamseeachanta/workspace-hub.git ~/.claude/skills/core-context-management-size-limits-mandatory

このコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします

ドキュメント

Size Limits (MANDATORY) (+3)

Size Limits (MANDATORY)

FileMax SizeMax LinesPurpose
~/.claude/CLAUDE.md2KB50Global preferences
Workspace CLAUDE.md4KB100Delegation patterns
Project CLAUDE.md8KB200Project rules
CLAUDE.local.md2KB50User overrides

Validation Command

# Run validation across all repos
./scripts/context/validate_context.sh

# Check single repo
./scripts/context/validate_context.sh digitalmodel

Content Categories

MUST be in CLAUDE.md:

  • Mandatory behavioral rules (TDD, batching, etc.)
  • Plan mode conventions
  • Cross-review requirements
  • File organization rules
  • Key delegation patterns

MUST be in .claude/docs/ (reference):

  • Agent lists and descriptions
  • MCP tool reference tables
  • Execution workflow diagrams
  • Code examples and patterns
  • Memory namespace details

Automated Improvement

The skill analyzes past work to suggest improvements:

  1. Pattern Detection: Identifies frequently used instructions
  2. Redundancy Removal: Flags duplicate content across files
  3. Usage Analysis: Tracks which docs are actually loaded
  4. Suggestion Generation: Proposes optimizations

GitHub リポジトリ

vamseeachanta/workspace-hub
パス: .claude/skills/_core/context-management/size-limits-mandatory

関連スキル

algorithmic-art

メタ

This Claude Skill creates original algorithmic art using p5.js with seeded randomness and interactive parameters. It generates .md files for algorithmic philosophies, plus .html and .js files for interactive generative art implementations. Use it when developers need to create flow fields, particle systems, or other computational art while avoiding copyright issues.

スキルを見る

subagent-driven-development

開発

This skill executes implementation plans by dispatching a fresh subagent for each independent task, with code review between tasks. It enables fast iteration while maintaining quality gates through this review process. Use it when working on mostly independent tasks within the same session to ensure continuous progress with built-in quality checks.

スキルを見る

executing-plans

デザイン

Use the executing-plans skill when you have a complete implementation plan to execute in controlled batches with review checkpoints. It loads and critically reviews the plan, then executes tasks in small batches (default 3 tasks) while reporting progress between each batch for architect review. This ensures systematic implementation with built-in quality control checkpoints.

スキルを見る

cost-optimization

その他

This Claude Skill helps developers optimize cloud costs through resource rightsizing, tagging strategies, and spending analysis. It provides a framework for reducing cloud expenses and implementing cost governance across AWS, Azure, and GCP. Use it when you need to analyze infrastructure costs, right-size resources, or meet budget constraints.

スキルを見る