context-monitor
について
コンテキスト監視スキルは、トークン使用量を自動的に追跡し、30k、50k、70kトークンの閾値で警告を提供して、コンテキスト枯渇を防止します。このスキルは、エージェント呼び出し時や大規模ファイル操作時にキーワードなしで自動起動し、コンテキスト管理の具体的な推奨事項を提示します。開発者はこのスキルを活用して最適なパフォーマンスを維持し、/clearコマンドを使用する適切なタイミングを把握すべきです。
クイックインストール
Claude Code
推奨/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/context-monitor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
Context Usage Monitor
Purpose
Monitor and warn about context usage to prevent context exhaustion.
Usage Thresholds
- 30k tokens: First warning (Yellow)
- 50k tokens: Strong warning (Orange)
- 70k tokens: Critical warning (Red) - Consider /clear
Monitoring Points
- After each agent invocation
- Before complex tasks
- When reading large files
Warning Messages
Yellow (30k)
⚠️ Context Usage: ~30k tokens
Consider focusing on current task only.
Orange (50k)
🟠 Context Usage: ~50k tokens
Recommend completing current task then /clear.
Red (70k+)
🔴 Context Usage: 70k+ tokens
CRITICAL: Use /clear soon to prevent errors.
Save important context before clearing.
Best Practices
- Use subagents to preserve main context
- Clear context between major features
- Avoid reading unnecessary large files
- Use Task tool for complex searches
Context-Saving Commands
Before /clear, save important info:
# Save current branch and status
git status > /tmp/context_save.txt
git diff --staged >> /tmp/context_save.txt
# After /clear, restore context:
cat /tmp/context_save.txt
Skill Version: v1.0 Last Updated: 2025-12-25 Project: career_ios_backend
GitHub リポジトリ
関連スキル
content-collections
メタThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
sglang
メタSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
cloudflare-turnstile
メタThis skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.
Algorithmic Art Generation
メタThis skill helps developers create algorithmic art using p5.js, focusing on generative art, computational aesthetics, and interactive visualizations. It automatically activates for topics like "generative art" or "p5.js visualization" and guides you through creating unique algorithms with features like seeded randomness, flow fields, and particle systems. Use it when you need to build reproducible, code-driven artistic patterns.
