writing-skills
について
このスキルは、効果的なスキルを構築するタイミングと方法を説明することで、開発者がSKILL.mdドキュメントを作成および更新することを支援します。適切なフロントマターと簡潔なマークダウンコンテンツを用いて、スキルドキュメントを構造化するためのガイドラインを提供します。スキルは、必要な時のみコーディングエージェントに対し的確なコンテキストを提供するように設計されており、不必要なLLMコンテキストの肥大化を防ぎます。
クイックインストール
Claude Code
推奨/plugin add https://github.com/dave1010/toolsgit clone https://github.com/dave1010/tools.git ~/.claude/skills/writing-skills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
Skills are used to for context that may be useful to a coding agent, without bloating LLM context at times theyre not useful.
Skills are only worthwhile if the coding agent fails a task without the skill.
Skills live in /.skills, with each skill having its own directory.
SKILL.md
Front matter
- Match the
nameto the directory name exactly. - Write the
descriptionas "Use when <scenario> - <what it does>" in under 30 words and third person. - Quote the description if it includes punctuation that could break YAML.
Markdown body
- Write concise instructions for the skill topic.
- Keep headings and bullet lists structured so readers can scan quickly.
Aditional files
Other files, like scripts or data, may live in the directory and be referenced by the skill.
AGENTS.md
A GitHub Action automatically regenerates the skills list in AGENTS.md.
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.
evaluating-llms-harness
テストThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
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.
