content-optimizer
について
コンテンツ最適化スキルは、キーワード密度、メタタグ、見出し構造、読みやすさを分析することで、オンページSEOの検証と改善を行います。開発者はこのスキルを活用して、既存コンテンツの最適化や、新規コンテンツがSEO要件を満たしているかの検証が可能です。キーワード配置やタイトルタグの長さといった主要要素について、具体的な指標と警告を提供します。
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/content-optimizer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
Content Optimizer
When to Use
- Optimizing existing content for better rankings
- Validating new content against SEO requirements
- Checking keyword density and placement
- Improving readability scores
- Creating meta tags
Keyword Density
Target: 1-2% for primary keyword
Calculation:
Density = (Keyword Count / Total Words) x 100
Placement Priorities:
- Title/H1 (required)
- First 100 words (required)
- At least one H2 (recommended)
- Conclusion (recommended)
- Distributed in body (natural)
Warning Signs:
-
3% = Keyword stuffing risk
- <0.5% = Under-optimized
- Exact match every paragraph = Unnatural
Meta Tag Optimization
Title Tag
- Length: 50-60 characters
- Keyword: Near the beginning
- Format:
{Keyword} - {Benefit} | {Brand} - Unique per page
Meta Description
- Length: 150-160 characters
- Keyword: Include naturally
- CTA: End with action verb
- Unique per page
URL Slug
- Short: 3-5 words
- Keyword: Include primary
- Readable: Use hyphens
- Lowercase only
Heading Structure
Valid Hierarchy:
H1: Page Title (exactly 1)
+-- H2: Main Section
| +-- H3: Subsection
| +-- H3: Subsection
+-- H2: Main Section
| +-- H3: Subsection
+-- H2: Conclusion
Common Errors:
- Multiple H1 tags
- Skipping levels (H1 -> H3)
- Using headings for styling only
- No keyword in H1
Readability Optimization
Flesch Reading Ease Target: 60-70
| Score | Level | Audience |
|---|---|---|
| 90-100 | Very Easy | 5th grade |
| 80-89 | Easy | 6th grade |
| 70-79 | Fairly Easy | 7th grade |
| 60-69 | Standard | 8th-9th grade |
| 50-59 | Fairly Difficult | 10th-12th grade |
| 30-49 | Difficult | College |
| 0-29 | Very Difficult | College graduate |
Improvement Techniques:
- Shorten sentences (<20 words avg)
- Shorten paragraphs (2-3 sentences)
- Replace jargon with plain language
- Use active voice
- Add subheadings every 200-300 words
- Use bullet points for lists
Optimization Checklist
Use this checklist when optimizing content:
- Primary keyword in title/H1
- Primary keyword in first 100 words
- Keyword density 1-2%
- Meta title 50-60 characters
- Meta description 150-160 characters with CTA
- Heading hierarchy valid (H1 -> H2 -> H3)
- At least 3 internal links
- At least 1 external authoritative link
- Flesch score 60-70
- No paragraphs > 3 sentences
- Subheadings every 200-300 words
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.
creating-opencode-plugins
メタThis skill provides the structure and API specifications for creating OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It offers implementation patterns for JavaScript/TypeScript modules that intercept and extend the AI assistant's lifecycle. Use it when you need to build event-driven plugins for monitoring, custom handling, or extending OpenCode's capabilities.
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.
