Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计提醒

content-optimization内容优化

Agent Skill

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

总安装

14,154

周安装

608

GitHub Stars

409

下载量

4,961
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:content-optimization(内容优化)
来源仓库:https://github.com/kostja94/marketing-skills
仓库路径:skills/content-optimization
安装命令:
npx skills add https://github.com/kostja94/marketing-skills --skill content-optimization
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/kostja94/marketing-skills --skill content-optimization

简介

content-optimization 用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。

  • 适用于提炼结构、补齐章节、统一术语或检查链接的场景。
  • 使用时应保留项目已有事实和路径,避免将未确认信息写成确定结论。
  • 涉及对外文案时需控制语气,避免过度营销或夸大能力。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

SEO Content: Content Optimization

Guides on-page content optimization: word count, heading keywords, keyword density vs stuffing, multimedia, tables, and lists. Complements heading-structure (structure) and content-strategy (planning).

When invoking: On first use, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.

Scope

  • Word count: For articles, see article-content (word count by type). This skill covers generic content length strategy.
  • H2 keywords: Placement, quantity, variation
  • Keyword density vs stuffing: Natural use; avoid manipulation
  • Multimedia: Images, tables, lists, video for structure and Featured Snippets. See featured-snippet for snippet-specific optimization; video-optimization for video SEO.

Initial Assessment

Check for project context first: If .claude/project-context.md or .cursor/project-context.md exists, read it for target keywords and content type.

Identify:

  1. Content type: Article, guide, listicle, pillar, news
  2. Target keyword: Primary and secondary
  3. Competitors: Top 10 average length and structure — see competitor-research

Word Count

Google does not rank by word count. Length should match search intent and topic depth. A 1,000-word post that satisfies intent can outrank a 3,000-word thin piece.

Reference Ranges by Content Type

For article word count by type (news, how-to, listicle, pillar, etc.), see article-content. Generic ranges:

Content typeWord countNotes
News / announcements300–600Time-sensitive; concise
Standard articles / how-tos1,000–1,500Single topic; actionable
Listicles / guides1,200–2,000"Top 10," "Best X"
Pillar / cornerstone2,000–3,500+Comprehensive; cluster hub

Strategy

  1. Analyze top 10 for target keyword — average length and depth
  2. Match intent — informational often needs ~40% longer than transactional
  3. Value over padding — each section must add genuine value; avoid fluff
  4. Comprehensive coverage — answer the query and related questions

H2 Heading Keywords

Placement

  • Primary keyword: Include naturally in at least one H2 when relevant
  • Related keywords: Use LSI and long-tail in other H2s for topical coverage
  • Avoid stuffing: Headings must stay clear and readable; organic placement only

Quantity

  • No strict limit — one H2 per major section; structure follows content
  • Typical article: 4–8 H2s; pillar: 8–15+ H2s
  • Hierarchy: H1 → H2 (major sections) → H3 (subsections); don't skip levels

Best Practices

PracticePurpose
Descriptive H2sSearch engines understand context; users scan
Answer-firstPlace direct answer in first 40–50 words after H2 for Featured Snippets; see featured-snippet
Keyword variationUse related terms; avoid repeating exact phrase in every H2
Logical flowH2s outline the article; support topical authority

Keyword Density vs Keyword Stuffing

Definitions

TermMeaning
Keyword density(Keyword count / Total words) × 100; a metric, not a ranking factor
Keyword stuffingExcessive, unnatural repetition to manipulate rankings; black-hat

Current Guidance

  • Keyword density is not a direct ranking factor — Google has stated since 2011 that repetition alone doesn't improve rankings
  • Reference range: 0.5%–1.5% for most content; some sources cite up to 2.5%
  • Use density mainly to avoid stuffing — if density exceeds ~2–3% and reads unnaturally, reduce
  • Prioritize natural placement: title, H1, first 100 words, 1–2 H2s, body; avoid forced repetition

How to Avoid Stuffing

  • Write for users first; keywords should fit naturally
  • Use synonyms, related terms, and question phrasing
  • If a sentence sounds awkward with the keyword, rewrite
  • Monitor: if every paragraph repeats the exact phrase, simplify

Multimedia: Images, Tables, Lists

Images

PracticePurpose
Alt, file names, captionsSee image-optimization for full image SEO (alt, format, responsive, lazy loading, image sitemap, LCP, captions for Featured Snippets)
Original over stockUnique images signal E-E-A-T — see eeat-signals

Content placement: Put images near relevant text; captions support snippet thumbnails. See image-optimization for captions; featured-snippet for snippet context.

Video

PracticePurpose
Embed + metadataVideoObject schema, video sitemap, thumbnail; see video-optimization
YouTubeGoogle prioritizes YouTube in search; GEO citation; see youtube-seo, generative-engine-optimization
Featured Snippet (video)Video schema; timestamps/chapters; see featured-snippet

Tables

  • Use for: Comparisons, stats, specs, "X vs Y"
  • Semantic HTML: <table>, <thead>, <tbody>, clear column headers
  • Featured Snippets: ~6% of snippets are tables; optimize headers with target keywords. See featured-snippet
  • Mobile: Responsive; avoid horizontal scroll when possible
  • Data quality: No empty cells; consistent units; accurate, current data

Lists: Ordered vs Unordered

TypeUse caseSEO / Snippet
Ordered (<ol>)Steps, rankings, sequences, "Top 10"List snippets (~19% of Featured Snippets); how-to; see featured-snippet
Unordered (<ul>)Non-sequential items, features, optionsBullet snippets; definitions, options

Best practices:

  • Use semantic <ol> and <ul>; avoid divs styled as lists
  • Answer-first: For snippet targets, put the direct answer in the first 40–50 words after the heading
  • Concise items: List items should be scannable; expand in body if needed
  • Logical order: Ordered lists = sequence matters; unordered = no sequence

GEO / AI Citation

Answer-first (direct answer in first 40–60 words after H2) supports both Featured Snippets and GEO. For article-level GEO (TL;DR, Key Takeaways, QAE pattern), see article-content and generative-engine-optimization. For Featured Snippet formats and optimization, see featured-snippet.


Content Audit Checklist

For article content audit (hook, QAE, product connection, CTA, references, gaps), see article-content. This skill covers generic content optimization (H2 keywords, multimedia, keyword density).


Output Format

  • Word count recommendation by content type
  • H2 outline with keyword placement
  • Keyword density check (avoid stuffing)
  • Structure (tables, lists) for Featured Snippet opportunity; see featured-snippet
  • Multimedia checklist (images per image-optimization; tables, lists)

Related Skills

  • heading-structure: H1–H6 hierarchy; H2 keyword placement
  • content-strategy: Topic clusters, pillar + cluster
  • keyword-research: Target keywords inform placement
  • featured-snippet: Snippet formats, structure; answer-first
  • howto-section-generator: How-to step sections; <ol> lists; HowTo vs FAQ
  • eeat-signals: E-E-A-T; original images, trust
  • image-optimization: Alt, captions, format, LCP, responsive, image sitemap
  • video-optimization: Video SEO; VideoObject; video sitemap
  • competitor-research: Competitor length and structure as reference
  • article-content: Article word count by type; Content Audit Checklist; article body creation

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

37.59%
按下载量换算1,865

Claude

27.16%
按下载量换算1,347

Cursor

19.87%
按下载量换算986

Gemini CLI

8.7%
按下载量换算432

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills