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

algo-seo-contentalgo SEO 内容

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

364

周安装

15

GitHub Stars

125

下载量

119
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:algo-seo-content(algo SEO 内容)
来源仓库:https://github.com/asgard-ai-platform/skills
仓库路径:skills/algo-seo-content
安装命令:
npx skills add https://github.com/asgard-ai-platform/skills --skill algo-seo-content
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/asgard-ai-platform/skills --skill algo-seo-content

简介

algo-seo-content 辅助内容策划与 SEO 优化,覆盖关键词研究到性能监控的全流程。

  • 适用于规划新内容、优化低效旧文及开展内容差距分析的任务场景。
  • 强调搜索意图匹配而非关键词堆砌,可集成到文档整理和内容改写流程中。
  • 安装依赖 GitHub 仓库,执行前应检查是否会触发文件读写或网络请求。
  • 不涉及技术性能调优,专注内容层面的语义与结构优化。

SKILL.md

Content SEO Strategy

Overview

Content SEO is the systematic process of creating and optimizing content to match search intent and rank organically. The pipeline: keyword research → intent mapping → content creation → on-page optimization → performance monitoring. Success depends on intent match, not keyword density.

When to Use

Trigger conditions:

  • Planning new content to capture organic search traffic
  • Optimizing existing underperforming content
  • Conducting keyword research and content gap analysis

When NOT to use:

  • When the issue is technical (page speed, crawlability) — use technical SEO
  • When the issue is off-page (backlinks, authority) — use backlink analysis

Algorithm

IRON LAW: Content Must Match SEARCH INTENT
A perfectly optimized page targeting the wrong intent will NOT rank.
Four intent types:
1. Informational — wants to learn ("how to", "what is")
2. Navigational — wants a specific site ("github login")
3. Commercial — comparing options ("best CRM 2025")
4. Transactional — wants to buy/do ("buy iPhone 16 case")
Check SERP results to determine actual intent before writing.

Phase 1: Input Validation

Define target topic/niche. Gather seed keywords from brainstorming, competitor analysis, and tools (Ahrefs, SEMrush, Google Keyword Planner). Gate: Seed keyword list with search volume and difficulty estimates.

Phase 2: Core Algorithm

  1. Keyword clustering: Group related keywords by intent and topic
  2. SERP analysis: Check top 10 results for each cluster — identify intent, content format, and depth
  3. Content gap analysis: Find keywords competitors rank for that you don't
  4. Content brief: Define: target keyword, intent, format (guide/list/comparison), word count benchmark, required subtopics from SERP analysis
  5. On-page optimization: Title tag (keyword front-loaded), meta description, H1/H2 structure, internal links, image alt text

Phase 3: Verification

Check: title contains primary keyword, intent matches SERP, all key subtopics covered, internal links to related content. Gate: Content matches identified intent and covers SERP-derived subtopics.

Phase 4: Output

Return content brief and optimization checklist.

Output Format

{
  "content_brief": {"primary_keyword": "...", "intent": "informational", "format": "how-to guide", "target_word_count": 2000, "subtopics": ["...", "..."]},
  "optimization": {"title": "...", "meta_description": "...", "h2_structure": ["...", "..."], "internal_links": 5},
  "metadata": {"search_volume": 2400, "keyword_difficulty": 35}
}

Examples

Sample I/O

Input: Topic "email marketing automation", target market: Taiwan SMBs Expected: Primary KW: "email行銷自動化", intent: commercial investigation, format: comparison guide, 2500 words

Edge Cases

InputExpectedWhy
Zero search volume keywordConsider if it's emerging or nonexistentMay be worth targeting if topically relevant
KD > 80 for new siteTarget long-tail variants firstNew sites can't compete on high-KD terms
Mixed intent SERPCreate content matching dominant intentDon't try to serve all intents in one page

Gotchas

  • Keyword density is dead: There's no optimal keyword density. Write naturally. Forced keyword insertion hurts readability and may trigger spam signals.
  • Search volume ≠ traffic: A #1 ranking for a 10K volume keyword won't bring 10K visits. Click-through rates vary by SERP features (ads, featured snippets, PAA).
  • Content freshness: Some queries demand fresh content (e.g., "best laptop 2025"). Outdated content drops rankings even if it once ranked #1.
  • Cannibalization: Multiple pages targeting the same keyword compete with each other. One strong page outperforms three mediocre ones.
  • E-E-A-T: For YMYL topics (health, finance), Google requires demonstrated Experience, Expertise, Authority, and Trust. Anonymous content won't rank.

References

  • For keyword clustering methodology, see references/keyword-clustering.md
  • For content brief templates, see references/content-brief-template.md

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

Claude

35.42%
按下载量换算42

Codex

34.64%
按下载量换算41

Cursor

18.2%
按下载量换算22

Gemini CLI

9.65%
按下载量换算11

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