SkillAtlasSkill 详情

seo-sxo

Codex-first SEO analysis suite with 1 orchestrator skill, 26 specialist workflows, 24 TOML agent...

审核状态:已审核Quality 80Security 92

复制安装命令

用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。

复制前请先查看来源、License 和安全提示。

项目 README

来源文件:README.md

抓取于 2026年8月25日

Codex SEO: SEO audit skill suite for Codex

Watch on YouTube

Codex SEO - SEO Audit Skill Suite for Codex

Codex-first SEO analysis suite with 1 orchestrator skill, 26 specialist workflows, 24 TOML agent profiles, MCP/API extensions, deterministic headless runners, and premium audit report generation.

CI Release Codex Skill License: MIT Python Workflows

Codex SEO is a Codex-native port of AgriciDaniel/claude-seo, synchronized to upstream main at a9cf338 and adapted for Codex skills, Codex plugins, TOML agents, shared cache artifacts, and repeatable local/API execution.

It covers technical SEO, on-page analysis, content quality, E-E-A-T, schema markup, image optimization, sitemap architecture, Core Web Vitals, GEO/AEO for AI search, backlinks, local SEO, maps intelligence, Google APIs, semantic clustering, SXO, drift monitoring, e-commerce SEO, hreflang, FLOW prompts, DataForSEO, Firecrawl, and Gemini/nanobanana image workflows.

Contents

Status

  • Repository visibility: public.
  • Current release: v1.9.6-codex.5.
  • Installer default ref: v1.9.6-codex.5.
  • Latest local validation: 52 tests passing, full installed smoke suite passing, demo readiness passing.
  • Runtime credentials stay outside the repo under Codex/local config paths.
  • Discovery topics: codex, codex-cli, codex-skills, seo, ai-seo, ai-search, technical-seo, generative-engine-optimization, core-web-vitals, schema-markup, local-seo, ecommerce-seo, content-strategy, google-search-console, dataforseo, mcp, python, automation, marketing-automation, open-source.

Install

One-Line Install

curl -fsSL https://raw.githubusercontent.com/AgriciDaniel/codex-seo/v1.9.6-codex.5/install.sh | bash

Windows:

irm https://raw.githubusercontent.com/AgriciDaniel/codex-seo/v1.9.6-codex.5/install.ps1 | iex

Review Before Installing

git clone https://github.com/AgriciDaniel/codex-seo.git
cd codex-seo
bash install.sh

Windows:

git clone https://github.com/AgriciDaniel/codex-seo.git
cd codex-seo
powershell -ExecutionPolicy Bypass -File .\install.ps1

The installer copies the skill suite into ~/.codex/skills/, installs TOML agents into ~/.codex/agents/, creates a Python virtualenv at ~/.codex/skills/seo/.venv/, installs core runtime dependencies, attempts optional capability groups, and verifies the runtime.

Installer Overrides

CODEX_HOME=~/.codex \
CODEX_SEO_REPO=https://github.com/AgriciDaniel/codex-seo \
CODEX_SEO_REF=v1.9.6-codex.5 \
bash install.sh
VariablePurpose
CODEX_HOMEAlternate Codex home. Defaults to ~/.codex.
CODEX_SEO_REPOGit URL, fork URL, or local repository path.
CODEX_SEO_REFBranch, tag, or commit. Defaults to v1.9.6-codex.5.
CODEX_SEO_SKIP_PLAYWRIGHT_BROWSER=1Skip Chromium install for visual/PDF workflows.
CODEX_SEO_PLAYWRIGHT_WITH_DEPS=1Ask Playwright to install system dependencies where supported.

Quick Start

Restart Codex after installation. Then ask naturally; a /seo command is not required:

Do a full SEO check on https://example.com following best practices.
Review this page for schema, Core Web Vitals, image SEO, and AI search readiness.
Create an SEO strategy and content roadmap for a local dental clinic.

Command-style prompts also work:

/seo audit https://example.com
/seo technical https://example.com
/seo schema https://example.com
/seo dataforseo serp "best seo tools"

Visual Overview

Codex SEO is designed as a Codex-first routing layer: the user can ask naturally, the orchestrator selects the right specialist workflow, and deterministic runners write repeatable artifacts instead of relying on invisible chat-only output.

%%{init: {"theme":"base","themeVariables":{"background":"#05080d","primaryColor":"#07131c","primaryTextColor":"#f5fbff","primaryBorderColor":"#00d7e6","lineColor":"#00d7e6","secondaryColor":"#06222a","tertiaryColor":"#ff9f1c","edgeLabelBackground":"#05080d","fontFamily":"Inter, ui-sans-serif, system-ui, sans-serif"}}}%%
flowchart LR
  user["User prompt<br/>natural language or /seo"] --> orchestrator["skills/seo/SKILL.md<br/>main orchestrator"]
  orchestrator --> cache[".seo-cache<br/>shared evidence"]
  orchestrator --> skills["26 specialist<br/>SEO workflows"]
  skills --> agents["24 TOML agents<br/>parallel analysis slices"]
  skills --> scripts["scripts/<br/>deterministic runners"]
  scripts --> output["output/<br/>Markdown, JSON, HTML, PDF"]
  cache --> skills
  class user,orchestrator accent
  class cache,scripts data
  class output output
  classDef default fill:#07131c,stroke:#00d7e6,color:#f5fbff,stroke-width:1.4px
  classDef accent fill:#10151a,stroke:#ff9f1c,color:#fff7ed,stroke-width:2px
  classDef data fill:#06222a,stroke:#21e6c1,color:#ecfeff,stroke-width:1.5px
  classDef output fill:#15101a,stroke:#ff9f1c,color:#fff7ed,stroke-width:1.8px

Commands

PromptPurpose
/seo audit <url>Full site audit with specialist routing and premium report support
/seo page <url>Deep single-page SEO analysis
/seo technical <url>Crawlability, indexability, security, JavaScript, CWV
/seo content <url>E-E-A-T, helpfulness, readability, AI citation readiness
/seo schema <url>Structured data detection, validation, and JSON-LD generation
/seo images <url>Alt text, image weight, formats, metadata, image SERP opportunities
/seo sitemap <url>XML sitemap discovery, quality gates, generation guidance
/seo geo <url>AI Overviews, ChatGPT, Perplexity, llms.txt, citability
/seo performance <url>Core Web Vitals, Lighthouse-oriented performance signals
/seo visual <url>Screenshots, mobile rendering, above-the-fold analysis
/seo plan <business-type>Strategic SEO roadmap and content plan
/seo programmatic <url>Programmatic SEO risk and scale planning
/seo competitor-pages <url>Comparison and alternatives page opportunities
/seo hreflang <url>International SEO, locale validation, content parity
/seo local <url>Local SEO, GBP signals, NAP, citations, reviews
/seo maps <command>Geo-grid, GBP audit, review intelligence, local maps signals
/seo google <command>GSC, PageSpeed, CrUX, Indexing API, GA4 workflows
/seo backlinks <url>Backlink profile summary and source-tier detection
/seo cluster <keyword>SERP-based topic clustering and hub-spoke planning
/seo sxo <url>Search Experience Optimization, intent/page-type fit
/seo drift baseline <url>Capture an SEO baseline before changes
/seo drift compare <url>Compare current SEO signals against a baseline
/seo ecommerce <url>Product SEO, marketplace visibility, product schema
/seo flow <stage>FLOW framework prompts for Find, Leverage, Optimize, Win
/seo dataforseo <command>Live SERP, keyword, backlink, content, and AI visibility data
/seo firecrawl <command>JS-rendered crawling and site mapping via Firecrawl
/seo image-gen <use-case>OG images, hero images, product visuals, infographics

Full command details live in docs/COMMANDS.md.

Features

Full Audit Pipeline

  • Detects site/business type.
  • Runs technical, content, schema, sitemap, performance, visual, GEO, image, and on-page analysis.
  • Adds conditional specialists for local, maps, Google APIs, backlinks, clusters, SXO, drift, and e-commerce.
  • Writes markdown reports, JSON summaries, cache artifacts, and optional premium HTML/PDF output.
%%{init: {"theme":"base","themeVariables":{"background":"#05080d","primaryColor":"#07131c","primaryTextColor":"#f5fbff","primaryBorderColor":"#00d7e6","lineColor":"#00d7e6","secondaryColor":"#06222a","tertiaryColor":"#ff9f1c","edgeLabelBackground":"#05080d","fontFamily":"Inter, ui-sans-serif, system-ui, sans-serif"}}}%%
flowchart TD
  request["Audit request"] --> detect["Detect site type<br/>business model and context"]
  detect --> core["Core audit specialists"]
  core --> technical["Technical"]
  core --> content["Content"]
  core --> schema["Schema"]
  core --> sitemap["Sitemap"]
  core --> geo["GEO / AI search"]
  core --> images["Images"]
  core --> performance["Performance"]
  core --> visual["Visual"]
  detect --> conditional["Conditional specialists"]
  conditional --> local["Local / Maps"]
  conditional --> backlinks["Backlinks"]
  conditional --> google["Google APIs"]
  conditional --> ecommerce["E-commerce"]
  conditional --> drift["Drift"]
  technical --> report["Unified SEO report"]
  content --> report
  schema --> report
  sitemap --> report
  geo --> report
  images --> report
  performance --> report
  visual --> report
  local --> report
  backlinks --> report
  google --> report
  ecommerce --> report
  drift --> report
  report --> artifacts["SUMMARY.json<br/>FULL-AUDIT-REPORT.md<br/>ACTION-PLAN.md<br/>optional HTML/PDF"]
  class request,detect accent
  class core,conditional data
  class report,artifacts output
  classDef default fill:#07131c,stroke:#00d7e6,color:#f5fbff,stroke-width:1.4px
  classDef accent fill:#10151a,stroke:#ff9f1c,color:#fff7ed,stroke-width:2px
  classDef data fill:#06222a,stroke:#21e6c1,color:#ecfeff,stroke-width:1.5px
  classDef output fill:#15101a,stroke:#ff9f1c,color:#fff7ed,stroke-width:1.8px

Technical SEO

  • Robots.txt, sitemap discovery, canonical checks, indexability, URL hygiene.
  • Security headers, JavaScript rendering risk, mobile basics, IndexNow.
  • Core Web Vitals with INP, LCP, CLS, FCP, TTFB, and PageSpeed/CrUX integrations where available.

Content, GEO, And SXO

  • E-E-A-T and helpful content signals.
  • AI citation readiness, answer-first formatting, entity clarity, llms.txt support.
  • Search experience analysis: page type, user stories, persona fit, intent mismatch.

Structured Data

  • JSON-LD extraction and validation.
  • Schema recommendations for Organization, LocalBusiness, Product, Article, FAQ, Breadcrumb, and related types.
  • Generated schema artifacts for downstream use.

Local, Maps, And E-Commerce SEO

  • Local SEO signals, GBP readiness, citations, reviews, NAP consistency.
  • Maps intelligence via free sources and DataForSEO when configured.
  • Product schema, marketplace endpoints, merchant visibility, and e-commerce template checks.

Drift Monitoring

  • Capture SEO-critical baselines.
  • Compare deployments or page changes.
  • Track title, meta, headings, canonical, schema, robots, links, and content deltas.
%%{init: {"theme":"base","themeVariables":{"background":"#05080d","primaryColor":"#07131c","primaryTextColor":"#f5fbff","primaryBorderColor":"#00d7e6","lineColor":"#00d7e6","actorBkg":"#07131c","actorBorder":"#00d7e6","actorTextColor":"#f5fbff","actorLineColor":"#21e6c1","signalColor":"#21e6c1","signalTextColor":"#f5fbff","labelBoxBkgColor":"#10151a","labelTextColor":"#f5fbff","noteBkgColor":"#10151a","noteTextColor":"#f5fbff","activationBkgColor":"#06222a","activationBorderColor":"#ff9f1c","fontFamily":"Inter, ui-sans-serif, system-ui, sans-serif"}}}%%
sequenceDiagram
  participant Before as Baseline
  participant Runner as Drift runner
  participant After as Current page
  participant Cache as .seo-cache
  participant Report as Drift report
  Before->>Runner: Capture titles, metas, canonicals, schema, headings
  Runner->>Cache: Store baseline snapshot
  After->>Runner: Re-check current SEO signals
  Cache->>Runner: Load prior snapshot
  Runner->>Report: Write changed, missing, and regressed signals

Deterministic Runners

  • scripts/run_skill_workflow.py standardizes output for every user-invokable workflow.
  • scripts/run_api_smoke_suite.py runs all supported workflows in one pass.
  • Setup-required workflows return structured fallback results instead of pretending live data exists.

Extensions

ExtensionSkillSetupNotes
DataForSEOseo-dataforseo, seo-maps, seo-ecommerce, seo-cluster./extensions/dataforseo/install.shLive SERP, keyword, backlinks, on-page, content, business data, AI visibility
Google APIsseo-google, seo-performancepython scripts/google_auth.py --setupPageSpeed, CrUX, GSC, URL Inspection, Indexing API, GA4
Firecrawlseo-firecrawl./extensions/firecrawl/install.shJS-rendered crawl, scrape, site map
Banana / Geminiseo-image-gen./extensions/banana/install.shAI image generation through nanobanana-mcp

Optional integrations enrich the same workflow surface. If credentials or MCP servers are missing, wrappers return setup_required or mcp_configured states with no fabricated live data.

%%{init: {"theme":"base","themeVariables":{"background":"#05080d","primaryColor":"#07131c","primaryTextColor":"#f5fbff","primaryBorderColor":"#00d7e6","lineColor":"#00d7e6","secondaryColor":"#06222a","tertiaryColor":"#ff9f1c","edgeLabelBackground":"#05080d","fontFamily":"Inter, ui-sans-serif, system-ui, sans-serif"}}}%%
flowchart LR
  codex["Codex SEO workflows"] --> local["Local evidence<br/>HTML, robots, sitemaps, screenshots"]
  codex --> dfs["DataForSEO MCP<br/>SERP, keywords, backlinks, maps"]
  codex --> google["Google APIs<br/>GSC, PageSpeed, CrUX, GA4"]
  codex --> firecrawl["Firecrawl MCP<br/>JS crawl and site maps"]
  codex --> banana["Gemini / nanobanana<br/>SEO image assets"]
  local --> artifacts["Reports and .seo-cache"]
  dfs --> artifacts
  google --> artifacts
  firecrawl --> artifacts
  banana --> artifacts
  class codex accent
  class local,dfs,google,firecrawl,banana data
  class artifacts output
  classDef default fill:#07131c,stroke:#00d7e6,color:#f5fbff,stroke-width:1.4px
  classDef accent fill:#10151a,stroke:#ff9f1c,color:#fff7ed,stroke-width:2px
  classDef data fill:#06222a,stroke:#21e6c1,color:#ecfeff,stroke-width:1.5px
  classDef output fill:#15101a,stroke:#ff9f1c,color:#fff7ed,stroke-width:1.8px

Demo readiness:

python scripts/demo_readiness.py --target https://example.com --live-apis --workflows --json

One low-depth DataForSEO proof:

python scripts/demo_readiness.py --target https://example.com --live-apis --live-serp --serp-keyword "seo tools" --json

Headless/API Usage

Run a single workflow:

python scripts/run_skill_workflow.py --skill seo-technical https://example.com --json
python scripts/run_skill_workflow.py --skill seo-google https://example.com --json
python scripts/run_skill_workflow.py --skill seo-dataforseo https://example.com --json

Run the full smoke suite:

python scripts/run_api_smoke_suite.py https://example.com --json

Verify environment:

python scripts/verify_environment.py --target https://example.com --json

Bootstrap a clean runtime:

python scripts/bootstrap_environment.py --venv .venv --json

Artifacts are written to output/. Shared project cache is written to .seo-cache/. Both are ignored by git.

%%{init: {"theme":"base","themeVariables":{"background":"#05080d","primaryColor":"#07131c","primaryTextColor":"#f5fbff","primaryBorderColor":"#00d7e6","lineColor":"#00d7e6","secondaryColor":"#06222a","tertiaryColor":"#ff9f1c","edgeLabelBackground":"#05080d","fontFamily":"Inter, ui-sans-serif, system-ui, sans-serif"}}}%%
flowchart LR
  cli["run_skill_workflow.py<br/>single workflow"] --> json["JSON result"]
  cli --> markdown["Markdown report"]
  cli --> cacheWrite[".seo-cache update"]
  suite["run_api_smoke_suite.py<br/>all workflows"] --> json
  suite --> outputRoot["output/api-smoke-*"]
  verify["verify_environment.py"] --> readiness["ready / setup_required<br/>capability status"]
  markdown --> outputRoot
  json --> outputRoot
  cacheWrite --> cache[".seo-cache"]
  class cli,suite,verify accent
  class cacheWrite,readiness data
  class json,markdown,outputRoot,cache output
  classDef default fill:#07131c,stroke:#00d7e6,color:#f5fbff,stroke-width:1.4px
  classDef accent fill:#10151a,stroke:#ff9f1c,color:#fff7ed,stroke-width:2px
  classDef data fill:#06222a,stroke:#21e6c1,color:#ecfeff,stroke-width:1.5px
  classDef output fill:#15101a,stroke:#ff9f1c,color:#fff7ed,stroke-width:1.8px

Architecture

The repository separates Codex-facing instructions, deterministic runtime code, optional provider setup, and validation contracts. That keeps the skill system usable in chat, installable as a suite, and testable from CI/API workflows.

%%{init: {"theme":"base","themeVariables":{"background":"#05080d","primaryColor":"#07131c","primaryTextColor":"#f5fbff","primaryBorderColor":"#00d7e6","lineColor":"#00d7e6","secondaryColor":"#06222a","tertiaryColor":"#ff9f1c","edgeLabelBackground":"#05080d","fontFamily":"Inter, ui-sans-serif, system-ui, sans-serif"}}}%%
flowchart TB
  manifest[".codex-plugin/plugin.json"] --> skillsRoot["skills/"]
  skillsRoot --> orchestrator["seo/SKILL.md<br/>routing and orchestration"]
  skillsRoot --> specialists["seo-*/SKILL.md<br/>specialist workflows"]
  agentsDir["agents/seo-*.toml"] --> specialists
  scriptsDir["scripts/<br/>deterministic runners"] --> specialists
  extensionsDir["extensions/<br/>optional MCP setup"] --> specialists
  references["skills/seo/references/<br/>thresholds and shared contracts"] --> specialists
  specialists --> cacheDir[".seo-cache/<br/>cross-skill memory"]
  specialists --> outputDir["output/<br/>reports and artifacts"]
  testsDir["tests/<br/>contract and smoke coverage"] --> manifest
  testsDir --> skillsRoot
  testsDir --> scriptsDir
  class manifest,orchestrator accent
  class skillsRoot,specialists,agentsDir,scriptsDir,extensionsDir,references,testsDir data
  class cacheDir,outputDir output
  classDef default fill:#07131c,stroke:#00d7e6,color:#f5fbff,stroke-width:1.4px
  classDef accent fill:#10151a,stroke:#ff9f1c,color:#fff7ed,stroke-width:2px
  classDef data fill:#06222a,stroke:#21e6c1,color:#ecfeff,stroke-width:1.5px
  classDef output fill:#15101a,stroke:#ff9f1c,color:#fff7ed,stroke-width:1.8px
codex-seo/
├── .codex-plugin/plugin.json        # Codex plugin manifest
├── skills/
│   ├── seo/SKILL.md                 # Main orchestrator
│   └── seo-*/SKILL.md               # 26 specialist workflows
├── agents/                          # 24 Codex TOML agent profiles
├── scripts/                         # Deterministic runners and API helpers
├── extensions/
│   ├── dataforseo/                  # DataForSEO MCP setup and docs
│   ├── firecrawl/                   # Firecrawl MCP setup and docs
│   └── banana/                      # Gemini/nanobanana image generation setup
├── hooks/                           # Quality-gate hooks
├── schema/                          # Schema.org templates
├── docs/                            # Architecture, commands, installation, MCP, demo
└── tests/                           # Contract and workflow tests

Design principles:

  • skills/ is the source of truth.
  • skills/seo/SKILL.md routes natural-language SEO requests.
  • TOML agents are Codex-native and mirror specialist workflows.
  • Runtime credentials stay in ~/.config/codex-seo/ or ~/.codex/settings.json.
  • Legacy claude-seo config/cache paths are read only as migration fallback.

More detail: docs/ARCHITECTURE.md.

Verification

Local release gate:

python -m pytest tests/
bash -n install.sh uninstall.sh
python -m compileall -q scripts hooks
python scripts/run_api_smoke_suite.py https://example.com --json

PowerShell parse check:

$files = Get-ChildItem -Recurse -Filter *.ps1
foreach ($f in $files) {
  $tokens = $null
  $errs = $null
  [System.Management.Automation.Language.Parser]::ParseFile($f.FullName, [ref]$tokens, [ref]$errs) > $null
  if ($errs.Count) { $errs; exit 1 }
}

Current GitHub CI runs:

  • dependency install
  • shell syntax checks
  • Python compile checks
  • --help checks for runner scripts
  • python -m pytest tests/
  • contract smoke checks for MCP-aware workflows

Requirements

  • Codex CLI with local skills support
  • Python 3.10+
  • Git
  • Optional: Playwright Chromium for screenshots and PDF reports
  • Optional: DataForSEO account for live SEO data
  • Optional: Google API credentials for PageSpeed/CrUX/GSC/GA4
  • Optional: Firecrawl API key for JS-rendered crawling
  • Optional: Google AI API key for Gemini/nanobanana image generation

Credentials And Cache

Codex SEO writes new local credentials and state to Codex-specific paths:

  • ~/.codex/settings.json for MCP server configuration
  • ~/.config/codex-seo/ for API configs and cost ledgers
  • ~/.cache/codex-seo/ for runtime caches
  • .seo-cache/ inside the active project for cross-skill summaries

Legacy ~/.config/claude-seo/ and ~/.cache/claude-seo/ paths are read only as migration fallback. Do not commit .seo-cache/, output/, .mcp.json, .env, OAuth tokens, service accounts, or provider keys.

Security

  • URL-aware scripts block private, loopback, reserved, multicast, unspecified, and metadata hosts.
  • Credential setup writes outside tracked repo files.
  • Sensitive local settings are expected to use 0600 file permissions.
  • DataForSEO calls use cost guardrails through scripts/dataforseo_costs.py.
  • Report vulnerabilities through SECURITY.md.

Uninstall

bash uninstall.sh

Windows:

powershell -ExecutionPolicy Bypass -File .\uninstall.ps1

Contributing

Use CONTRIBUTING.md for local setup and validation, CODE_OF_CONDUCT.md for project standards, SECURITY.md for vulnerability reporting, and CREDITS.md for project credits. Agent-facing project context is also available in llms.txt.

Related Projects

Credits

Special thanks to avalonreset for making the Codex conversion possible and for creating the initial Codex SEO version that this repository builds on.

Attribution

Original project and concept by AgriciDaniel in claude-seo. This Codex port preserves upstream SEO capabilities and adapts the runtime for Codex skills, TOML agents, plugin discovery, cache sharing, MCP extension setup, and API-safe wrappers.

Codex SEO is released under the MIT License. FLOW prompt references retain their upstream attribution and licensing notices where included.

内容与创作

低风险

  • 来源需自行核对维护者身份。
  • 包含脚本或命令调用,安装前请复核。
  • 未检测到明显外部权限要求。
  • 未检测到高风险命令。
  • 扫描发现:0 条。

Codex — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/AgriciDaniel/codex-seo.git
  3. 将 "skills/seo-sxo" 文件夹复制到 Codex 的 skills 目录中。
  4. 重启 Codex 让新的 skill 生效。

Codex — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Codex 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Codex 让新的 skill 生效。

Claude Code — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/AgriciDaniel/codex-seo.git
  3. 将 "skills/seo-sxo" 文件夹复制到 Claude Code 的 skills 目录中。
  4. 重启 Claude Code 让新的 skill 生效。

Claude Code — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Claude Code 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Claude Code 让新的 skill 生效。

Cursor — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/AgriciDaniel/codex-seo.git
  3. 将 "skills/seo-sxo" 文件夹复制到 Cursor 的 skills 目录中。
  4. 重启 Cursor 让新的 skill 生效。

Cursor — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Cursor 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Cursor 让新的 skill 生效。

GitHub Copilot — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/AgriciDaniel/codex-seo.git
  3. 将 "skills/seo-sxo" 文件夹复制到 GitHub Copilot 的 skills 目录中。
  4. 重启 GitHub Copilot 让新的 skill 生效。

GitHub Copilot — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 GitHub Copilot 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 GitHub Copilot 让新的 skill 生效。

Windsurf — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/AgriciDaniel/codex-seo.git
  3. 将 "skills/seo-sxo" 文件夹复制到 Windsurf 的 skills 目录中。
  4. 重启 Windsurf 让新的 skill 生效。

Windsurf — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Windsurf 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Windsurf 让新的 skill 生效。
查看 SKILL.md 原文
name: seo-sxo
description: >
  Search Experience Optimization: reads Google SERPs backwards to detect page-type
  mismatches, derives user stories from search intent signals, and scores pages
  from multiple persona perspectives. Identifies why well-optimized pages fail
  to rank by analyzing what Google rewards for each keyword. Use when user says
  "SXO", "search experience", "page type mismatch", "SERP analysis", "user story",
  "persona scoring", "why isn't my page ranking", "intent mismatch", or "wireframe".
user-invokable: true
argument-hint: "<url> [keyword]"
license: MIT
metadata:
  author: AgriciDaniel
  original_author: "Florian Schmitz (Pro Hub Challenge)"
  version: "1.9.6"
  category: seo

Search Experience Optimization (SXO)

Shared Data Cache

Step 0 -- Check shared data cache:

Before gathering, check .seo-cache/ for reusable context from related SEO skills. Reference: ../seo/references/shared-data-cache.md for schemas and dependency map.

Check these cache files when present:

  • .seo-cache/site-meta.json for domain, business type, industry, and crawl context

  • .seo-cache/audit-scores.json for prior full-audit priorities

  • .seo-cache/pages/{url-slug}/page-analysis.json for page-level context when a URL is provided

  • If found: parse and use clearly valid fields (note "Using cached [X] from [date]")

  • If missing, corrupt, or irrelevant: continue with fresh evidence

  • If the user says "refresh" or "re-run": ignore cache reads and overwrite on write

SXO bridges the gap between SEO (what Google rewards) and UX (what users need). Traditional SEO audits check technical health. SXO asks: "Does this page deserve to rank for this keyword based on what Google is actually rewarding in the SERP?"

Core Insight

A page can score 95/100 on technical SEO and still fail to rank because it is the wrong page type for the keyword. If Google shows 8 product pages and 2 comparison pages for your keyword, your blog post will never break through -- no matter how well-optimized it is.

Commands

CommandPurpose
/seo sxo <url>Full SXO analysis (auto-detect keyword from page)
/seo sxo <url> <keyword>Full SXO analysis for a specific keyword
/seo sxo wireframe <url>Generate IST/SOLL wireframe with concrete placeholders
/seo sxo personas <url>Persona-only scoring (skip SERP analysis)

Execution Pipeline

Step 1: Target Acquisition

  1. Fetch the target URL via scripts/fetch_page.py (SSRF-safe)
  2. Parse with scripts/parse_html.py to extract: title, H1, meta description, headings hierarchy, word count, schema markup, CTAs, media elements
  3. If no keyword provided, extract primary keyword from title tag + H1 overlap
  4. Validate keyword is non-empty before proceeding

Step 2: SERP Backwards Analysis

Read references/page-type-taxonomy.md for classification rules.

  1. Search Google for the target keyword (WebSearch)
  2. For each of the top 10 organic results, record:
    • URL and domain authority tier (brand / niche authority / unknown)
    • Page type (classify using taxonomy)
    • Content format (long-form, listicle, how-to, comparison, tool, video)
    • Word count estimate (from snippet length and page structure)
    • Schema types present (from SERP features: ratings, FAQ, HowTo)
    • Media signals (video carousel, image pack, thumbnail presence)
  3. Record SERP features present:
    • Featured snippet (paragraph / list / table / video)
    • People Also Ask (extract all visible questions)
    • Ads (top and bottom -- count and analyze ad copy themes)
    • Related searches (extract all)
    • Knowledge panel / local pack / shopping results
    • AI Overview presence and source types
  4. Calculate SERP consensus:
    • Dominant page type (>60% = strong consensus, 40-60% = mixed, <40% = fragmented)
    • Content depth expectations (average word count tier)
    • Schema expectation (most common structured data types)
    • Media expectations (video required? images critical?)

Step 3: Page-Type Mismatch Detection

This is the core SXO insight. Compare target page type against SERP consensus.

Mismatch severity levels:

Target TypeSERP ExpectsSeverityRecommendation
Blog PostProduct PagesCRITICALCreate dedicated product page
Blog PostComparisonHIGHRestructure as comparison with matrix
ProductInformationalHIGHAdd educational content layer
Landing PageTool/CalculatorHIGHBuild interactive tool component
Service PageLocal ResultsMEDIUMAdd location signals + local schema
Any type match-ALIGNEDFocus on content depth and UX

Classification rules:

  • Classify target page using references/page-type-taxonomy.md
  • Classify each SERP result using the same taxonomy
  • Flag mismatch if target type differs from SERP dominant type
  • If SERP is fragmented (no dominant type), note opportunity for differentiation

Step 4: User Story Derivation

Read references/user-story-framework.md for the full framework.

From SERP signals, derive user stories:

  1. PAA questions reveal knowledge gaps and concerns
  2. Ad copy themes reveal commercial triggers and value propositions
  3. Related searches reveal the search journey (what comes before/after)
  4. Featured snippet format reveals the expected answer structure
  5. AI Overview reveals what Google considers the definitive answer

For each signal cluster, generate a user story:

As a [persona derived from signal],
I want to [goal derived from query intent],
because [emotional driver from ad copy / PAA tone],
but I'm blocked by [barrier derived from PAA questions / related searches].

Generate 3-5 user stories covering the primary intent angles.

Step 5: Gap Analysis

Compare the target page against SERP expectations across 7 dimensions:

DimensionWhat to CompareScore
Page TypeTarget type vs SERP dominant type0-15
Content DepthWord count, heading depth, topic coverage0-15
UX SignalsCTA clarity, above-fold content, mobile layout0-15
Schema MarkupPresent vs expected structured data types0-15
Media RichnessImages, video, interactive elements vs SERP norm0-15
Authority SignalsE-E-A-T markers, social proof, credentials0-15
FreshnessLast updated, date signals, content recency0-10

Total: 0-100 SXO Gap Score (lower = larger gap, higher = better alignment)

Step 6: Persona-Based Scoring

Read references/persona-scoring.md for methodology.

  1. Derive 4-7 personas from SERP intent signals:
    • Cluster PAA questions by theme
    • Segment ad copy by target audience
    • Map related searches to journey stages
  2. For each persona, score the target page on 4 dimensions (25 pts each):
    • Relevance: Does the page address this persona's need?
    • Clarity: Can this persona find their answer within 10 seconds?
    • Trust: Are there adequate trust signals for this persona?
    • Action: Is there a clear next step for this persona?
  3. Output persona cards with scores and specific improvement recommendations
  4. Sort recommendations by weakest persona first (biggest opportunity)

Step 7: Wireframe Generation (Optional)

Only execute when /seo sxo wireframe is invoked.

Read references/wireframe-templates.md for templates.

  1. Generate IST (current state) wireframe from parsed page structure
  2. Generate SOLL (target state) wireframe based on:
    • SERP consensus page type
    • Gap analysis findings
    • Persona scoring weaknesses
  3. Use ultra-concrete placeholders:
    • NOT: "Add a CTA here"
    • YES: "Add pricing CTA with annual savings badge below hero, linking to /pricing#enterprise"
  4. Output as semantic HTML section outline with annotations

DataForSEO Integration

If DataForSEO MCP tools are available:

  1. Before any API call, run cost estimate and confirm with user
  2. Use google_organic_serp for precise SERP data (positions, features, snippets)
  3. Use keyword_data for search volume and competition metrics
  4. Fall back to WebSearch if DataForSEO unavailable -- note reduced precision in output

SXO Score vs SEO Health Score

The SXO score is separate from the main SEO Health Score.

  • SEO Health Score = technical compliance (crawlability, speed, schema, etc.)
  • SXO Gap Score = alignment between page and SERP expectations
  • A page can score 95 SEO + 30 SXO = technically perfect but strategically misaligned
  • Both scores should be reported together when both are available

Cross-Skill References

FindingHand Off To
E-E-A-T gaps in persona scoring/seo content for deep E-E-A-T audit
Missing schema types/seo schema for generation
Local intent detected in SERP/seo local for GBP analysis
Content depth gaps/seo page for deep page analysis
Technical issues found during fetch/seo technical for full audit
Image/media gaps/seo images for optimization

Output Format

Full SXO Analysis

## SXO Analysis: [URL]
### Target Keyword: [keyword]

### 1. SERP Landscape
- Dominant page type: [type] ([confidence]% consensus)
- SERP features: [list]
- Content depth norm: [word count range]
- Schema expectation: [types]

### 2. Page-Type Alignment
- Your page type: [type]
- SERP expects: [type]
- Verdict: [ALIGNED | MISMATCH (severity)]
- Impact: [explanation]

### 3. User Stories (derived from SERP signals)
[3-5 user stories with source signals]

### 4. Gap Analysis (SXO Score: XX/100)
[7-dimension breakdown table]

### 5. Persona Scores
[4-7 persona cards with 4-dimension scores]

### 6. Priority Actions
[Ranked list: fix mismatch first, then weakest persona gaps]

### 7. Limitations
[What could not be assessed, data source notes]

Error Handling

ErrorAction
URL fetch failsReport error, suggest checking URL accessibility
No keyword provided or detectedAsk user to provide target keyword
WebSearch returns <5 resultsProceed with available data, note limited sample
SERP has no organic results (all ads)Note highly commercial SERP, analyze ad copy only
Target page is JavaScript-renderedNote limitation, use available HTML content
DataForSEO cost exceeds thresholdFall back to WebSearch, notify user

Quality Checklist

Before delivering results, verify:

  • Target URL was fetched via scripts/fetch_page.py (not raw curl/fetch)
  • Page type classification uses taxonomy from references
  • At least 5 SERP results were analyzed
  • User stories cite specific SERP signals as evidence
  • Persona scores include concrete improvement suggestions
  • SXO score is clearly labeled as separate from SEO Health Score
  • Limitations section is present and honest
  • Cross-skill recommendations are included where relevant

Write to shared data cache

After completing all work, write a concise JSON summary to .seo-cache/ when the workflow produced durable findings. Use the schemas and naming rules in ../seo/references/shared-data-cache.md; include at least cache_type, analyzed_at, source URL/domain, key findings, issues, recommendations, and tool limitations. Add .seo-cache/ to .gitignore if it is missing.

发现问题?提交给管理员复核

评分:

评论 (0)

暂无评论,成为第一个评论者吧!