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。
Codex-first SEO analysis suite with 1 orchestrator skill, 26 specialist workflows, 24 TOML agent...
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。
来源文件:README.md
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.
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.
v1.9.6-codex.5.v1.9.6-codex.5.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.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
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.
CODEX_HOME=~/.codex \
CODEX_SEO_REPO=https://github.com/AgriciDaniel/codex-seo \
CODEX_SEO_REF=v1.9.6-codex.5 \
bash install.sh
| Variable | Purpose |
|---|---|
CODEX_HOME | Alternate Codex home. Defaults to ~/.codex. |
CODEX_SEO_REPO | Git URL, fork URL, or local repository path. |
CODEX_SEO_REF | Branch, tag, or commit. Defaults to v1.9.6-codex.5. |
CODEX_SEO_SKIP_PLAYWRIGHT_BROWSER=1 | Skip Chromium install for visual/PDF workflows. |
CODEX_SEO_PLAYWRIGHT_WITH_DEPS=1 | Ask Playwright to install system dependencies where supported. |
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"
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
| Prompt | Purpose |
|---|---|
/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.
%%{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
%%{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
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.| Extension | Skill | Setup | Notes |
|---|---|---|---|
| DataForSEO | seo-dataforseo, seo-maps, seo-ecommerce, seo-cluster | ./extensions/dataforseo/install.sh | Live SERP, keyword, backlinks, on-page, content, business data, AI visibility |
| Google APIs | seo-google, seo-performance | python scripts/google_auth.py --setup | PageSpeed, CrUX, GSC, URL Inspection, Indexing API, GA4 |
| Firecrawl | seo-firecrawl | ./extensions/firecrawl/install.sh | JS-rendered crawl, scrape, site map |
| Banana / Gemini | seo-image-gen | ./extensions/banana/install.sh | AI 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
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
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.~/.config/codex-seo/ or ~/.codex/settings.json.claude-seo config/cache paths are read only as migration fallback.More detail: docs/ARCHITECTURE.md.
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:
--help checks for runner scriptspython -m pytest tests/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 summariesLegacy ~/.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.
0600 file permissions.scripts/dataforseo_costs.py.bash uninstall.sh
Windows:
powershell -ExecutionPolicy Bypass -File .\uninstall.ps1
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.
claude-seo - original Claude Code SEO skill suiteclaude-blog - blog creation and optimization skill ecosystemclaude-ads - paid advertising audit skill suiteflow - evidence-led SEO framework for AI searchwp-mcp-ultimate - WordPress MCP serverSpecial thanks to avalonreset for making the Codex conversion possible and for creating the initial Codex SEO version that this repository builds on.
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.
name: seo-local
description: >
Local SEO analysis covering Google Business Profile optimization, NAP
consistency, citation health, review signals, local schema markup,
location page quality, multi-location SEO, and industry-specific
recommendations. Detects business type (brick-and-mortar, SAB, hybrid)
and industry vertical (restaurant, healthcare, legal, home services,
real estate, automotive). Use when user says "local SEO", "Google
Business Profile", "GBP", "map pack", "local pack", "citations",
"NAP consistency", "local rankings", "service area", "multi-location",
or "local search".
user-invokable: true
argument-hint: "[url]"
license: MIT
metadata:
author: AgriciDaniel
version: "1.9.6"
category: seoStep 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
| Metric | Value | Source |
|---|---|---|
| GBP signals share of local pack weight | 32% | Whitespark 2026 |
| Proximity share of ranking variance | 55.2% | Search Atlas ML study |
| Review signals share (up from 16%) | ~20% | Whitespark 2026 |
| Google searches seeking local info | 46% | Industry data |
| Mobile "near me" searches leading to visit in 24h | 76% | Google confirmed |
| ChatGPT/AI usage for local recommendations | 45% (up from 6%) | BrightLocal LCRS 2026 |
| ChatGPT local conversion rate | 15.9% | Seer Interactive |
| Google organic local conversion rate | 1.76% | Seer Interactive |
| Local pack ads growth (Jan 2025 to Jan 2026) | 1% to 22% | Sterling Sky |
Detect from page signals before analysis. This determines which checks apply.
areaServed in schema without address.streetAddressImpact on checks: SABs skip embedded map verification and physical address consistency. Brick-and-mortar gets full NAP + map checks.
Detect from page signals and GBP category patterns. Routes to industry-specific checks from references/local-schema-types.md.
| Vertical | Detection Signals |
|---|---|
| Restaurant | /menu, menu items, reservations, cuisine types, food ordering, "dine-in", "takeout" |
| Healthcare | insurance accepted, patients, appointments, NPI, medical terms, "Dr.", HIPAA notice |
| Legal | attorney, lawyer, practice areas, bar admission, case results, "free consultation" |
| Home Services | service area, emergency service, "free estimate", licensed/insured/bonded, "24/7" |
| Real Estate | listings, MLS, properties for sale/rent, agent bio, brokerage, "open house" |
| Automotive | inventory, VIN, test drive, dealership, service department, "new/used/certified" |
If no vertical detected, use generic LocalBusiness analysis path.
Primary category is the single most important local pack factor (Whitespark #1, score: 193). Incorrect primary category is the #1 negative factor (score: 176).
Check for:
Scoring guide:
Review velocity matters more than total count. The 18-day rule (Sterling Sky): rankings cliff if no new reviews for 3 weeks.
Check for:
aggregateRating in schema (ratingValue, reviewCount, bestRating)Industry-specific:
Scoring guide:
Dedicated service pages = #1 local organic factor AND #2 AI visibility factor (Whitespark 2026).
Check for:
tel: link) and contact form above the foldMulti-location specific:
domain.com/locations/city-name/ (subdirectories consolidate link equity better, Bruce Clay: 50%+ traffic lift)@idScoring guide:
Citations declining for traditional pack rankings but 3 of top 5 AI visibility factors are citation-related (Whitespark 2026). Google's July 2025 documentation update removed "directories" from prominence definition.
Check for:
site:yelp.com "Business Name"site:bbb.org "Business Name"references/local-schema-types.md for per-vertical citation sourcesScoring guide:
Schema is NOT a direct ranking factor (John Mueller confirmed). But enables rich results (43% CTR increase, Webstix case study) and helps AI systems parse business information.
Check for:
name, address with PostalAddress sub-propertiesgeo (minimum 5 decimal places, Confirmed), openingHoursSpecification, telephone, url, priceRange (<100 chars), image, aggregateRatingreferences/local-schema-types.md:
Restaurant not generic LocalBusinessLegalService not deprecated AttorneyAutoDealer not deprecated VehicleListingMedicalClinic/Hospital/Dentist not generic MedicalBusinessareaServed with named cities (recommended, not in Google's official list but Schema.org supported)@id, linked via branchOf to Organization on homepagereferences/local-schema-types.md):
Scoring guide:
Links declining for local pack but remain ~26% of local organic ranking (Whitespark 2026, #2 factor group). "Best of" list placements = #1 AI visibility citation factor.
Check for:
Scoring guide:
Do not duplicate seo-geo analysis. Provide local-specific AI context and recommend /seo geo <url> for full analysis.
Key local AI facts:
Recommendation: Run /seo geo <url> for comprehensive AI search visibility analysis including citability scoring, llms.txt check, and brand mention audit.
Load on-demand as needed:
references/local-seo-signals.md: Ranking factors, review benchmarks, citation tiers, GBP feature status, algorithm updatesreferences/local-schema-types.md: LocalBusiness subtypes by industry, schema patterns, citation sources per verticalGenerate LOCAL-SEO-ANALYSIS-{domain}.md with:
geo coordinates with 5+ decimal precisiontel: link for click-to-callIf DataForSEO MCP tools are available, use local_business_data for live GBP data extraction, google_local_pack_serp for real-time local pack positions, and business_listings for automated citation auditing across directories.
| Scenario | Action |
|---|---|
| URL unreachable (DNS failure, connection refused) | Report the error clearly. Do not guess site content. Suggest the user verify the URL and try again. |
| No local signals detected on page | Report that no local business indicators were found. Suggest the user confirm this is a local business and provide the GBP listing URL if available. |
| NAP not found in page HTML | Check schema and meta tags. If still absent, flag as Critical issue. Recommend adding visible NAP to footer and contact page. |
| Industry vertical unclear | Present the top two detected verticals with supporting signals. Ask the user to confirm before applying industry-specific recommendations. |
| Multi-location with 50+ location pages | Apply the quality gates from seo orchestrator: WARNING at 30+ pages (enforce 60%+ unique), HARD STOP at 50+ pages (require user justification before continuing). |
For prompt-guided local optimization, use /seo flow local <url> — FLOW's 11 local-stage prompts cover GBP optimization, meta descriptions, title tags, and structured local audit workflows.
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.
评论 (0)
暂无评论,成为第一个评论者吧!