菜单
Run SEO audit (39 rules) with AI visibility checks — GEO (20 rules for AI bot access, snippet restrictions) and AEO (4 schema checks). Auto-fix included. Use when user wants to check or improve search visibility.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | seo-audit |
| description | Run SEO audit (39 rules) with AI visibility checks — GEO (20 rules for AI bot access, snippet restrictions) and AEO (4 schema checks). Auto-fix included. Use when user wants to check or improve search visibility. |
| argument-hint | <url-or-directory> |
| allowed-tools | Bash, Read, Edit, Grep, Glob |
| paths | ["**/*.html","**/index.html","**/*.htm"] |
Search optimization audit with AI visibility signals. Finds issues AND fixes them.
Run the SEO scanner on the project:
node ${CLAUDE_PLUGIN_ROOT}/tools/seo-scanner.mjs <project-directory>
Parse the JSON output for findings and scores (seo, geo, aeo).
Large sites: when a site has many pages and each needs page-specific fixes, escalate to a dynamic Workflow (describe the audit and include the word "workflow") so the scan-then-fix-then-verify pipeline runs across pages in parallel instead of one at a time.
Present findings grouped by category with severity:
For each finding, apply the appropriate fix:
SEO fixes (use Edit tool on HTML files):
<title> in <head><meta name="description" content="..."><link rel="canonical">node ${CLAUDE_PLUGIN_ROOT}/tools/sitemap-generator.mjs <dir> <url>node ${CLAUDE_PLUGIN_ROOT}/tools/robots-generator.mjs <dir> <url>GEO fixes:
node ${CLAUDE_PLUGIN_ROOT}/tools/llms-txt-generator.mjs <dir>node ${CLAUDE_PLUGIN_ROOT}/tools/structured-data-generator.mjs <dir> --type=<type>AEO fixes:
Google Search Console (requires ULTRASHIP_GSC_CREDENTIALS):
# Submit sitemap
node ${CLAUDE_PLUGIN_ROOT}/tools/gsc-client.mjs submit-sitemap <site-url> <sitemap-url>
# Check if pages are indexed
node ${CLAUDE_PLUGIN_ROOT}/tools/gsc-client.mjs inspect-url <site-url> <page-url>
# See what keywords you rank for
node ${CLAUDE_PLUGIN_ROOT}/tools/gsc-client.mjs query <site-url> 28
# List all submitted sitemaps
node ${CLAUDE_PLUGIN_ROOT}/tools/gsc-client.mjs list-sitemaps <site-url>
Bing Webmaster Tools (requires ULTRASHIP_BING_KEY):
# Submit sitemap (also powers DuckDuckGo + ChatGPT Search)
node ${CLAUDE_PLUGIN_ROOT}/tools/bing-webmaster.mjs submit-sitemap <site-url> <sitemap-url>
# Submit specific URLs for fast indexing
node ${CLAUDE_PLUGIN_ROOT}/tools/bing-webmaster.mjs submit-url <site-url> <page-url>
# Batch submit multiple URLs
node ${CLAUDE_PLUGIN_ROOT}/tools/bing-webmaster.mjs submit-url-batch <site-url> <url1> <url2> ...
# Check URL traffic
node ${CLAUDE_PLUGIN_ROOT}/tools/bing-webmaster.mjs url-info <site-url> <page-url>
If credentials are not set, show setup instructions from the tool's error output. Do NOT skip this phase — submitting sitemaps to both GSC and Bing is critical for indexing speed.
Why Bing matters for AI search: Bing's index powers ChatGPT Search, DuckDuckGo, and Yahoo. Submitting your sitemap to Bing directly improves AI search visibility.
Run content scoring on all pages:
node ${CLAUDE_PLUGIN_ROOT}/tools/content-scorer.mjs <project-directory>
For pages with a known target keyword:
node ${CLAUDE_PLUGIN_ROOT}/tools/content-scorer.mjs <project-directory> --keyword=<keyword>
Report readability scores (Flesch-Kincaid), keyword density, thin content, and GEO heading optimization.
Validate Open Graph tags and image accessibility:
node ${CLAUDE_PLUGIN_ROOT}/tools/og-validator.mjs <project-directory>
Fix missing OG tags, broken OG images, and oversized preview images.
If a production URL is available, check for redirect chains:
node ${CLAUDE_PLUGIN_ROOT}/tools/redirect-checker.mjs --sitemap=<sitemap-url>
Fix redirect chains (consolidate to single hop), convert 302s to 301s, and resolve mixed HTTP/HTTPS.
Re-run the scanner to confirm fixes and report before/after scores.
Save scores for historical comparison:
node ${CLAUDE_PLUGIN_ROOT}/tools/audit-history.mjs save <project-dir> seo <score>
node ${CLAUDE_PLUGIN_ROOT}/tools/audit-history.mjs save <project-dir> geo <score>
node ${CLAUDE_PLUGIN_ROOT}/tools/audit-history.mjs save <project-dir> aeo <score>
After technical fixes, advise on content-level optimizations that the scanner cannot automate:
GEO Content Patterns (for AI citation):
E-E-A-T Signals (for AI trust):
AI Bot Access:
Citation-Worthy Page Formats:
Key test: "If your content can't answer a question clearly in 30 seconds, AI engines won't select it for generated answers."
For SEO specialists working on client sites, provide a content audit after the technical scan:
Content Health Assessment:
Competitor Gap Analysis Guidance: After technical fixes, advise the user to:
Content Update/Consolidate/Delete Decision Framework: For each existing content page, recommend one of:
Page Speed Budget by Page Type:
Ultraship cannot check backlinks (requires paid APIs like Ahrefs/Semrush with massive crawl indexes). Instead, provide strategic guidance that a $10K/month SEO consultant would give:
Internal Link Optimization (we CAN automate): The scanner already detects orphan pages and pages with zero internal links. After fixing those:
Backlink Acquisition Strategy (guidance for user):
High-value link building tactics (ranked by ROI):
What NOT to do:
Domain Authority Monitoring (guidance for user):
Fix, don't just audit. Every finding should have a concrete fix applied. Every content page should have a strategy to be cited by AI. Every client engagement should include technical fixes + content audit + backlink strategy.
Build a regression + eval harness for AI-written code and AI features. Generates characterization tests that lock current behavior before a refactor, scaffolds a Promptfoo eval suite for chatbots/RAG/classifiers, and wires it into the ship-gate. Use when the user wants evals, regression tests for AI code, to stop AI features drifting, or to test an LLM feature.
Run security audit — dependency vulnerabilities, secret scanning, OWASP pattern detection, HTTP headers. Use when user wants to harden their project.
Accessibility audit + auto-fix (WCAG 2.2 A/AA). Scans built/static HTML for screen-reader, keyboard, and structure failures, fixes the deterministic ones, and escalates to a rendered scan for contrast and focus. Use when the user wants to check or improve accessibility, fix WCAG issues, or pass an a11y review.
Turn the /ship scorecard into a blocking, config-as-code quality gate. Sets per-category score thresholds, hard-fails on leaked secrets or critical findings, and wires the gate into a pre-push hook and CI so nothing below the bar merges. Use when the user wants a merge gate, CI quality gate, pre-push check, or to enforce ship-readiness.
Post-deploy canary monitoring — checks site health, detects regressions, monitors for errors after deployment. Use after deploying to verify production is healthy.
Code review with principal-engineer-level depth. Reviews for correctness, performance, security, maintainability, and architecture. Use when completing tasks, reviewing PRs, or before merging.