Agentic-SEO-Skill
An LLM-first, agentic SEO analysis skill for Antigravity, Claude Code, and Codex. It orchestrates multiple specialist sub-skills (technical SEO, content/E-E-A-T, performance/CWV, schema, sitemap, visual checks, links, GEO/AEO, entity SEO, hreflang, programmatic safeguards, plus GitHub repo SEO/benchmarking) to collect evidence from target URLs (and optionally run verification scripts) and generate structured audit outputs and prioritized action plans.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
README describes use of environment variables for GitHub tokens but does not document secret logging/redaction practices, secure storage, or fine-grained scoping. The tool performs external URL fetching and (optionally) browser-based checks; this increases exposure to untrusted HTML/JS during crawling/rendering and heightens the importance of sandboxing and safe error handling. No information is provided about dependency scanning, pinned versions, or CVE management.
⚡ Reliability
Best When
You want an evidence-based, multi-signal SEO audit driven by an LLM inside an IDE/agent environment, and you can provide/allow URL crawling and optional API credentials (e.g., GitHub/GSC).
Avoid When
You need a strict, standardized API product (REST/SDK) for programmatic integration, or you require guaranteed error handling/idempotency guarantees and observability typical of production SaaS.
Use Cases
- • Run full technical/content/schema/performance SEO audits for a website
- • Deep-dive analysis of a single URL or blog post (metadata, headings, schema, readability, CWV-oriented checks)
- • Validate and generate schema.org JSON-LD
- • Audit sitemap quality and crawl/indexability-related signals
- • Assess GEO (AI crawler readiness) and AEO (featured snippet / snippet targeting) signals
- • Perform hreflang/i18n validation
- • Audit image SEO (alt text, formats, lazy loading, CLS-related signals)
- • Analyze internal link structure and broken links
- • Generate GitHub repository SEO reports and action plans (metadata/topics/README/community/benchmarking/archiving)
- • Optional: use GSC/GitHub credentials for deeper checks (where supported by scripts)
Not For
- • A managed, hosted SEO service (it appears to be a local/IDE skill with scripts)
- • Real-time SEO monitoring with guaranteed uptime/SLA
- • Use as a compliance/legal decision tool for regulated content (it provides SEO guidance, not legal advice)
- • Environments where running headless browsers (Playwright) or crawling external sites is disallowed
Interface
Authentication
Authentication is described mainly for GitHub-related scripts (token or gh CLI). The README mentions GSC data requiring credentials but does not specify the auth method, scopes, or how secrets are stored/handled.
Pricing
No pricing described; appears to be open-source/local usage. Costs depend on LLM usage and any external services (e.g., crawling, PageSpeed/Lighthouse, Playwright).
Agent Metadata
Known Gotchas
- ⚠ Skill auto-triggers on SEO keywords; agents may inadvertently run heavy crawl/browser workflows.
- ⚠ Some checks imply external fetching/crawling and optional headless browsing (Playwright), which can be slow and may fail on blocked/complex sites.
- ⚠ Credential-dependent scripts (GitHub/GSC) may behave differently depending on environment variables vs gh CLI setup.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for Agentic-SEO-Skill.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.