SEO Audit Agent
Description
Technical SEO audit agent — your AI coding assistant fetches live pages and collects facts; a deterministic engine scores them (same facts = same verdict) and writes the prioritized fix report. Claude Code, OpenCode, Codex.
Installation
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open the source below and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
README
SEO Audit Agent
**Give your AI coding assistant a job: audit my site's technical SEO, page by page — and don't stop until every priority page is checked.**
SEO Audit Agent is a tiny, open, do-it-yourself technical SEO auditor. You install it once into [Claude Code](https://claude.com/claude-code), [OpenCode](https://opencode.ai), or [Codex CLI](https://github.com/openai/codex). From then on, you just say:
*"Audit 20 pages of my site based on site.md and give me the prioritized fix report."*
…and your AI goes to work: fetching live pages from your sitemap, extracting the exact fact set (titles, meta descriptions, h1 structure, canonicals, Open Graph, image alts, structured data), recording each page through an evidence-gated engine that **scores deterministically** — same facts, same verdict, every time. Fix pages, re-audit, watch the deltas.
No accounts. No subscriptions. No black-box "site health 74/100" — you see every issue, per page, with the facts that produced it.
What you get
| 📏 Deterministic scoring | Your AI collects facts; the engine judges. Two sessions auditing the same page produce the identical score. No LLM vibes in the verdict. |
| 🚫 Scope-locked | The engine refuses any URL outside the domain declared in site.md. No drive-by audits of the wrong site. |
| ✅ Completeness gate | A page counts only when its full fact set is recorded. Partial audits are visible but don't count toward the target. |
| 🔁 Fix → re-audit → delta | reaudit replaces facts for the same page and shows the score change. Progress becomes measurable. |
| 📄 Prioritized reports | export md writes SEO-AUDIT.md: worst pages first, CRITICAL/HIGH/MEDIUM/LOW issues, explicit fix order. CSV too. |
| 🔁 Batch loop + scheduler | Resume across sessions; hands-free mode wakes your AI tool per batch. |
Install (pick ONE — both take under 2 minutes)
Option A · One terminal command
curl -fsSL https://raw
Related Skills
Fastapi Review
Review a FastAPI application for architecture, async correctness, dependency injection, Pydantic schemas, secu
Security Defense in Depth
Implement multi-layered testing and security best practices.
Security SecLists Official Repository
[OWASP Testing Guide](https://owasp.org/www-project-web-security-testing-guide/)
Security Threat Hunting with Sigma Rules
Use Sigma detection rules to hunt for threats and analyze security events
Security Maintenance Walkthrough - 2026-03-29
- Re-triaged the full 2026-03-15 security finding set against current `main` and wrote a fresh current-head re
Security Google Workspace Model Armor
Filter user-generated content for safety
Security Related Agents
Django Reviewer
Expert Django code reviewer specializing in ORM correctness, DRF patterns, migration safety, security misconfi
Token Auditor
Scans ui/src/ for hardcoded visual values, duplicate components, and shadcn replacement candidates; produces d
Gitnexus Security Boundary Reviewer
GitNexus security and trust-boundary reviewer. Use for auth, permissions, secrets, injection, unsafe parsing,