convez.ai
SkillMarketing & VendasIntermediário
JeffLi1993

SEO Audit Skill

JeffLi1993/seo-audit-skill

Auditoria SEO automatizada com Python + LLM em relatórios HTML

Ver no GitHub
BomPluginScore · de 0 a 100

Skill reutilizável para auditoria SEO de páginas individuais que combina scripts Python determinísticos com avaliação semântica via LLM. Gera relatórios HTML estruturados com achados acionáveis, cobrindo desde crawlability e canonicalização até análise de conteúdo e Core Web Vitals.

Instalação

$npx convez-ai JeffLi1993/seo-audit-skill

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
789
Forks
102
Acompanhando
2
Saúde
42%
Último commit
há 5 meses
Versão
—
Issues abertas
1
Contribuidores
1

Casos de uso

  • Auditar saúde SEO técnica de páginas antes de publicação
  • Identificar problemas de canonicalização, robots.txt e schema markup
  • Gerar relatórios estruturados com priorização de correções de impacto

Veredito

Ferramenta prática e bem arquiteturada para SEO técnico em escala. A combinação de checks determinísticos (Python) + semânticos (LLM) resolve bem o problema real de auditoria. Útil para profissionais de SEO e time de produto que precisam validar saúde antes de deploy.

README

A tradução para o português deste README ainda está na fila.

seo-audit-skill

English · 中文 · SEO Audit Agent Skill

Reusable Agent Skills for single-page SEO auditing. Give it a URL — get a structured HTML report with actionable findings.

Built on a Script + LLM two-layer architecture: Python scripts handle deterministic checks (HTTP status, XML parsing, string matching), while the LLM handles semantic judgment (keyword intent, content quality, page type inference). Works with Claude Code, Cursor, and any agent runtime that supports SKILL.md.

Best practices

  1. Run npx skills add JeffLi1993/seo-audit-skill, then audit your page (for example: audit this page: https://example.com). Open the report at reports/<hostname>-audit.html and review it yourself: keep what matters for your goals, skip what does not.
  2. Share the report (or the key sections) with Cursor or Claude Code and have the assistant work through the findings and fixes item by item.

Report Output

Each audit produces a standalone HTML report saved to reports/<hostname>-audit.html.

SectionWhat you get
Audit SummaryOne-line verdict + critical / warnings / passing at a glance
Site ChecksCrawlability · URL Canonicalization · i18n · Schema · E-E-A-T
Page ChecksPageSpeed · TDK · H1 · Headings · Word Count · Internal Links
Priority ActionsTop 3 highest-impact fixes, ranked
Insight WalkthroughEvidence → Impact → Fix for each major finding
audit this page: https://openclaw.ai
→ ✅ Report saved → reports/openclaw-ai-audit.html
WebsiteAudit SummarySite ChecksPage Checks & insights
colaos.ai

Skills

SkillTierWhen to use
seo-auditBasicDefault — give it a URL, get a 20+ check structured report
seo-audit-fullFullDeep: Core Web Vitals, content quality, GSC data, competitor gap

Audit Coverage

Site-level

CheckWhat it verifiesBasicFull
robots.txtRFC 9309 group parsing, Allow/Disallow logic, Googlebot status, Sitemap directives✅✅
sitemap.xmlValid XML, URL count, follows Sitemap directive path from robots.txt✅✅
404 HandlingTrue 404 vs soft 404 (200) vs redirect-to-homepage (301)✅✅
URL CanonicalizationHTTP→HTTPS redirect, www consistency, trailing slash, canonical tag match✅✅
i18n / hreflangReciprocal symmetry, BCP 47 codes, x-default, URL path structure✅✅
Schema (JSON-LD)@type detection, required fields, @graph flattening, type conflict check✅✅
E-E-A-T Trust PagesAbout / Contact / Privacy / Terms — exists (HTTP 200) + reachable from footer/nav✅✅
GSC Crawl StatusIndex coverage, crawl errors, blocked resources—✅
Core Web VitalsLCP, CLS, INP from CrUX field data—✅

Page-level

CheckWhat it verifiesBasicFull
URL SlugLowercase, hyphenated, keyword present, stop word & stuffing detection✅✅
Title Tag50–60 chars, keyword position, homepage vs inner page rules✅✅
Meta Description120–160 chars, keyword match, concrete value prop (not generic fluff)✅✅
H1 TagSingle H1, keyword match (full / partial / none), semantic intent review✅✅
Canonical TagSelf-referencing, matches final URL after redirects✅✅
Image Alt TextAlt attribute check on all <img>, JS-render detection✅✅
Word CountBody text ≥ 500 words, thin content flag✅✅
Keyword PlacementPrimary keyword within first 100 body words✅✅
Heading StructureH2 count (target 5–7), H3/H2 ratio, keyword distribution in H2s✅✅
Internal LinksSame-origin links (excl. nav/footer), equity distribution✅✅
OG / Social Tagsog:image, twitter:card, social preview completeness—✅
Content QualityE-E-A-T depth, readability, specificity vs competitors—✅
Robots Metanoindex, nofollow, max-snippet directives—✅

Structure

seo-audit-skill/
├── seo-audit/
│   ├── SKILL.md                       # Skill definition + agent workflow
│   ├── references/REFERENCE.md        # Field definitions, edge cases
│   ├── assets/report-template.html    # HTML output template
│   └── scripts/
│       ├── check-site.py              # robots.txt + sitemap → JSON
│       ├── check-page.py              # TDK + H1 + canonical + slug → JSON
│       ├── check-schema.py            # JSON-LD extraction + validation → JSON
│       └── fetch-page.py              # Raw HTML fetcher, SSRF protection
└── seo-audit-full/
    ├── SKILL.md
    ├── references/REFERENCE.md
    ├── assets/report-template.html
    └── scripts/
        └── check-social.py            # OG + Twitter Card validation → JSON

Architecture: Script + LLM

URL
 │
 ▼
┌──────────────────────────────────────────────────┐
│  Layer 1 · Python Scripts                        │
│  Deterministic checks → structured JSON          │
│                                                  │
│  check-site.py      robots.txt, sitemap (RFC 9309)
│  check-page.py      H1 / title / meta / canonical│
│  check-schema.py    JSON-LD @type + field valid. │
│  fetch-page.py      raw HTML + SSRF protection   │
└───────────────────────┬──────────────────────────┘
                        │ JSON + llm_review_required flag
                        ▼
┌──────────────────────────────────────────────────┐
│  Layer 2 · LLM Agent                             │
│  Semantic judgment on flagged fields only         │
│                                                  │
│  · Keyword intent alignment (H1 / title)         │
│  · Meta description quality & specificity        │
│  · Page type → expected Schema @type mapping     │
│  · E-E-A-T trust page reachability (footer/nav)  │
│  · Content analysis (word count, heading, links) │
└───────────────────────┬──────────────────────────┘
                        │
                        ▼
              report-template.html
              → reports/<hostname>-audit.html

Why two layers? Scripts handle the 80% of checks that are deterministic — does robots.txt exist? Is the title 55 characters? The LLM handles the 20% that require understanding — does this H1 semantically cover the intent of "AI workflow automation"? The llm_review_required flag ensures the LLM only intervenes when the script explicitly cannot make the call. No hallucination on factual checks, no blind spots on semantic ones.


Installation

Option 1: CLI (Recommended)

npx skills add JeffLi1993/seo-audit-skill

# Or install a specific tier
npx skills add JeffLi1993/seo-audit-skill --skill seo-audit
npx skills add JeffLi1993/seo-audit-skill --skill seo-audit-full

Option 2: Claude Code Plugin

/plugin marketplace add JeffLi1993/seo-audit-skill
/plugin install seo-audit-skill

Usage

audit this page: https://example.com

Scripts

All scripts output structured JSON to stdout. Exit code 0 = pass/warn, 1 = any fail.

ScriptWhat it does
check-site.pyrobots.txt + sitemap — RFC 9309 group parsing, Allow override, multi-Sitemap path
check-page.pyH1 / title / meta / canonical / URL slug — keyword match with stop-word-aware filter
check-schema.pyJSON-LD extraction, @graph flattening, @type + required field validation
fetch-page.pyRaw HTML fetch — SSRF protection, redirect chain tracking, Googlebot UA option

Dependency: pip install requests


License

MIT

Ver o original no GitHub

Bom para

Relacionados