seo-specialist
Skill do Especialista SEO para otimização de páginas e sistemas para motores de busca tradicionais e também para otimização para ser citado por LLMs (ChatGPT, Claude, Perplexity, Google AI Overviews). Use quando precisar otimizar meta tags, Open Graph, sitemap, schema markup, Core Web Vitals, performance, imagens, fontes, acessibilidade para SEO, ou qualquer decisão de ranqueamento e citação por motores generativos. Trigger em: "SEO", "meta tags", "Open Graph", "sitemap", "schema markup", "Core Web Vitals", "performance", "LCP", "CLS", "ranking", "canonical", "robots.txt", "GEO", "AEO", "Answer Engine", "LLM citation", "AI Overview", "llms.txt", "generative engine optimization", "answer engine optimization".
60
71%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/14-seo-specialist/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its domain (SEO for both traditional and generative search engines), lists specific concrete capabilities, and provides explicit trigger guidance with a comprehensive list of natural keywords. The description effectively differentiates itself from general web development or performance skills by anchoring on SEO-specific terminology and the emerging generative engine optimization space.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: optimizing meta tags, Open Graph, sitemap, schema markup, Core Web Vitals, performance, images, fonts, accessibility for SEO, and ranking/citation decisions for generative engines. | 3 / 3 |
Completeness | Clearly answers both 'what' (SEO optimization for traditional and generative engines, with specific capabilities listed) and 'when' (explicit 'Use quando precisar...' clause and a dedicated 'Trigger em:' list with specific keywords). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say, including both traditional SEO terms ('SEO', 'meta tags', 'sitemap', 'robots.txt', 'canonical') and emerging generative AI terms ('GEO', 'AEO', 'LLM citation', 'AI Overview', 'llms.txt'). Covers common abbreviations and variations. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around SEO and generative engine optimization with highly specific trigger terms like 'schema markup', 'Core Web Vitals', 'LLM citation', 'GEO', 'AEO' that are unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at actionability with complete, executable code examples and thorough checklists covering traditional SEO and GEO/AEO. However, it is severely bloated — at 400+ lines it explains many concepts Claude already knows (semantic HTML basics, what E-E-A-T means, what Core Web Vitals measure) and inlines content that should be in separate referenced files. The lack of a clear sequenced workflow and the monolithic structure significantly reduce its effectiveness as a skill document.
Suggestions
Extract the bulk content (schema templates, semantic HTML reference, GEO/AEO deep guide, code examples) into separate referenced files like `seo-schemas.md`, `seo-geo-aeo.md`, and `seo-code-templates.md`, keeping SKILL.md as a concise overview with navigation links.
Remove explanations of concepts Claude already knows — delete the Core Web Vitals description column, the E-E-A-T acronym expansion, the semantic HTML reference table, and the prose explaining what GEO/AEO is. Just state the rules and patterns.
Add an explicit sequenced workflow with validation checkpoints, e.g.: 1. Audit current page → 2. Implement meta tags → 3. Validate with Rich Results Test → 4. Run Lighthouse → 5. Fix issues → 6. Re-validate → 7. Handoff to QA.
Cut the 'good vs bad' examples in GEO section and the verbose explanations (e.g., 'LLMs como ChatGPT, Claude, Perplexity e Google AI Overviews viraram a primeira camada...') — state the pattern directly without motivation paragraphs.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It explains concepts Claude already knows (what Core Web Vitals are, what semantic HTML is, what E-E-A-T stands for), includes a full semantic HTML reference table that's basic knowledge, and has extensive prose explaining GEO/AEO concepts rather than just providing actionable patterns. Many sections could be 50-70% shorter. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste-ready TypeScript/JavaScript code for meta tags, schema markup, optimized images, fonts, lazy loading, and third-party scripts. Code examples are complete with proper imports, types, and realistic configurations. The checklists are concrete and specific. | 3 / 3 |
Workflow Clarity | The handoff sections define clear inputs/outputs and the checklists provide verification steps, but there's no explicit sequenced workflow with validation checkpoints for the overall SEO optimization process. The skill reads more as a reference document than a step-by-step workflow. Missing feedback loops for validation (e.g., run Lighthouse → fix issues → re-run). | 2 / 3 |
Progressive Disclosure | The skill is a monolithic wall of text with everything inline. It references `docs/skill-guides/seo-specialist.md` for templates but then includes all templates inline anyway. The semantic HTML reference, full GEO/AEO guide, all schema examples, and all code templates are crammed into one file when they should be split into referenced sub-files. No bundle files are provided to support the references mentioned. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (596 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- felvieira/claude-skills-fv
- Commit
7577622
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.