SEO and AI discovery (GEO) - schema, ChatGPT/Perplexity optimization
33
30%
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/web-content/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is essentially a topic label rather than a functional skill description. It identifies the domain (SEO and GEO) and mentions specific platforms but fails to describe concrete actions or provide explicit trigger guidance for when Claude should select this skill. It needs significant expansion to be effective in a multi-skill selection context.
Suggestions
Add explicit concrete actions such as 'Generates structured data/schema markup, optimizes content for AI citation in ChatGPT and Perplexity, audits pages for search visibility'.
Add a 'Use when...' clause with trigger terms like 'Use when the user asks about SEO, search engine optimization, structured data, schema markup, AI search visibility, generative engine optimization, or optimizing content for ChatGPT/Perplexity discovery'.
Expand the acronym GEO (Generative Engine Optimization) since not all users will know this term, and include related natural language terms like 'AI search', 'LLM visibility', 'rich snippets'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (SEO and AI discovery/GEO) and mentions some specific areas like 'schema' and 'ChatGPT/Perplexity optimization', but doesn't list concrete actions (e.g., 'generate structured data markup', 'optimize content for AI citation'). | 2 / 3 |
Completeness | Provides a partial 'what' (SEO and AI discovery optimization) but has no 'when' clause or explicit trigger guidance. The description reads more like a label than a functional description, and the missing 'Use when...' clause caps this at 2 per the rubric, but the 'what' is also weak enough to warrant a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'SEO', 'schema', 'ChatGPT', 'Perplexity', and 'GEO', which users might naturally mention. However, it's missing common variations like 'search engine optimization', 'structured data', 'rich snippets', 'AI search', 'generative engine optimization', or 'LLM visibility'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of SEO + AI discovery (GEO) + specific platforms (ChatGPT/Perplexity) provides some distinctiveness, but 'SEO' alone is broad and could overlap with general content writing or marketing skills. The mention of specific AI platforms helps narrow it somewhat. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a comprehensive but bloated reference document that tries to cover too much in a single file. Its strengths are the concrete schema JSON examples and the structured checklists, but it suffers from excessive verbosity, explaining concepts Claude already knows (SEO basics, E-E-A-T, what a homepage is), and a lack of progressive disclosure. The content would benefit enormously from being split into focused sub-files and trimmed to only novel, non-obvious guidance.
Suggestions
Split content into separate files: SCHEMAS.md (all JSON-LD examples), TEMPLATES.md (page type structures), PLATFORMS.md (ChatGPT/Perplexity/Claude/Gemini tips), and keep SKILL.md as a concise overview with links to each.
Remove explanations of concepts Claude already knows: E-E-A-T definitions, what SEO vs GEO is, basic page structure advice (put a headline, put a CTA). Focus on non-obvious patterns and specific implementation details.
Add a clear end-to-end workflow: 'Step 1: Identify page type → Step 2: Generate schema from template → Step 3: Validate with schema.org validator → Step 4: If errors, fix and re-validate → Step 5: Write content following template → Step 6: Run checklist.'
Remove time-sensitive statistics ('AI traffic grew 1,200% between July 2024 and February 2025', 'Google's search share dropped below 90%') that will become outdated and waste tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~400+ lines. It explains basic concepts Claude already knows (what SEO is, what E-E-A-T stands for, what a homepage structure looks like, how to write meta descriptions). Much of this is general web content marketing knowledge that doesn't need to be spelled out. The philosophy section, E-E-A-T breakdown, and platform-specific optimization sections are largely common knowledge for Claude. The content could be reduced by 60-70% while preserving all actionable value. | 1 / 3 |
Actionability | The skill provides concrete schema JSON examples that are copy-paste ready, HTML snippets for stat boxes and TL;DR sections, and a useful analytics tracking script. However, much of the content is template/structural guidance (e.g., 'put a headline here, put a CTA here') rather than executable instructions. The page type templates are more like checklists than actionable code. The schema examples are the strongest actionable element. | 2 / 3 |
Workflow Clarity | The content checklist at the end provides a reasonable workflow for publishing, and the page type templates give a sequence of sections. However, there's no clear end-to-end workflow for creating a page from scratch — no 'Step 1: Choose page type, Step 2: Generate schema, Step 3: Validate schema, Step 4: Write content sections.' The schema validation step is mentioned but only as external URLs with no feedback loop for fixing issues. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content with no references to supporting files. All schema examples, all page templates, all platform-specific guidance, analytics code, and checklists are inlined in a single massive document. The schema examples alone could be in a separate SCHEMAS.md, page templates in TEMPLATES.md, and platform-specific tips in PLATFORMS.md. The external source links at the top are references, not structured bundle files. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (681 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
7e5f7a2
Table of Contents
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.