web-content
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 a terse fragment that hints at a specific niche (SEO + generative engine optimization) but fails to articulate concrete actions or provide any 'when to use' guidance. It reads more like a topic label than a functional skill description, relying on comma-separated keywords rather than clear capability statements.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios, e.g., 'Use when the user asks about improving search rankings, structured data markup, AI search visibility, or optimizing content for ChatGPT/Perplexity citations.'
Expand the capability list with concrete actions, e.g., 'Generates JSON-LD schema markup, optimizes content for AI citation and discovery, audits pages for search engine and generative AI visibility.'
Include common user-facing keyword variations such as 'search engine optimization', 'structured data', 'JSON-LD', 'rich snippets', 'AI search optimization', and 'generative engine optimization'.
| 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 involving schema) but completely lacks a 'when' clause or any explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' itself is also weak, warranting 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 misses common variations like 'search engine optimization', 'structured data', 'AI search', 'rich snippets', 'JSON-LD', or 'AI visibility'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of SEO with AI discovery platforms (ChatGPT/Perplexity) and the GEO acronym 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 but isn't enough for a clear niche. | 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 reference document for SEO/GEO optimization but suffers from extreme verbosity — it includes extensive content Claude already knows (page structure basics, E-E-A-T concepts, what homepages should contain). The strongest elements are the concrete schema JSON templates and AI referral tracking code. The weakest aspects are the monolithic structure with no progressive disclosure and significant padding with general web content knowledge.
Suggestions
Reduce content by 60-70% by removing page structure templates (homepage, landing page, etc.) that describe common knowledge, and focus only on GEO-specific additions Claude wouldn't already know (schema templates, AI analytics, TL;DR patterns).
Split into multiple files: keep SKILL.md as a concise overview with the checklist and quick reference, then reference separate files for schema templates (SCHEMA.md), page type templates (TEMPLATES.md), and analytics setup (ANALYTICS.md).
Add an explicit workflow: e.g., 1) Identify page type → 2) Apply template → 3) Add schema markup → 4) Validate schema → 5) Run checklist — with validation checkpoints at each step.
Remove the Philosophy section and platform-specific DO/AVOID lists, which are general knowledge; instead, condense platform differences into a single comparison table.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Much of the content explains basic web concepts Claude already knows (what E-E-A-T is, what a homepage should contain, basic HTML structure). The philosophy section, platform-specific optimization tips, and page type templates are largely common knowledge for Claude. The skill could be reduced to schema templates, the GEO-specific checklist, and the AI analytics tracking code. | 1 / 3 |
Actionability | Provides concrete schema JSON examples and analytics tracking code that are copy-paste ready, which is good. However, much of the content is template/guideline-oriented rather than executable — page structure templates are descriptive outlines rather than actionable code, and platform optimization sections are just DO/AVOID lists without concrete implementation steps. | 2 / 3 |
Workflow Clarity | The content checklist at the end provides a clear sequence (SEO checklist → GEO checklist → schema validation), but there's no explicit workflow for creating a page from start to finish. The skill reads more like a reference document than a guided process. Schema validation 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, page templates, analytics code, platform tips, and checklists are inlined in a single massive document. The content would benefit enormously from splitting schema examples, page templates, and platform-specific guides into separate referenced 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 | |
- Repository
- alinaqi/claude-bootstrap
- Commit
65efb33
- 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.