Audit and fix HTML metadata including page titles, meta descriptions, canonical URLs, Open Graph tags, Twitter cards, favicons, JSON-LD structured data, and robots directives. Use when adding SEO metadata, fixing social share previews, reviewing Open Graph tags, setting up canonical URLs, or shipping new pages that need correct meta tags.
90
88%
Does it follow best practices?
Impact
94%
1.00xAverage score across 3 eval scenarios
Passed
No known issues
Quality
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 an excellent skill description that follows best practices. It uses third person voice, lists comprehensive specific capabilities, includes an explicit 'Use when...' clause with multiple natural trigger scenarios, and carves out a distinct niche around HTML metadata and SEO optimization that won't conflict with broader web development skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Audit and fix HTML metadata including page titles, meta descriptions, canonical URLs, Open Graph tags, Twitter cards, favicons, JSON-LD structured data, and robots directives.' This comprehensively covers the domain with specific technical elements. | 3 / 3 |
Completeness | Clearly answers both what ('Audit and fix HTML metadata including...') AND when ('Use when adding SEO metadata, fixing social share previews, reviewing Open Graph tags, setting up canonical URLs, or shipping new pages that need correct meta tags'). Explicit 'Use when...' clause with multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'SEO metadata', 'social share previews', 'Open Graph tags', 'canonical URLs', 'meta tags', 'Twitter cards'. These are terms developers and marketers naturally use when discussing these tasks. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on HTML metadata and SEO-related tags. The specific mentions of Open Graph, Twitter cards, JSON-LD, and canonical URLs create a distinct domain unlikely to conflict with general HTML or web development skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise skill that effectively prioritizes metadata rules and provides clear workflow guidance. Its main weakness is the lack of concrete code examples - the skill tells Claude what to do but doesn't show executable HTML/JSX snippets for common metadata patterns. The organization is good but could benefit from splitting detailed reference material into separate files.
Suggestions
Add concrete HTML/JSX code examples for common metadata patterns (e.g., a complete Open Graph tag set, a JSON-LD block, canonical URL implementation)
Include framework-specific examples for Next.js metadata API and react-helmet since these are explicitly mentioned as patterns to follow
Consider splitting detailed rule categories (structured data, icons/manifest) into separate reference files to improve progressive disclosure
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables and bullet points to convey rules without unnecessary explanation. It assumes Claude understands HTML metadata concepts and doesn't waste tokens explaining what Open Graph or canonical URLs are. | 3 / 3 |
Actionability | The skill provides clear rules and guidelines but lacks concrete code examples. No executable HTML snippets, no copy-paste ready meta tag templates, and no specific framework examples (Next.js metadata API, react-helmet) despite mentioning them. | 2 / 3 |
Workflow Clarity | The workflow section provides a clear 5-step sequence with explicit prioritization. The priority table and 'fix critical issues first' guidance creates a logical order. Validation step (verify social cards on real URL) is explicitly included. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and a priority table, but everything is in one file. For a skill this comprehensive (8 rule categories), some content could be split into separate reference files for icons, structured data, or framework-specific patterns. | 2 / 3 |
Total | 10 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
95d0e08
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.