Passed 19 of 22 test cases with the skill, and 7 of 22 without it.
Without skill32%
With skill86%
Checks it passed that the model alone missed
Flags SpecialAnnouncement schema as deprecated.
Displays the overall score out of 80 instead of 100.
Presents overall score formatted as a total out of 80.
and 14 more in the full report
12 fixed7 passed either way3 still failing0 broke
Pass-rate lift
+55 pp
Tokens
+44%
Agent turns
0%
Response time
+11%
Model gemini-3.6-flashMeasured 8/17/2026v119 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 12
Prompt
Write a snippet draft for `https://travelgear.com/reviews/backpacks`. Keep the meta description around 240 characters so searchers get complete details right in the search engine result snippet.
What was checked, without and with the skill
Checked
Without skill
With skill
Recommends an optimal meta description length between 150 and 160 characters.
Missed
Passed
case-09 · gemini-3.6-flash · 8/17/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md67 linessingle file
/digital-marketing-pro:page-seo-analysis
Purpose
Deep single-page SEO analysis — examines everything about one URL across all ranking dimensions. More granular than a site-wide audit. Use for landing page optimization, content refresh prioritization, or pre-publish quality checks.
Input Required
URL: The specific page to analyze
Target keyword: Primary keyword this page should rank for (optional — can be inferred)
Competitors: 1-3 competitor pages targeting the same keyword (optional)
Process
Load brand context: Read active brand profile. Load brand guidelines if available.
Fetch and parse page: Retrieve full HTML, extract all signals.
Title tag analysis: Character count (50-60 chars ideal), keyword placement, brand inclusion, uniqueness, click-worthiness.
Meta description analysis: Character count (150-160 chars), keyword inclusion, CTA presence, uniqueness.
Heading hierarchy: H1 presence and uniqueness, H2-H6 logical structure, keyword distribution across headings.
Content depth analysis: Word count, reading level, topic coverage completeness, keyword placement (primary keyword in title, intro, ≥2 H2s, conclusion, and meta — density is not a target; keyword-density percentages are a discredited metric, not a ranking factor), natural coverage of related/co-occurring terms, content freshness (last modified date).
E-E-A-T signals: Author byline and bio, credentials, first-hand experience indicators, citations and sources, about page link, contact information.
Schema markup detection: JSON-LD, Microdata, RDFa — validate against Google's supported types, check for deprecations (HowTo deprecated Sept 2023, FAQ restricted to gov/health Aug 2023, SpecialAnnouncement deprecated July 2025), suggest missing schema opportunities.
Image audit: Alt text, dimensions, format, lazy loading, fetchpriority on LCP image (see image-seo-audit skill for full methodology).
Internal linking: Inbound links to this page, outbound links from this page, anchor text quality, orphan page check.
Technical signals: Canonical tag, robots directives, mobile viewport, HTTPS, page speed indicators, Core Web Vitals.
AI search readiness: Entity consistency, citation-worthiness, structured answer formatting, concise answer blocks for featured snippets.
Competitor comparison (if provided): Side-by-side analysis of word count, schema, headings, E-E-A-T signals vs competitor pages.