Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →サイトのSEO問題を監査・診断し、改善提案を行うスキル。 「SEOを監査して」「検索順位が上がらない原因を調べて」「技術SEOをチェック」等のリクエストで発動。
.claude/skills/minicoohei-seo-audit/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 118% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 89% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 175% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 72% | 0% |
You are an expert in search engine optimization. Your goal is to identify SEO issues and provide actionable recommendations to improve organic search performance.
Check for product marketing context first: If .claude/product-marketing-context.md exists, read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Before auditing, understand:
Robots.txt
XML Sitemap
Site Architecture
Crawl Budget Issues (for large sites)
Index Status
Indexation Issues
Canonicalization
Core Web Vitals
Speed Factors
Tools
Check for:
Common issues:
Check for:
Common issues:
Check for:
Common issues:
Primary Page Content
Thin Content Issues
Check for:
Check for:
Common issues:
Per Page
Site-Wide
Experience
Expertise
Authoritativeness
Trustworthiness
Executive Summary
Technical SEO Findings For each issue:
On-Page SEO Findings Same format as above
Content Findings Same format as above
Prioritized Action Plan
Free Tools
Paid Tools (if available)
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→pass | 31,484 | 20,243 | -36% | 1 | 1 | 0% | 5,279 | 5,475 | +4% | 0 | 0 | — |
case-01 | fail→fail | 32,577 | 26,510 | -19% | 1 | 1 | 0% | 5,408 | 6,242 | +15% | 0 | 0 | — |
case-03 | fail→fail | 28,740 | 22,639 | -21% | 1 | 1 | 0% | 4,651 | 5,698 | +23% | 0 | 0 | — |
case-04 | pass→pass | 5,807 | 6,881 | +18% | 1 | 1 | 0% | 1,117 | 3,073 | +175% | 0 | 0 | — |
case-05 | pass→pass | 14,331 | 12,919 | -10% | 1 | 1 | 0% | 2,544 | 4,376 | +72% | 0 | 0 | — |
case-06 | pass→pass | 16,062 | 15,816 | -2% | 1 | 1 | 0% | 2,471 | 4,515 | +83% | 0 | 0 | — |
case-07 | pass→pass | 15,701 | 6,171 | -61% | 1 | 1 | 0% | 2,565 | 3,082 | +20% | 0 | 0 | — |
case-08 | pass→pass | 7,192 | 8,040 | +12% | 1 | 1 | 0% | 1,345 | 3,539 | +163% | 0 | 0 | — |
case-09 | pass→pass | 14,128 | 12,334 | -13% | 1 | 1 | 0% | 2,364 | 4,161 | +76% | 0 | 0 | — |
case-10 | fail→pass | 7,060 | 4,515 | -36% | 1 | 1 | 0% | 1,272 | 2,775 | +118% | 0 | 0 | — |
case-11 | pass→pass | 16,186 | 9,651 | -40% | 1 | 1 | 0% | 2,666 | 3,736 | +40% | 0 | 0 | — |
case-12 | fail→fail | 17,136 | 21,061 | +23% | 1 | 1 | 0% | 2,819 | 5,491 | +95% | 0 | 0 | — |
case-13 | pass→pass | 20,535 | 18,504 | -10% | 1 | 1 | 0% | 3,246 | 5,138 | +58% | 0 | 0 | — |
case-14 | pass→pass | 18,360 | 13,861 | -25% | 1 | 1 | 0% | 2,917 | 4,130 | +42% | 0 | 0 | — |
case-15 | pass→pass | 16,268 | 16,670 | +2% | 1 | 1 | 0% | 2,583 | 4,549 | +76% | 0 | 0 | — |
case-16 | pass→pass | 13,392 | 11,797 | -12% | 1 | 1 | 0% | 2,039 | 3,814 | +87% | 0 | 0 | — |
case-17 | pass→pass | 15,977 | 12,279 | -23% | 1 | 1 | 0% | 2,412 | 4,013 | +66% | 0 | 0 | — |
case-18 | pass→pass | 14,433 | 13,041 | -10% | 1 | 1 | 0% | 2,258 | 4,258 | +89% | 0 | 0 | — |
case-19 | fail→pass | 14,595 | 15,029 | +3% | 1 | 1 | 0% | 2,449 | 4,630 | +89% | 0 | 0 | — |
case-20 | pass→pass | 15,953 | 10,445 | -35% | 1 | 1 | 0% | 2,816 | 3,854 | +37% | 0 | 0 | — |
case-21 | pass→pass | 17,555 | 11,811 | -33% | 1 | 1 | 0% | 3,152 | 3,942 | +25% | 0 | 0 | — |
case-22 | pass→pass | 17,441 | 14,155 | -19% | 1 | 1 | 0% | 2,884 | 4,318 | +50% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +14 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.