Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Run a comprehensive SEO audit — keyword research, on-page analysis, content gaps, technical checks, and competitor comparison. Use when assessing a site's SEO health, when finding keyword opportunities and content gaps competitors own, or when you need a prioritized action plan split into quick wins and strategic investments.
.claude/skills/evolution-foundation-mkt-seo-audit/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 68% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 82% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 154% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 63% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 123% | 0% |
> If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Audit a website's SEO health, research keyword opportunities, identify content gaps, and benchmark against competitors. Produces a prioritized action plan a marketer can execute immediately.
User runs /seo-audit or asks for an SEO audit, keyword research, content gap analysis, technical SEO check, or competitor SEO comparison.
Gather the following from the user. If not provided, ask before proceeding:
If not specified, default to full site audit.
Research keywords related to the user's domain, topic, or target keywords.
If ~~SEO tools are connected:
If ~~product analytics are connected:
If tools are not connected:
For each keyword opportunity, assess:
For each key page (homepage, top landing pages, recent blog posts), evaluate:
Identify what's missing from the user's content strategy:
Evaluate technical foundations that affect crawlability and rankings:
For each competitor, compare:
Open with a 3-5 sentence summary of overall SEO health. Highlight:
| Keyword | Est. Difficulty | Opportunity Score | Current Ranking | Intent | Recommended Content Type | |---------|----------------|-------------------|-----------------|--------|--------------------------|
Opportunity score: high, medium, or low — based on the combination of search demand, difficulty, and relevance to the user's business.
Include 15-25 keyword opportunities, sorted by opportunity score.
| Page | Issue | Severity | Recommended Fix | |------|-------|----------|-----------------|
Severity levels:
For each content gap identified, provide:
| Check | Status | Details | |-------|--------|---------|
Status: Pass, Fail, or Warning.
| Dimension | Your Site | Competitor A | Competitor B | Winner | |-----------|-----------|--------------|--------------|--------|
Include rows for: keyword count, content depth, publishing frequency, backlink signals, technical score, SERP feature presence.
Split recommendations into two categories:
Quick Wins (do this week):
Strategic Investments (plan for this quarter):
For each action item, include:
After presenting the audit, ask:
"Would you like me to:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | fail→fail | 31,548 | 36,323 | +15% | 1 | 1 | 0% | 5,308 | 8,005 | +51% | 0 | 0 | — |
case-01 | fail→fail | 26,042 | 27,268 | +5% | 1 | 1 | 0% | 4,276 | 5,972 | +40% | 0 | 0 | — |
case-02 | fail→fail | 18,405 | 5,794 | -69% | 1 | 1 | 0% | 3,149 | 2,317 | -26% | 0 | 0 | — |
case-03 | fail→pass | 18,289 | 18,514 | +1% | 1 | 1 | 0% | 3,097 | 5,197 | +68% | 0 | 0 | — |
case-04 | fail→fail | 14,372 | 14,397 | +0% | 1 | 1 | 0% | 2,586 | 4,501 | +74% | 0 | 0 | — |
case-05 | fail→fail | 29,147 | 30,286 | +4% | 1 | 1 | 0% | 5,106 | 6,842 | +34% | 0 | 0 | — |
case-07 | fail→fail | 11,777 | 15,016 | +28% | 1 | 1 | 0% | 2,040 | 4,805 | +136% | 0 | 0 | — |
case-08 | pass→pass | 12,436 | 14,194 | +14% | 1 | 1 | 0% | 2,194 | 3,945 | +80% | 0 | 0 | — |
case-09 | fail→fail | 18,233 | 22,348 | +23% | 1 | 1 | 0% | 3,015 | 5,639 | +87% | 0 | 0 | — |
case-10 | fail→fail | 14,848 | 5,260 | -65% | 1 | 1 | 0% | 2,517 | 2,296 | -9% | 0 | 0 | — |
case-11 | fail→pass | 16,064 | 17,390 | +8% | 1 | 1 | 0% | 2,693 | 4,896 | +82% | 0 | 0 | — |
case-12 | fail→fail | 14,459 | 5,712 | -60% | 1 | 1 | 0% | 2,399 | 2,343 | -2% | 0 | 0 | — |
case-13 | fail→pass | 13,882 | 20,109 | +45% | 1 | 1 | 0% | 2,104 | 5,339 | +154% | 0 | 0 | — |
case-14 | fail→pass | 15,922 | 16,268 | +2% | 1 | 1 | 0% | 2,925 | 4,772 | +63% | 0 | 0 | — |
case-15 | pass→pass | 12,818 | 15,564 | +21% | 1 | 1 | 0% | 2,312 | 4,801 | +108% | 0 | 0 | — |
case-16 | pass→pass | 9,799 | 9,099 | -7% | 1 | 1 | 0% | 1,561 | 3,457 | +121% | 0 | 0 | — |
case-17 | fail→pass | 11,369 | 12,973 | +14% | 1 | 1 | 0% | 1,871 | 4,176 | +123% | 0 | 0 | — |
case-18 | fail→fail | 14,584 | 6,211 | -57% | 1 | 1 | 0% | 2,443 | 2,428 | -1% | 0 | 0 | — |
case-19 | pass→pass | 11,370 | 20,741 | +82% | 1 | 1 | 0% | 1,630 | 4,671 | +187% | 0 | 0 | — |
case-20 | pass→pass | 16,564 | 15,018 | -9% | 1 | 1 | 0% | 2,712 | 4,531 | +67% | 0 | 0 | — |
case-21 | fail→pass | 15,562 | 9,923 | -36% | 1 | 1 | 0% | 2,418 | 3,445 | +42% | 0 | 0 | — |
case-22 | pass→pass | 14,324 | 9,953 | -31% | 1 | 1 | 0% | 2,597 | 3,777 | +45% | 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, and 18 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +27 percentage points is the difference between those two pass rates over the 18 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.