Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Query and operate connected Google Search Console properties through NotFair MCP. Use for live GSC query or page performance, clicks, impressions, CTR, position, traffic changes, indexing status, URL inspection, sitemap reads or approved sitemap submission/removal, and Search Console MCP setup. Route full-site SEO audits to seo-analysis.
.claude/skills/nowork-studio-search-console/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -15% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-16 | ✓→✗ | ▼ Worse | 25% | 0% |
Read ../shared/operating-contract.md. Use the live connector's instructions and schemas to choose tools for the task. For a full-site SEO audit that also needs crawling and on-page analysis, hand off to /notfair:seo-analysis after confirming access.
~~search-console to the actual Search Console connector and inspect its current tools. Use live property information to identify the intended site.sc-domain:example.com and https://example.com/ are different properties.Correlate totals, queries, pages, countries, and devices as needed for the question. Choose available reporting capabilities; batch related reads when supported and useful, and use a narrow read for a single property, URL, or sitemap.
query dimension when reconciling property-level clicks and impressions. Anonymized low-volume queries make query rows incomplete by design.all data as provisional.Lead with the largest material gain or loss, affected queries/pages, evidence-backed hypothesis, confidence, and the next SEO action. Route content rewrites, technical remediation, or full audits to the corresponding SEO skill.
Submit or remove a sitemap through a supported capability only after showing the exact verified property and sitemap URL and obtaining approval. Confirm the sitemap belongs to the selected property and is fetchable before submission when possible.
Submission and deletion are reversible counterparts, but deleting a submitted sitemap does not remove its URLs from Google's index. Never describe sitemap submission as an indexing guarantee. Confirm the resulting sitemap state from returned before/after evidence or a fresh list.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-17 | pass→pass | 19,201 | 15,075 | -21% | 1 | 1 | 0% | 2,175 | 2,230 | +3% | 0 | 0 | — |
case-18 | fail→fail | 24,495 | 13,033 | -47% | 1 | 1 | 0% | 1,445 | 1,723 | +19% | 0 | 0 | — |
case-01 | fail→pass | 20,145 | 14,143 | -30% | 1 | 1 | 0% | 2,383 | 2,029 | -15% | 0 | 0 | — |
case-02 | fail→fail | 12,625 | 8,238 | -35% | 1 | 1 | 0% | 1,398 | 1,004 | -28% | 0 | 0 | — |
case-03 | fail→pass | 11,847 | 11,526 | -3% | 1 | 1 | 0% | 1,173 | 1,675 | +43% | 0 | 0 | — |
case-04 | fail→fail | 20,612 | 13,116 | -36% | 1 | 1 | 0% | 2,932 | 1,874 | -36% | 0 | 0 | — |
case-05 | pass→pass | 16,247 | 12,178 | -25% | 1 | 1 | 0% | 1,989 | 1,734 | -13% | 0 | 0 | — |
case-06 | fail→pass | 17,656 | 11,288 | -36% | 1 | 1 | 0% | 1,820 | 1,441 | -21% | 0 | 0 | — |
case-07 | pass→pass | 16,424 | 11,659 | -29% | 1 | 1 | 0% | 1,673 | 1,573 | -6% | 0 | 0 | — |
case-08 | pass→pass | 16,942 | 16,953 | +0% | 1 | 1 | 0% | 2,114 | 2,649 | +25% | 0 | 0 | — |
case-09 | pass→pass | 14,647 | 11,901 | -19% | 1 | 1 | 0% | 1,453 | 1,566 | +8% | 0 | 0 | — |
case-10 | fail→fail | 15,903 | 13,579 | -15% | 1 | 1 | 0% | 1,739 | 1,943 | +12% | 0 | 0 | — |
case-11 | pass→pass | 24,184 | 26,656 | +10% | 1 | 1 | 0% | 2,761 | 3,895 | +41% | 0 | 0 | — |
case-12 | pass→pass | 14,635 | 12,184 | -17% | 1 | 1 | 0% | 1,676 | 1,617 | -4% | 0 | 0 | — |
case-13 | fail→fail | 10,374 | 14,118 | +36% | 1 | 1 | 0% | 923 | 1,948 | +111% | 0 | 0 | — |
case-14 | fail→fail | 13,283 | 13,848 | +4% | 1 | 1 | 0% | 1,244 | 766 | -38% | 0 | 0 | — |
case-15 | fail→pass | 19,672 | 15,583 | -21% | 1 | 1 | 0% | 2,346 | 2,263 | -4% | 0 | 0 | — |
case-16 | pass→fail | 22,141 | 24,589 | +11% | 1 | 1 | 0% | 2,893 | 3,612 | +25% | 0 | 0 | — |
case-19 | pass→pass | 21,062 | 16,922 | -20% | 1 | 1 | 0% | 2,446 | 2,302 | -6% | 0 | 0 | — |
case-20 | pass→pass | 22,387 | 21,107 | -6% | 1 | 1 | 0% | 2,758 | 3,152 | +14% | 0 | 0 | — |
case-21 | pass→pass | 17,431 | 13,845 | -21% | 1 | 1 | 0% | 2,066 | 1,937 | -6% | 0 | 0 | — |
case-22 | pass→pass | 27,878 | 12,185 | -56% | 1 | 1 | 0% | 2,046 | 1,796 | -12% | 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 21 counted toward the lift figure. The other 1 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 +14 percentage points is the difference between those two pass rates over the 21 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 9/8/2026 | +5% |
Other measured skills in the registry, with their headline benchmark lift.