Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).
.claude/skills/davila7-geo-fundamentals/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | -33% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -50% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 24% | 0% |
> Optimization for AI-powered search engines.
GEO = Generative Engine Optimization
| Goal | Platform | |------|----------| | Be cited in AI responses | ChatGPT, Claude, Perplexity, Gemini |
| Aspect | SEO | GEO | |--------|-----|-----| | Goal | #1 ranking | AI citations | | Platform | Google | AI engines | | Metrics | Rankings, CTR | Citation rate | | Focus | Keywords | Entities, data |
| Engine | Citation Style | Opportunity | |--------|----------------|-------------| | Perplexity | Numbered 1]2] | Highest citation rate | | ChatGPT | Inline/footnotes | Custom GPTs | | Claude | Contextual | Long-form content | | Gemini | Sources section | SEO crossover |
How AI engines select content to cite:
| Factor | Weight | |--------|--------| | Semantic relevance | ~40% | | Keyword match | ~20% | | Authority signals | ~15% | | Freshness | ~10% | | Source diversity | ~15% |
| Element | Why It Works | |---------|--------------| | Original statistics | Unique, citable data | | Expert quotes | Authority transfer | | Clear definitions | Easy to extract | | Step-by-step guides | Actionable value | | Comparison tables | Structured info | | FAQ sections | Direct answers |
| Action | Purpose | |--------|---------| | Google Knowledge Panel | Entity recognition | | Wikipedia (if notable) | Authority source | | Consistent info across web | Entity consolidation | | Industry mentions | Authority signals |
| Crawler | Engine | |---------|--------| | GPTBot | ChatGPT/OpenAI | | Claude-Web | Claude | | PerplexityBot | Perplexity | | Googlebot | Gemini (shared) |
| Strategy | When | |----------|------| | Allow all | Want AI citations | | Block GPTBot | Don't want OpenAI training | | Selective | Allow some, block others |
| Metric | How to Track | |--------|--------------| | AI citations | Manual monitoring | | "According to Brand]" mentions | Search in AI | | Competitor citations | Compare share | | AI-referred traffic | UTM parameters |
| ❌ Don't | ✅ Do | |----------|-------| | Publish without dates | Add timestamps | | Vague attributions | Name sources | | Skip author info | Show credentials | | Thin content | Comprehensive coverage |
> Remember: AI cites content that's clear, authoritative, and easy to extract. Be the best answer.
| Script | Purpose | Command | |--------|---------|---------| | scripts/geo_checker.py | GEO audit (AI citation readiness) | python scripts/geo_checker.py <project_path> |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-16 | pass→pass | 10,585 | 2,859 | -73% | 1 | 1 | 0% | 1,622 | 1,269 | -22% | 0 | 0 | — |
case-10 | pass→pass | 14,735 | 10,901 | -26% | 1 | 1 | 0% | 2,322 | 2,805 | +21% | 0 | 0 | — |
case-01 | pass→fail | 17,558 | 17,102 | -3% | 1 | 1 | 0% | 2,766 | 3,629 | +31% | 0 | 0 | — |
case-02 | fail→fail | 20,583 | 19,267 | -6% | 1 | 1 | 0% | 3,187 | 4,323 | +36% | 0 | 0 | — |
case-03 | fail→pass | 21,619 | 10,099 | -53% | 1 | 1 | 0% | 4,100 | 2,762 | -33% | 0 | 0 | — |
case-09 | fail→fail | 18,294 | 15,020 | -18% | 1 | 1 | 0% | 2,712 | 3,127 | +15% | 0 | 0 | — |
case-04 | fail→pass | 17,418 | 7,708 | -56% | 1 | 1 | 0% | 3,184 | 2,212 | -31% | 0 | 0 | — |
case-05 | pass→pass | 13,372 | 7,918 | -41% | 1 | 1 | 0% | 2,374 | 2,346 | -1% | 0 | 0 | — |
case-06 | pass→pass | 16,381 | 17,413 | +6% | 1 | 1 | 0% | 2,415 | 3,554 | +47% | 0 | 0 | — |
case-07 | fail→pass | 17,497 | 15,734 | -10% | 1 | 1 | 0% | 2,727 | 3,398 | +25% | 0 | 0 | — |
case-08 | fail→pass | 15,383 | 3,738 | -76% | 1 | 1 | 0% | 2,859 | 1,422 | -50% | 0 | 0 | — |
case-11 | fail→fail | 18,271 | 19,712 | +8% | 1 | 1 | 0% | 2,836 | 3,964 | +40% | 0 | 0 | — |
case-12 | fail→pass | 16,039 | 14,340 | -11% | 1 | 1 | 0% | 2,550 | 3,173 | +24% | 0 | 0 | — |
case-13 | pass→pass | 16,852 | 16,393 | -3% | 1 | 1 | 0% | 2,998 | 3,991 | +33% | 0 | 0 | — |
case-14 | pass→pass | 6,353 | 1,871 | -71% | 1 | 1 | 0% | 928 | 1,170 | +26% | 0 | 0 | — |
case-15 | fail→pass | 12,668 | 4,453 | -65% | 1 | 1 | 0% | 2,201 | 1,599 | -27% | 0 | 0 | — |
case-17 | pass→pass | 15,878 | 14,192 | -11% | 1 | 1 | 0% | 2,602 | 3,306 | +27% | 0 | 0 | — |
case-18 | pass→pass | 13,863 | 2,826 | -80% | 1 | 1 | 0% | 2,055 | 1,218 | -41% | 0 | 0 | — |
case-19 | pass→pass | 7,385 | 2,329 | -68% | 1 | 1 | 0% | 1,150 | 1,214 | +6% | 0 | 0 | — |
case-20 | pass→pass | 5,616 | 4,141 | -26% | 1 | 1 | 0% | 1,086 | 1,580 | +45% | 0 | 0 | — |
case-21 | pass→pass | 3,541 | 2,652 | -25% | 1 | 1 | 0% | 564 | 1,396 | +148% | 0 | 0 | — |
case-22 | pass→pass | 5,102 | 4,440 | -13% | 1 | 1 | 0% | 990 | 1,754 | +77% | 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 +23 percentage points is the difference between those two pass rates over the 22 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.
Other measured skills in the registry, with their headline benchmark lift.