Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to create, optimize, or audit glossary page content and structure. Also use when the user mentions "glossary," "definitions," "terminology," "industry terms," "glossary page," "term definitions," "vocabulary," "glossary SEO," or "definition page." For definitions at scale, use programmatic-seo.
.claude/skills/kostja94-glossary-page-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -24% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 314% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 30% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 31% | 0% |
Guides glossary page structure, content, and internal linking for SEO.
When invoking: On first use, if helpful, open with 1-2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.
Check for project context first: If .claude/project-context.md or .cursor/project-context.md exists, read it for industry terms and customer language.
Identify:
| Element | Purpose | |---------|---------| | Alphabetical index | A-Z or by category | | Term + definition | Clear, concise explanation | | Related terms | Cross-links within glossary | | Internal links | Link to relevant blog/content | | Search | Help users find terms |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 4,765 | 14,313 | +200% | 1 | 1 | 0% | 732 | 3,032 | +314% | 0 | 0 | — |
case-02 | pass→pass | 14,746 | 16,392 | +11% | 1 | 1 | 0% | 2,697 | 3,504 | +30% | 0 | 0 | — |
case-03 | fail→pass | 6,019 | 6,398 | +6% | 1 | 1 | 0% | 1,198 | 1,776 | +48% | 0 | 0 | — |
case-04 | pass→pass | 11,481 | 12,831 | +12% | 1 | 1 | 0% | 2,548 | 3,348 | +31% | 0 | 0 | — |
case-05 | pass→pass | 6,426 | 4,162 | -35% | 1 | 1 | 0% | 1,184 | 1,215 | +3% | 0 | 0 | — |
case-06 | pass→pass | 8,795 | 6,191 | -30% | 1 | 1 | 0% | 1,505 | 1,624 | +8% | 0 | 0 | — |
case-07 | pass→pass | 10,957 | 8,330 | -24% | 1 | 1 | 0% | 1,878 | 1,980 | +5% | 0 | 0 | — |
case-16 | pass→pass | 18,893 | 10,179 | -46% | 1 | 1 | 0% | 3,409 | 2,571 | -25% | 0 | 0 | — |
case-08 | pass→pass | 10,467 | 7,620 | -27% | 1 | 1 | 0% | 1,963 | 1,954 | -0% | 0 | 0 | — |
case-09 | pass→pass | 15,104 | 8,965 | -41% | 1 | 1 | 0% | 2,605 | 2,238 | -14% | 0 | 0 | — |
case-10 | pass→pass | 9,630 | 6,291 | -35% | 1 | 1 | 0% | 1,749 | 1,482 | -15% | 0 | 0 | — |
case-11 | pass→pass | 8,935 | 6,577 | -26% | 1 | 1 | 0% | 1,477 | 1,797 | +22% | 0 | 0 | — |
case-17 | fail→pass | 12,516 | 6,563 | -48% | 1 | 1 | 0% | 2,270 | 1,736 | -24% | 0 | 0 | — |
case-12 | pass→pass | 9,494 | 8,616 | -9% | 1 | 1 | 0% | 1,834 | 2,170 | +18% | 0 | 0 | — |
case-13 | pass→pass | 8,555 | 6,097 | -29% | 1 | 1 | 0% | 1,601 | 1,693 | +6% | 0 | 0 | — |
case-14 | pass→pass | 9,696 | 6,006 | -38% | 1 | 1 | 0% | 1,641 | 1,628 | -1% | 0 | 0 | — |
case-15 | pass→pass | 14,857 | 10,373 | -30% | 1 | 1 | 0% | 2,549 | 2,512 | -1% | 0 | 0 | — |
case-18 | pass→pass | 9,905 | 4,996 | -50% | 1 | 1 | 0% | 1,734 | 1,581 | -9% | 0 | 0 | — |
case-19 | pass→pass | 26,214 | 28,512 | +9% | 1 | 1 | 0% | 6,176 | 6,455 | +5% | 0 | 0 | — |
case-20 | pass→pass | 7,376 | 7,884 | +7% | 1 | 1 | 0% | 1,269 | 2,069 | +63% | 0 | 0 | — |
case-21 | pass→pass | 12,258 | 12,390 | +1% | 1 | 1 | 0% | 2,817 | 3,570 | +27% | 0 | 0 | — |
case-22 | pass→pass | 7,537 | 7,487 | -1% | 1 | 1 | 0% | 1,634 | 2,060 | +26% | 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 +9 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.