Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.
.claude/skills/davila7-architecture/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -58% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -72% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -59% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -72% | 0% |
> "Requirements drive architecture. Trade-offs inform decisions. ADRs capture rationale."
Read ONLY files relevant to the request! Check the content map, find what you need.
| File | Description | When to Read | |------|-------------|--------------| | context-discovery.md | Questions to ask, project classification | Starting architecture design | | trade-off-analysis.md | ADR templates, trade-off framework | Documenting decisions | | pattern-selection.md | Decision trees, anti-patterns | Choosing patterns | | examples.md | MVP, SaaS, Enterprise examples | Reference implementations | | patterns-reference.md | Quick lookup for patterns | Pattern comparison |
| Skill | Use For | |-------|---------| | @[skills/database-design] | Database schema design | | @[skills/api-patterns] | API design patterns | | @[skills/deployment-procedures] | Deployment architecture |
"Simplicity is the ultimate sophistication."
Before finalizing architecture:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 9,183 | 2,160 | -76% | 1 | 1 | 0% | 1,659 | 813 | -51% | 0 | 0 | — |
case-02 | fail→pass | 10,710 | 2,237 | -79% | 1 | 1 | 0% | 1,901 | 801 | -58% | 0 | 0 | — |
case-03 | fail→pass | 16,042 | 2,804 | -83% | 1 | 1 | 0% | 2,718 | 768 | -72% | 0 | 0 | — |
case-04 | fail→pass | 9,449 | 1,818 | -81% | 1 | 1 | 0% | 1,626 | 659 | -59% | 0 | 0 | — |
case-05 | fail→pass | 15,216 | 2,283 | -85% | 1 | 1 | 0% | 2,558 | 724 | -72% | 0 | 0 | — |
case-06 | pass→pass | 8,273 | 4,760 | -42% | 1 | 1 | 0% | 1,389 | 1,249 | -10% | 0 | 0 | — |
case-07 | pass→pass | 14,212 | 13,942 | -2% | 1 | 1 | 0% | 2,323 | 2,661 | +15% | 0 | 0 | — |
case-08 | fail→fail | 10,863 | 9,459 | -13% | 1 | 1 | 0% | 1,712 | 1,786 | +4% | 0 | 0 | — |
case-09 | pass→pass | 12,067 | 6,960 | -42% | 1 | 1 | 0% | 2,107 | 1,469 | -30% | 0 | 0 | — |
case-10 | pass→pass | 9,061 | 4,696 | -48% | 1 | 1 | 0% | 1,510 | 1,061 | -30% | 0 | 0 | — |
case-11 | pass→pass | 8,585 | 5,783 | -33% | 1 | 1 | 0% | 1,345 | 1,359 | +1% | 0 | 0 | — |
case-12 | pass→pass | 10,833 | 9,561 | -12% | 1 | 1 | 0% | 1,849 | 1,798 | -3% | 0 | 0 | — |
case-13 | pass→fail | 6,052 | 3,579 | -41% | 1 | 1 | 0% | 861 | 969 | +13% | 0 | 0 | — |
case-14 | pass→pass | 9,797 | 6,707 | -32% | 1 | 1 | 0% | 1,485 | 1,424 | -4% | 0 | 0 | — |
case-15 | pass→pass | 9,261 | 8,623 | -7% | 1 | 1 | 0% | 1,498 | 1,632 | +9% | 0 | 0 | — |
case-16 | pass→pass | 13,070 | 13,515 | +3% | 1 | 1 | 0% | 2,184 | 2,660 | +22% | 0 | 0 | — |
case-17 | pass→pass | 13,501 | 13,380 | -1% | 1 | 1 | 0% | 2,108 | 2,423 | +15% | 0 | 0 | — |
case-18 | fail→pass | 11,294 | 2,032 | -82% | 1 | 1 | 0% | 1,820 | 686 | -62% | 0 | 0 | — |
case-19 | pass→pass | 9,589 | 2,316 | -76% | 1 | 1 | 0% | 1,519 | 705 | -54% | 0 | 0 | — |
case-20 | pass→pass | 4,737 | 2,151 | -55% | 1 | 1 | 0% | 859 | 677 | -21% | 0 | 0 | — |
case-21 | pass→pass | 6,341 | 1,633 | -74% | 1 | 1 | 0% | 1,115 | 661 | -41% | 0 | 0 | — |
case-22 | pass→pass | 15,125 | 12,669 | -16% | 1 | 1 | 0% | 3,259 | 3,067 | -6% | 0 | 0 | — |
case-23 | pass→pass | 9,712 | 11,581 | +19% | 1 | 1 | 0% | 2,503 | 3,232 | +29% | 0 | 0 | — |
case-24 | pass→pass | 9,038 | 6,066 | -33% | 1 | 1 | 0% | 2,023 | 1,589 | -21% | 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. 24 cases were attempted. The headline lift of +21 percentage points is the difference between those two pass rates over the 24 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.