Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →API design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination.
.claude/skills/davila7-api-patterns/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-17 | ✗→✓ | ▲ Improved | -48% | 0% |
| case-01 | ✓→✗ | ▼ Worse | -7% | 0% |
| case-13 | ✓→✓ | ＝ Same ✓ | 7% | 0% |
| case-14 | ✓→✓ | ＝ Same ✓ | -1% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 1% | 0% |
> API design principles and decision-making for 2025. > Learn to THINK, not copy fixed patterns.
Read ONLY files relevant to the request! Check the content map, find what you need.
| File | Description | When to Read | |------|-------------|--------------| | api-style.md | REST vs GraphQL vs tRPC decision tree | Choosing API type | | rest.md | Resource naming, HTTP methods, status codes | Designing REST API | | response.md | Envelope pattern, error format, pagination | Response structure | | graphql.md | Schema design, when to use, security | Considering GraphQL | | trpc.md | TypeScript monorepo, type safety | TS fullstack projects | | versioning.md | URI/Header/Query versioning | API evolution planning | | auth.md | JWT, OAuth, Passkey, API Keys | Auth pattern selection | | rate-limiting.md | Token bucket, sliding window | API protection | | documentation.md | OpenAPI/Swagger best practices | Documentation | | security-testing.md | OWASP API Top 10, auth/authz testing | Security audits |
| Need | Skill | |------|-------| | API implementation | @[skills/backend-development] | | Data structure | @[skills/database-design] | | Security details | @[skills/security-hardening] |
Before designing an API:
DON'T:
DO:
| Script | Purpose | Command | |--------|---------|---------| | scripts/api_validator.py | API endpoint validation | python scripts/api_validator.py <project_path> |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-13 | pass→pass | 15,034 | 13,009 | -13% | 1 | 1 | 0% | 2,692 | 2,872 | +7% | 0 | 0 | — |
case-14 | pass→pass | 14,764 | 11,704 | -21% | 1 | 1 | 0% | 2,579 | 2,561 | -1% | 0 | 0 | — |
case-01 | pass→fail | 19,598 | 14,790 | -25% | 1 | 1 | 0% | 3,349 | 3,116 | -7% | 0 | 0 | — |
case-02 | pass→pass | 12,375 | 9,935 | -20% | 1 | 1 | 0% | 2,573 | 2,591 | +1% | 0 | 0 | — |
case-03 | fail→fail | 19,387 | 19,325 | -0% | 1 | 1 | 0% | 3,466 | 4,219 | +22% | 0 | 0 | — |
case-04 | pass→pass | 18,034 | 11,914 | -34% | 1 | 1 | 0% | 3,827 | 3,144 | -18% | 0 | 0 | — |
case-05 | pass→pass | 18,921 | 14,463 | -24% | 1 | 1 | 0% | 4,078 | 3,773 | -7% | 0 | 0 | — |
case-06 | pass→pass | 15,836 | 15,030 | -5% | 1 | 1 | 0% | 3,075 | 3,519 | +14% | 0 | 0 | — |
case-07 | pass→pass | 8,821 | 7,506 | -15% | 1 | 1 | 0% | 1,878 | 2,132 | +14% | 0 | 0 | — |
case-08 | pass→pass | 14,811 | 11,067 | -25% | 1 | 1 | 0% | 2,391 | 2,470 | +3% | 0 | 0 | — |
case-09 | pass→pass | 15,525 | 12,961 | -17% | 1 | 1 | 0% | 2,896 | 3,161 | +9% | 0 | 0 | — |
case-10 | pass→pass | 19,044 | 12,560 | -34% | 1 | 1 | 0% | 3,359 | 2,754 | -18% | 0 | 0 | — |
case-11 | pass→pass | 16,394 | 14,930 | -9% | 1 | 1 | 0% | 2,552 | 3,233 | +27% | 0 | 0 | — |
case-12 | pass→pass | 15,834 | 14,211 | -10% | 1 | 1 | 0% | 2,662 | 3,056 | +15% | 0 | 0 | — |
case-15 | pass→pass | 8,394 | 6,692 | -20% | 1 | 1 | 0% | 1,699 | 1,845 | +9% | 0 | 0 | — |
case-16 | pass→pass | 15,422 | 11,729 | -24% | 1 | 1 | 0% | 2,525 | 2,424 | -4% | 0 | 0 | — |
case-17 | fail→pass | 11,992 | 3,198 | -73% | 1 | 1 | 0% | 2,099 | 1,094 | -48% | 0 | 0 | — |
case-18 | pass→pass | 6,523 | 2,146 | -67% | 1 | 1 | 0% | 1,051 | 999 | -5% | 0 | 0 | — |
case-19 | pass→pass | 4,711 | 7,736 | +64% | 1 | 1 | 0% | 770 | 1,762 | +129% | 0 | 0 | — |
case-20 | pass→pass | 11,227 | 11,401 | +2% | 1 | 1 | 0% | 2,148 | 2,673 | +24% | 0 | 0 | — |
case-21 | pass→pass | 6,319 | 6,805 | +8% | 1 | 1 | 0% | 1,264 | 1,818 | +44% | 0 | 0 | — |
case-22 | pass→pass | 13,319 | 9,972 | -25% | 1 | 1 | 0% | 2,321 | 2,359 | +2% | 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 0 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.