Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Senior Engineer agent for architecture decisions, code review, DevOps, and API design. Orchestrates engineering and engineering-team skills for technical implementation work. Spawn when users need system design, code quality review, CI/CD pipeline setup, or infrastructure decisions.
.claude/skills/alirezarezvani-cs-senior-engineer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 32% | 0% |
Cross-cutting senior engineer covering architecture, backend, DevOps, security, and API design. Acts as technical lead who can assess tradeoffs, review code, design systems, and set up delivery pipelines.
engineering/database-designer — Schema design, query optimization, migrationsengineering/api-design-reviewer — REST/GraphQL API contract reviewengineering/migration-architect — System migration planningengineering-team/senior-architect — High-level architecture patternsengineering-team/senior-backend — Backend implementation patternsengineering/pr-review-expert — Pull request review methodologyengineering/focused-fix — Deep-dive feature repair (5-phase: scope → trace → diagnose → fix → verify)engineering-team/code-reviewer — Code quality analysisengineering-team/tdd-guide — Test-driven developmentengineering-team/senior-qa — Quality assurance strategyengineering/ci-cd-pipeline-builder — Pipeline generation (GitHub Actions, GitLab CI)engineering/skills/changelog-generator — Changelog generation, version bumping, release notesengineering-team/senior-devops — Infrastructure and deploymentengineering/observability-designer — Monitoring and alertingengineering-team/senior-security — Application securityengineering-team/senior-secops — Security operationsengineering/dependency-auditor — Supply chain securitysenior-architectdatabase-designerapi-design-reviewerci-cd-pipeline-buildercode-reviewer + pr-review-experttdd-guidesenior-securitysenior-devopsci-cd-pipeline-builderdependency-auditorobservability-designerchangelog-generatorfocused-fix Phase 1 (SCOPE)tech-debt-tracker| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-15 | pass→pass | 23,318 | 15,846 | -32% | 1 | 1 | 0% | 2,596 | 3,603 | +39% | 0 | 0 | — |
case-01 | fail→pass | 51,970 | 23,758 | -54% | 1 | 1 | 0% | 6,222 | 5,235 | -16% | 0 | 0 | — |
case-02 | fail→pass | 30,176 | 27,773 | -8% | 1 | 1 | 0% | 6,214 | 7,163 | +15% | 0 | 0 | — |
case-03 | fail→fail | 15,360 | 26,564 | +73% | 1 | 1 | 0% | 2,758 | 5,428 | +97% | 0 | 0 | — |
case-04 | fail→fail | 13,634 | 12,554 | -8% | 1 | 1 | 0% | 2,344 | 3,246 | +38% | 0 | 0 | — |
case-09 | fail→fail | 14,520 | 11,783 | -19% | 1 | 1 | 0% | 2,540 | 2,722 | +7% | 0 | 0 | — |
case-05 | fail→pass | 14,569 | 8,785 | -40% | 1 | 1 | 0% | 2,943 | 2,430 | -17% | 0 | 0 | — |
case-06 | pass→pass | 14,764 | 11,012 | -25% | 1 | 1 | 0% | 1,898 | 2,906 | +53% | 0 | 0 | — |
case-07 | pass→pass | 11,296 | 8,331 | -26% | 1 | 1 | 0% | 1,981 | 2,389 | +21% | 0 | 0 | — |
case-08 | fail→pass | 12,002 | 11,878 | -1% | 1 | 1 | 0% | 1,807 | 3,024 | +67% | 0 | 0 | — |
case-10 | fail→fail | 15,636 | 23,596 | +51% | 1 | 1 | 0% | 2,594 | 4,287 | +65% | 0 | 0 | — |
case-11 | pass→pass | 24,975 | 12,873 | -48% | 1 | 1 | 0% | 2,521 | 3,379 | +34% | 0 | 0 | — |
case-12 | fail→fail | 11,881 | 13,836 | +16% | 1 | 1 | 0% | 1,902 | 3,294 | +73% | 0 | 0 | — |
case-13 | fail→pass | 13,821 | 14,560 | +5% | 1 | 1 | 0% | 2,567 | 3,380 | +32% | 0 | 0 | — |
case-14 | fail→pass | 10,931 | 3,394 | -69% | 1 | 1 | 0% | 1,602 | 1,670 | +4% | 0 | 0 | — |
case-16 | fail→pass | 7,593 | 8,534 | +12% | 1 | 1 | 0% | 1,412 | 2,222 | +57% | 0 | 0 | — |
case-17 | pass→pass | 7,406 | 4,458 | -40% | 1 | 1 | 0% | 1,165 | 1,789 | +54% | 0 | 0 | — |
case-18 | fail→pass | 8,204 | 2,961 | -64% | 1 | 1 | 0% | 1,517 | 1,493 | -2% | 0 | 0 | — |
case-19 | fail→pass | 4,782 | 8,590 | +80% | 1 | 1 | 0% | 726 | 2,507 | +245% | 0 | 0 | — |
case-20 | pass→fail | 9,913 | 4,670 | -53% | 1 | 1 | 0% | 1,641 | 1,769 | +8% | 0 | 0 | — |
case-21 | pass→pass | 10,306 | 5,957 | -42% | 1 | 1 | 0% | 1,869 | 1,941 | +4% | 0 | 0 | — |
case-22 | fail→pass | 9,632 | 4,291 | -55% | 1 | 1 | 0% | 1,734 | 1,744 | +1% | 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 +41 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are 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.