Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Engineering Team Lead agent for coordinating QA, security, data engineering, ML, and frontend/backend teams. Orchestrates engineering-team skills for team-level technical decisions. Spawn when users need team coordination, tech stack evaluation, incident response, or cross-functional engineering work.
.claude/skills/alirezarezvani-cs-engineering-lead/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-06 | ✓→✗ | ▼ Worse | -15% | 0% |
| case-21 | ✓→✗ | ▼ Worse | 72% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 25% | 0% |
Engineering team lead coordinating across specializations: frontend, backend, QA, security, data, ML, and DevOps. Focuses on team-level decisions, incident management, and cross-functional delivery.
engineering-team/senior-frontend — React/Next.js, design systemsengineering-team/senior-backend — APIs, databases, system designengineering-team/senior-fullstack — End-to-end feature deliveryengineering-team/senior-qa — Test strategy, automationengineering-team/playwright-pro — E2E testing with Playwrightengineering-team/tdd-guide — Test-driven developmentengineering-team/senior-security — Application securityengineering-team/senior-secops — Security operations, complianceengineering-team/senior-data-engineer — Data pipelines, warehousingengineering-team/senior-data-scientist — Analysis, modelingengineering-team/senior-ml-engineer — ML systems, deploymentengineering-team/senior-devops — Infrastructure, CI/CDengineering-team/incident-commander — Incident managementengineering-team/aws-solution-architect — Cloud architectureengineering-team/tech-stack-evaluator — Technology evaluationincident-commandertech-stack-evaluator| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 17,616 | 18,479 | +5% | 1 | 1 | 0% | 2,475 | 3,099 | +25% | 0 | 0 | — |
case-02 | pass→pass | 12,117 | 11,848 | -2% | 1 | 1 | 0% | 2,366 | 2,845 | +20% | 0 | 0 | — |
case-03 | pass→pass | 15,934 | 16,687 | +5% | 1 | 1 | 0% | 2,650 | 3,593 | +36% | 0 | 0 | — |
case-04 | pass→pass | 9,074 | 4,230 | -53% | 1 | 1 | 0% | 1,506 | 1,241 | -18% | 0 | 0 | — |
case-05 | pass→pass | 11,786 | 8,617 | -27% | 1 | 1 | 0% | 2,117 | 2,200 | +4% | 0 | 0 | — |
case-06 | pass→fail | 7,704 | 2,080 | -73% | 1 | 1 | 0% | 1,269 | 1,082 | -15% | 0 | 0 | — |
case-07 | pass→pass | 11,009 | 7,020 | -36% | 1 | 1 | 0% | 1,595 | 1,931 | +21% | 0 | 0 | — |
case-08 | pass→pass | 15,741 | 11,023 | -30% | 1 | 1 | 0% | 1,998 | 2,303 | +15% | 0 | 0 | — |
case-09 | pass→pass | 11,664 | 8,868 | -24% | 1 | 1 | 0% | 1,982 | 1,883 | -5% | 0 | 0 | — |
case-10 | pass→pass | 17,092 | 8,477 | -50% | 1 | 1 | 0% | 1,267 | 2,062 | +63% | 0 | 0 | — |
case-11 | fail→pass | 8,189 | 2,789 | -66% | 1 | 1 | 0% | 1,017 | 1,176 | +16% | 0 | 0 | — |
case-12 | pass→pass | 15,344 | 9,530 | -38% | 1 | 1 | 0% | 2,558 | 2,533 | -1% | 0 | 0 | — |
case-13 | pass→pass | 12,553 | 14,563 | +16% | 1 | 1 | 0% | 2,189 | 3,176 | +45% | 0 | 0 | — |
case-14 | pass→pass | 9,075 | 4,753 | -48% | 1 | 1 | 0% | 1,514 | 1,654 | +9% | 0 | 0 | — |
case-15 | fail→pass | 10,758 | 7,789 | -28% | 1 | 1 | 0% | 1,834 | 1,794 | -2% | 0 | 0 | — |
case-16 | pass→pass | 3,891 | 2,192 | -44% | 1 | 1 | 0% | 631 | 1,124 | +78% | 0 | 0 | — |
case-17 | pass→pass | 6,508 | 6,389 | -2% | 1 | 1 | 0% | 1,121 | 1,701 | +52% | 0 | 0 | — |
case-18 | pass→pass | 10,144 | 10,426 | +3% | 1 | 1 | 0% | 1,527 | 2,514 | +65% | 0 | 0 | — |
case-19 | pass→pass | 7,779 | 9,405 | +21% | 1 | 1 | 0% | 1,345 | 2,013 | +50% | 0 | 0 | — |
case-20 | pass→pass | 15,780 | 18,414 | +17% | 1 | 1 | 0% | 3,552 | 4,855 | +37% | 0 | 0 | — |
case-21 | pass→fail | 19,209 | 26,927 | +40% | 1 | 1 | 0% | 3,363 | 5,770 | +72% | 0 | 0 | — |
case-22 | pass→pass | 15,018 | 14,721 | -2% | 1 | 1 | 0% | 3,035 | 3,106 | +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. 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.