Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Index of the engineering-team skills bundle for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw, and 6 more tools. Architecture, frontend, backend, QA, DevOps, security, AI/ML, data engineering, Playwright, Stripe, AWS, MS365 (stdlib-only Python tools). Use when browsing or choosing among engineering-team role skills — load only the one specialist SKILL.md you need, never bulk-load the bundle.
.claude/skills/alirezarezvani-engineering-skills/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-12 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -15% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 72% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -41% | 0% |
32 production-ready engineering skills organized into core engineering, security, AI/ML/Data, and specialized tools.
/read engineering-team/skills/senior-fullstack/SKILL.mdbashnpx agent-skills-cli add alirezarezvani/claude-skills/engineering-team
| Skill | Folder | Focus | |-------|--------|-------| | Senior Architect | senior-architect/ | System design, architecture patterns | | Senior Frontend | senior-frontend/ | React, Next.js, TypeScript, Tailwind | | Senior Backend | senior-backend/ | API design, database optimization | | Senior Fullstack | senior-fullstack/ | Project scaffolding, code quality | | Senior QA | senior-qa/ | Test generation, coverage analysis | | Senior DevOps | senior-devops/ | CI/CD, infrastructure, containers | | Senior SecOps | senior-secops/ | Security operations, vulnerability management | | Code Reviewer | code-reviewer/ | PR review, code quality analysis | | Senior Security | senior-security/ | Threat modeling, STRIDE, penetration testing | | AWS Solution Architect | aws-solution-architect/ | Serverless, CloudFormation, cost optimization | | MS365 Tenant Manager | ms365-tenant-manager/ | Microsoft 365 administration | | TDD Guide | tdd-guide/ | Test-driven development workflows | | Tech Stack Evaluator | tech-stack-evaluator/ | Technology comparison, TCO analysis |
| Skill | Folder | Focus | |-------|--------|-------| | Senior Data Scientist | senior-data-scientist/ | Statistical modeling, experimentation | | Senior Data Engineer | senior-data-engineer/ | Pipelines, ETL, data quality | | Senior ML Engineer | senior-ml-engineer/ | Model deployment, MLOps, LLM integration | | Senior Prompt Engineer | senior-prompt-engineer/ | Prompt optimization, RAG, agents | | Senior Computer Vision | senior-computer-vision/ | Object detection, segmentation |
| Skill | Folder | Focus | |-------|--------|-------| | Playwright Pro | playwright-pro/ | E2E testing (9 sub-skills) | | Self-Improving Agent | self-improving-agent/ | Memory curation (5 sub-skills) | | Stripe Integration | stripe-integration-expert/ | Payment integration, webhooks | | Incident Commander | incident-commander/ | Incident response workflows | | Email Template Builder | email-template-builder/ | HTML email generation |
30+ scripts, all stdlib-only. Run directly:
bashpython3 <skill>/scripts/<tool>.py --help
No pip install needed. Scripts include embedded samples for demo mode.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-12 | fail→pass | 12,264 | 2,112 | -83% | 1 | 1 | 0% | 1,726 | 1,103 | -36% | 0 | 0 | — |
case-01 | fail→pass | 10,256 | 3,719 | -64% | 1 | 1 | 0% | 1,765 | 1,503 | -15% | 0 | 0 | — |
case-02 | fail→pass | 11,871 | 2,170 | -82% | 1 | 1 | 0% | 1,957 | 1,151 | -41% | 0 | 0 | — |
case-03 | fail→pass | 4,645 | 3,493 | -25% | 1 | 1 | 0% | 747 | 1,286 | +72% | 0 | 0 | — |
case-04 | fail→pass | 10,359 | 1,778 | -83% | 1 | 1 | 0% | 1,706 | 1,000 | -41% | 0 | 0 | — |
case-05 | pass→pass | 10,641 | 2,875 | -73% | 1 | 1 | 0% | 1,785 | 1,150 | -36% | 0 | 0 | — |
case-06 | fail→pass | 9,728 | 1,649 | -83% | 1 | 1 | 0% | 1,727 | 988 | -43% | 0 | 0 | — |
case-07 | fail→pass | 2,501 | 2,121 | -15% | 1 | 1 | 0% | 397 | 1,090 | +175% | 0 | 0 | — |
case-08 | fail→pass | 3,951 | 2,399 | -39% | 1 | 1 | 0% | 596 | 1,104 | +85% | 0 | 0 | — |
case-09 | pass→pass | 11,339 | 1,847 | -84% | 1 | 1 | 0% | 1,655 | 1,085 | -34% | 0 | 0 | — |
case-10 | pass→pass | 8,228 | 5,951 | -28% | 1 | 1 | 0% | 1,408 | 1,082 | -23% | 0 | 0 | — |
case-11 | fail→pass | 17,194 | 2,761 | -84% | 1 | 1 | 0% | 2,162 | 1,000 | -54% | 0 | 0 | — |
case-13 | fail→pass | 10,307 | 2,262 | -78% | 1 | 1 | 0% | 1,843 | 1,061 | -42% | 0 | 0 | — |
case-14 | pass→pass | 7,559 | 1,387 | -82% | 1 | 1 | 0% | 1,058 | 959 | -9% | 0 | 0 | — |
case-15 | pass→pass | 9,263 | 1,496 | -84% | 1 | 1 | 0% | 1,454 | 1,009 | -31% | 0 | 0 | — |
case-16 | fail→pass | 9,269 | 2,684 | -71% | 1 | 1 | 0% | 1,471 | 1,114 | -24% | 0 | 0 | — |
case-17 | fail→pass | 10,348 | 1,814 | -82% | 1 | 1 | 0% | 1,810 | 1,064 | -41% | 0 | 0 | — |
case-18 | fail→pass | 16,198 | 1,627 | -90% | 1 | 1 | 0% | 2,728 | 1,041 | -62% | 0 | 0 | — |
case-19 | pass→pass | 5,047 | 2,358 | -53% | 1 | 1 | 0% | 870 | 1,002 | +15% | 0 | 0 | — |
case-20 | pass→pass | 12,757 | 5,639 | -56% | 1 | 1 | 0% | 1,739 | 1,875 | +8% | 0 | 0 | — |
case-21 | pass→pass | 2,933 | 2,069 | -29% | 1 | 1 | 0% | 401 | 1,051 | +162% | 0 | 0 | — |
case-22 | pass→pass | 6,286 | 4,047 | -36% | 1 | 1 | 0% | 1,181 | 1,454 | +23% | 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 +59 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.