Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Fullstack development toolkit with project scaffolding for Next.js/FastAPI/MERN/Django stacks and code quality analysis. Use when scaffolding new projects, analyzing codebase quality, or implementing fullstack architecture patterns.
.claude/skills/borghei-senior-fullstack/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 138% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 198% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 14% | 0% |
Fullstack development skill that scaffolds production-ready project structures (Next.js, FastAPI+React, MERN, Django+React) and runs static code quality analysis across security, complexity, dependency health, test coverage, and documentation — paired with reference guides for architecture patterns, development workflows, and stack selection.
Use this skill when you hear:
Before scaffolding, confirm these inputs. If any is unknown or vague, ASK — do not assume:
project_scaffolder positional args)project_scaffolder vs code_quality_analyzer)Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
| Tool | Purpose | Command | |------|---------|---------| | project_scaffolder.py | Scaffold a fullstack project structure with boilerplate, Docker, and env config | python scripts/project_scaffolder.py nextjs my-app --output ./projects | | code_quality_analyzer.py | Static-analyze a codebase for security, complexity, deps, coverage, and docs | python scripts/code_quality_analyzer.py . --verbose --json --output audit.json |
Load the reference that matches the task — keep this file lean and pull detail on demand:
What this skill covers:
What this skill does NOT cover:
senior-devops for observability toolingaws-solution-architect and senior-devopsnpm audit, pip-audit, or senior-secops for deep security analysis| Skill | Integration | Data Flow | |-------|-------------|-----------| | senior-devops | CI/CD pipeline setup for scaffolded projects | Scaffolder output directory feeds into DevOps pipeline configuration and Docker deployment workflows | | senior-secops | Deep security audit after initial quality scan | Code quality analyzer P0/P1 security findings hand off to SecOps for remediation tracking and penetration testing | | senior-qa | Test strategy for scaffolded projects | Test coverage estimation from the analyzer informs QA test plan gaps; scaffolded test infrastructure provides the harness | | code-reviewer | Automated review of generated and existing code | Quality analyzer JSON report provides structured input for code review checklists and PR approval criteria | | senior-architect | Architecture validation of stack choices | Tech stack guide recommendations feed into architecture decision records; complexity metrics validate design compliance | | aws-solution-architect | Cloud deployment of scaffolded applications | Docker Compose configurations from the scaffolder translate into ECS/EKS task definitions and infrastructure blueprints |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 14,579 | 25,843 | +77% | 1 | 1 | 0% | 1,681 | 3,999 | +138% | 0 | 0 | — |
case-02 | fail→pass | 17,912 | 9,480 | -47% | 1 | 1 | 0% | 3,410 | 2,764 | -19% | 0 | 0 | — |
case-03 | fail→pass | 3,774 | 3,262 | -14% | 1 | 1 | 0% | 623 | 1,856 | +198% | 0 | 0 | — |
case-04 | fail→pass | 12,937 | 5,281 | -59% | 1 | 1 | 0% | 2,135 | 2,183 | +2% | 0 | 0 | — |
case-05 | fail→pass | 20,446 | 18,298 | -11% | 1 | 1 | 0% | 4,111 | 4,674 | +14% | 0 | 0 | — |
case-21 | fail→fail | 17,714 | 15,235 | -14% | 1 | 1 | 0% | 3,260 | 4,174 | +28% | 0 | 0 | — |
case-06 | fail→pass | 12,926 | 2,751 | -79% | 1 | 1 | 0% | 2,267 | 1,727 | -24% | 0 | 0 | — |
case-07 | fail→pass | 7,950 | 2,414 | -70% | 1 | 1 | 0% | 1,423 | 1,701 | +20% | 0 | 0 | — |
case-08 | fail→pass | 7,233 | 4,028 | -44% | 1 | 1 | 0% | 1,093 | 1,956 | +79% | 0 | 0 | — |
case-09 | fail→pass | 7,248 | 5,734 | -21% | 1 | 1 | 0% | 1,156 | 2,240 | +94% | 0 | 0 | — |
case-10 | pass→pass | 9,132 | 6,277 | -31% | 1 | 1 | 0% | 1,447 | 2,295 | +59% | 0 | 0 | — |
case-11 | pass→pass | 16,285 | 12,253 | -25% | 1 | 1 | 0% | 2,266 | 3,212 | +42% | 0 | 0 | — |
case-12 | pass→pass | 17,720 | 17,137 | -3% | 1 | 1 | 0% | 2,691 | 3,819 | +42% | 0 | 0 | — |
case-13 | fail→pass | 14,616 | 9,144 | -37% | 1 | 1 | 0% | 2,227 | 2,949 | +32% | 0 | 0 | — |
case-14 | fail→pass | 6,252 | 4,309 | -31% | 1 | 1 | 0% | 929 | 1,989 | +114% | 0 | 0 | — |
case-15 | fail→pass | 10,680 | 3,611 | -66% | 1 | 1 | 0% | 1,662 | 1,924 | +16% | 0 | 0 | — |
case-16 | fail→pass | 16,474 | 2,957 | -82% | 1 | 1 | 0% | 2,376 | 1,788 | -25% | 0 | 0 | — |
case-17 | fail→pass | 15,717 | 8,586 | -45% | 1 | 1 | 0% | 2,307 | 2,625 | +14% | 0 | 0 | — |
case-18 | fail→fail | 15,303 | 11,025 | -28% | 1 | 1 | 0% | 2,200 | 2,824 | +28% | 0 | 0 | — |
case-19 | fail→fail | 21,303 | 18,028 | -15% | 1 | 1 | 0% | 3,163 | 4,398 | +39% | 0 | 0 | — |
case-20 | fail→fail | 21,308 | 25,391 | +19% | 1 | 1 | 0% | 4,230 | 6,581 | +56% | 0 | 0 | — |
case-22 | fail→pass | 19,628 | 15,288 | -22% | 1 | 1 | 0% | 3,248 | 3,866 | +19% | 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 +68 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.