code-audit-suite

Run the full local code-audit suite (all scanners + build-verify) against a directory in one pass and drive findings to zero.

This skill should be used when the user asks to "check architecture", "Architektur prüfen", "find circular dependencies", "zirkuläre Abhängigkeiten", "run dependency-cruiser", "enforce layer/import rules", "module boundaries", "Abhängigkeitsgraph", or wants to validate the dependency structure of a JS/TS codebase. Runs dependency-cruiser in Docker and drives violations to zero, processed directly in Claude Code.

This skill should be used when the user asks to "run Bearer", "scan for PII", "Datenschutz prüfen", "DSGVO/GDPR check", "find sensitive data flows", "PII/PHI scan", "privacy risk", or wants to know where personal/health data flows through the code. Runs Bearer in Docker to classify and trace sensitive data, processed directly in Claude Code.

This skill should be used when the user asks to "verify the build", "does it compile", "kompiliert das", "typecheck", "Typprüfung", "check the build", "build prüfen", "does it actually build/run", "funktioniert der Code wirklich", or wants to confirm that refactored/generated code still COMPILES and BUILDS — not just that it passes lint/quality scans. Runs the project's real compiler/typechecker (and, opt-in, its Docker build) in Docker and gates on failure. Processed directly in Claude Code.

This skill should be used when the user asks to "run all scanners", "full code audit", "run the whole quality suite", "Komplett-Audit", "alles prüfen", "alle Tools laufen lassen", "mega scan", "full security and quality scan", or wants the entire local tool chain (SonarQube, Trivy, Opengrep, secrets, Bearer, MegaLinter, architecture, Kubescape, DAST, ScanCode) run in one pass and driven to zero. Orchestrates every individual skill, aggregates results, processed directly in Claude Code.

This skill should be used when the user asks to "run a DAST scan", "scan the running app", "run OWASP ZAP", "run Nuclei", "penetration test", "Web-App-Security prüfen", "Runtime-Security", "API security scan", "check security headers/injection on a live URL", or wants to test a running application for exploitable vulnerabilities. Runs OWASP ZAP + Nuclei in Docker against a URL, processed directly in Claude Code.