levnikolaevich/claude-code-skills Skills

Coordinates 9 specialized audit workers (security, build, architecture, code quality, dependencies, dead code, observability, concurrency, lifecycle). Researches best practices, delegates parallel audits, aggregates results into docs/project/codebase_audit.md.

Security audit worker (L3). Scans codebase for hardcoded secrets, SQL injection, XSS, insecure dependencies, missing input validation. Returns findings with severity (Critical/High/Medium/Low), location, effort, and recommendations.

Build health audit worker (L3). Checks compiler/linter errors, deprecation warnings, type errors, failed tests, build configuration issues. Returns findings with severity (Critical/High/Medium/Low), location, effort, and recommendations.

Code principles audit worker (L3). Checks DRY (10 types), KISS/YAGNI, error handling, DI patterns. Returns findings with severity, location, effort, pattern_signature.

Code quality audit worker (L3). Checks cyclomatic complexity, deep nesting, long methods, god classes, method signature quality, O(n²) algorithms, N+1 queries, magic numbers/constants. Returns findings with severity, location, effort, recommendations.

Dependencies audit worker (L3). Checks outdated packages, unused deps, reinvented wheels, vulnerability scan (CVE/CVSS). Supports mode: full | vulnerabilities_only.

Dead code & legacy audit worker (L3). Checks unreachable code, unused imports/variables/functions, commented-out code, backward compatibility shims, deprecated patterns. Returns findings.

Observability audit worker (L3). Checks structured logging, health check endpoints, metrics collection, request tracing, log levels. Returns findings with severity, location, effort, recommendations.

Concurrency audit worker (L3). Checks race conditions, missing async/await, resource contention, thread safety, deadlock potential. Returns findings with severity, location, effort, recommendations.

Application lifecycle audit worker (L3). Checks bootstrap initialization order, graceful shutdown, resource cleanup, signal handling, liveness/readiness probes. Returns findings with severity, location, effort, recommendations.

Test suite audit coordinator (L2). Delegates to 5 workers (Business Logic, E2E, Value, Coverage, Isolation). Aggregates results into docs/project/test_audit.md.

Business Logic Focus audit worker (L3). Detects tests that validate framework/library behavior (Prisma, Express, bcrypt, JWT, axios, React hooks) instead of OUR code. Returns findings with REMOVE decisions.

E2E Critical Coverage audit worker (L3). Validates E2E coverage for critical paths (Money 20+, Security 20+, Data 15+). Pure risk-based - no pyramid percentages.

Risk-Based Value audit worker (L3). Calculates Usefulness Score = Impact (1-5) × Probability (1-5) for each test. Returns KEEP/REVIEW/REMOVE decisions based on thresholds (≥15 KEEP, 10-14 REVIEW, <10 REMOVE).

Coverage Gaps audit worker (L3). Identifies missing tests for critical paths (Money 20+, Security 20+, Data Integrity 15+, Core Flows 15+). Returns list of untested critical business logic with priority justification.

Test Isolation + Anti-Patterns audit worker (L3). Checks isolation (APIs/DB/FS/Time/Random/Network), determinism (flaky, order-dependent), and 7 anti-patterns.

Audits architectural patterns against best practices (MCP Ref, Context7, WebSearch). Maintains patterns catalog, calculates 4 scores. Output: docs/project/patterns_catalog.md. Use when user asks to: (1) Check architecture health, (2) Audit patterns before refactoring, (3) Find undocumented patterns in codebase.

L3 Worker. Analyzes single pattern implementation, calculates 4 scores (compliance, completeness, quality, implementation), identifies gaps and issues. Usually invoked by ln-640, can also analyze a specific pattern on user request.

L3 Worker. Audits layer boundaries + cross-layer consistency: I/O violations, transaction boundaries (commit ownership), session ownership (DI vs local).

API contract audit worker (L3). Checks layer leakage in method signatures, missing DTOs, entity leakage to API, inconsistent error contracts, redundant method overloads. Returns findings with penalty-based scoring + diagnostic sub-scores.

L3 Worker. Builds dependency graph, detects cycles (DFS), validates boundary rules, calculates coupling metrics (Ca/Ce/I, CCD/NCCD). Adaptive architecture detection.

L3 Worker. Goal-based open-source replacement auditor: discovers custom modules (>100 LOC), analyzes PURPOSE via code reading, searches OSS alternatives via MCP Research (WebSearch, Context7, Ref), evaluates quality (stars, maintenance, license, CVE, API compatibility), generates migration plan.

L3 Worker. Audits project physical structure: file hygiene, ignore file quality, framework convention compliance, domain/layer organization, naming conventions. Stack-adaptive via auto-detection.

Coordinates 4 specialized audit workers (query efficiency, transaction correctness, runtime performance, resource lifecycle). Researches DB/ORM/async best practices, delegates parallel audits, aggregates results into docs/project/persistence_audit.md.