Claude Skills by tensology

Coordinates code quality: ln-511 metrics, ln-512 cleanup, inline agent review (Codex + Gemini), ln-513 regression, ln-514 log analysis. Returns quality_verdict + aggregated results.

Checks DRY/KISS/YAGNI/architecture compliance with quantitative Code Quality Score. Validates decisions via MCP Ref. Reports with SEC-/PERF-/MNT-/ARCH-/BP-/OPT- prefixes.

Applies safe auto-fixes for low-risk audit findings (unused imports, dead code, commented-out code). Confidence >=90% only. Creates single commit with summary.

Worker that runs existing tests to catch regressions. Auto-detects framework, reports pass/fail. No status changes or task creation.

Analyzes application logs: classifies errors, checks log quality/format, maps stack traces to source, recommends fixes.

Performs manual testing of Story AC via executable bash scripts saved to tests/manual/. Creates reusable test suites per Story.

Checks hardcoded secrets, SQL injection, XSS, insecure dependencies, missing input validation. Returns findings with severity, location, effort, recommendations.

Checks compiler/linter errors, deprecation warnings, type errors, failed tests, build config issues. Returns findings with severity, location, effort, recommendations.

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

Checks cyclomatic complexity, nesting, long methods, god classes, method signatures, O(n²), N+1 queries, constants management. Returns findings.

Checks outdated packages, unused deps, reinvented wheels, vulnerability scan (CVE/CVSS).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

Checks unreachable code, unused imports/variables/functions, commented-out code, backward compatibility shims, deprecated patterns. Returns findings.

Checks structured logging, health check endpoints, metrics collection, request tracing, log levels. Returns findings with severity, location, effort, recommendations.

Checks async races, thread safety, TOCTOU, deadlocks, blocking I/O, resource contention, cross-process races. Two-layer detection: grep + agent reasoning.

Checks bootstrap initialization order, graceful shutdown, resource cleanup, signal handling, liveness/readiness probes. Returns findings.

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

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.

Checks isolation (APIs/DB/FS/Time/Random/Network), determinism (flaky, order-dependent), and 7 anti-patterns.

Audits architectural patterns against best practices. Maintains patterns catalog, calculates 4 scores per pattern. Output: patterns_catalog.md.

Analyzes single pattern implementation, calculates 4 scores (compliance, completeness, quality, implementation), identifies gaps. Invoked by ln-640 or standalone.

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

Checks layer leakage in method signatures, missing DTOs, entity leakage to API, inconsistent error contracts. Returns findings with penalty-based scoring.

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

Discovers custom modules (>100 LOC), analyzes purpose, searches OSS alternatives via MCP Research, evaluates quality (stars, license, CVE), generates migration plan.

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

Audits env var config: file inventory, code-to-example sync, default desync, naming, startup validation. Stack-adaptive.

Universal project bootstrapper: CREATE new or TRANSFORM existing project to production-ready structure

Frontend structure worker: SCAFFOLD new React project or RESTRUCTURE existing monolith to component-based architecture

Generates .NET Clean Architecture backend structure from entity definitions

Universal seed data generator: MIGRATE from ORM schemas or GENERATE from entity definitions to any target format

Universal platform artifact cleaner: Replit, StackBlitz, CodeSandbox, Glitch

Generates Docker and docker-compose configuration for multi-container development

Generates GitHub Actions CI workflow configuration

Configures environment variables and secrets protection

Configures ESLint, Prettier, Ruff, mypy, and .NET analyzers

Configures Husky, lint-staged, commitlint, and Python pre-commit

Creates test infrastructure with Vitest, xUnit, and pytest

Scans codebase for hardcoded secrets. Returns normalized findings with severity and remediation guidance. Pre-commit hook integration.

Configures structured logging (Serilog/.NET, structlog/Python)

Configures global exception handling middleware

Configures CORS policy for development and production

Configures health check endpoints for Kubernetes readiness/liveness/startup

Configures Swagger/OpenAPI documentation

Multi-cycle diagnostic pipeline: profile → research → optimize → repeat with full-stack bottleneck analysis

Runtime profiling with multi-metric measurement, instrumentation, and performance map generation

Competitive benchmarks, solution research, and hypothesis generation for identified bottlenecks

Multi-file hypothesis testing with keep/discard loop, compound baselines, and experiment logging

Upgrades npm/yarn/pnpm dependencies with breaking change handling

Upgrades .NET NuGet packages with breaking change handling

Upgrades Python pip/poetry/pipenv dependencies with breaking change handling