Browse Skills

Designing Tests provides testing strategies, templates, and coverage guidance for unit, integration, and E2E tests. Use it when adding tests, improving coverage, or debugging test failures.

Optimizing Performance analyzes and optimizes application performance across frontend, backend, and database layers. Use it when diagnosing slowness, improving load times, optimizing queries, or reducing bundle size.

Security Patterns provides reusable code for authentication, authorization, encryption, secrets management, and security hardening. Use it when designing auth flows, managing secrets, configuring CORS, rate limiting, or implementing JWT, OAuth, password hashing, API keys, or RBAC.

Azure App Onboard Prereq performs a static, read-only evaluation of source code to assess build health, app completeness, dependencies, stack compatibility, and deployment feasibility before Azure infrastructure work. Use it to identify blockers and determine if an app is ready to deploy to Azure.

Brooks Audit maps module dependencies, checks layering integrity, and flags structural decay across a codebase, drawing on twelve classic engineering books. Use it for architecture audits or to give new developers a codebase tour.

Brooks Debt identifies, classifies, and prioritizes maintainability problems and builds a refactoring roadmap using twelve classic engineering books. Use it to plan what to clean up first or justify refactoring to management.

Brooks Health scores a project across four quality dimensions—PR quality, architecture, tech debt, and test quality—in a single pass, drawing on twelve classic engineering books. Use it for an overall quality assessment before a release or team onboarding.

Brooks Review performs PR code review that surfaces decay risks, design smells, and maintainability issues with concrete Symptom → Source → Consequence → Remedy findings, drawing on twelve classic engineering books. Use it when reviewing a PR, diff, or pasted code for readiness to merge or refactoring feedback.

Brooks Sweep runs a unified analysis across code decay, architecture, tech debt, and test quality, then applies fixes directly to the codebase. Use it when asked to sweep the codebase, fix everything, auto-fix all issues, or clean up the whole project in one command.

Brooks Test reviews an existing test suite for structural quality problems—brittleness, mock abuse, coverage illusions, slow execution, and poor readability—using principles from classic engineering books. Use it when tests keep breaking, take forever, or pass while bugs reach production.

Decision Verification checks whether a recorded DecisionRecord still holds by running baseline vs measure evidence loops and drift detection. Use it when a shipped decision needs a post-implementation reality-check before further work relies on it.

H-Diagnose identifies the most likely cause of a concrete failure by stabilizing the signal and testing multiple rival explanations in parallel read-only probes. Use it when symptoms are observable but the root cause is unclear, and preserve losing hypotheses for fallback or replay.