VilnaCRM-Org

Systematically retrieve and address PR code review comments using make pr-comments. Use when handling code review feedback or addressing PR comments.

Codex entrypoint for post-implementation BMAD FR/NFR review gates. Use after a PR, feature, or bugfix has BMAD specs and must be checked against every functional requirement, non-functional requirement, expanded quality dimension, Wikipedia system quality…

Run a BMAD spec-driven post-implementation review gate. Use after implementing a GitHub PR, feature, bugfix, or task with BMAD specs to verify every FR/NFR, pinned NonFunctionals.com NFR category, expanded quality dimension, Wikipedia system quality…

Design LLM-powered modules with Clean Architecture boundaries, SOLID, DRY, KISS, and provider-agnostic ports/adapters. Use when adding prompt workflows, model/provider clients, tool orchestration, AI review automation, agent skills, or other LLM-backed…

advanced elicitation. Use when the user asks about advanced elicitation.

adversarial review. Use when the user asks about adversarial review.

Research, briefs, discovery. Use when the user asks about analyst.

Technical design, architecture. Use when the user asks about architect.

Run comprehensive CI checks before committing changes. Use when the user asks to run CI, run quality checks, validate code quality, or before finishing any task that involves code changes.

Ensure proper code organization with class names, directories, namespaces, and naming consistency following the principle "Directory X contains ONLY class type X".

Design and implement DDD patterns (entities, value objects, aggregates, CQRS). Use when creating new domain objects, implementing bounded contexts, designing repository interfaces, or learning proper layer separation. For fixing existing Deptrac violations,…

Implement production-grade caching with cache keys/TTLs/consistency classes per query, SWR (stale-while-revalidate), layered explicit invalidation, and comprehensive testing for stale reads and cache warmup. Use when adding caching to queries, implementing…

Systematically retrieve and address PR code review comments using make pr-comments. Enforces DDD architecture, code organization principles, and quality standards. Use when handling code review feedback, refactoring based on reviewer suggestions, or…

Guide for contributing to the OpenAPI layer using processor pattern, complexity management, and functional programming. Use when adding endpoint factories, processors, parameter descriptions, reducing cyclomatic complexity, or fixing OpenAPI validation…

Portable autonomous BMALPH planning for Codex. Use when the user wants specs from a short task description and expects the current AI session to orchestrate BMALPH subagents without human interaction.

BMAD master agent — navigate phases. Use when the user asks about bmalph.

Overview of the protected frontend quality thresholds and a quick-reference router that maps every failing quality check — ESLint, TypeScript, markdownlint, jscpd, rust-code-analysis metrics, dependency-cruiser, Jest/Playwright coverage and visual tests,…

Run a BMAD spec-driven post-implementation review gate for React/TypeScript frontend work that blocks completion until every requirement row scores 5/5 and the gate reports zero new findings. Use when a GitHub PR, feature, bugfix, or task implemented against…

Run the full local frontend CI suite through the profile's make target map and drive every check to green before committing. Use when the user asks to run CI, run quality checks, validate frontend code quality, or before finishing any task that touches…

Systematically retrieve, categorize, and address PR code review comments with an auditable evidence ledger — AI review loop, per-comment commits, suppression-free fixes, and pushed-head verification of required checks and approval. Use when handling code…

Create a comprehensive frontend project documentation suite from scratch by analyzing the React/TypeScript codebase and verifying every claim against it. Use when setting up INITIAL documentation for a project or building a complete docs/ suite where none…

Hold a React frontend to its Lighthouse performance budgets (desktop 95 / mobile 85, integer-percent floors mapped by quality.lighthouse_desktop and quality.lighthouse_mobile), keep web-vitals, bundle size, and code-splitting healthy, defend deferred-DI…

Run and fix the frontend static-quality lane — formatting, ESLint, TypeScript, markdownlint, jscpd duplication, and rust-code-analysis metrics — through the profile's make target map, raise-only and with no suppressions. Use when the user asks to format code,…

Capture the modular (bulletproof-react) frontend architecture - module/feature layering, the Component -> Hook -> Repository -> API flow, dependency-cruiser import boundaries, and path-alias conventions. Use when placing a feature, component, hook, store, or…

Use when placing features, repositories, hooks, or fixing dependency-cruiser errors.

Use when improving frontend performance, Lighthouse, web-vitals, or a11y.

Keep the Bats make-target contract in sync when adding or renaming a Makefile target so the bats CI check stays green

Use when adding frontend telemetry, logs, Sentry, or web-vitals signals.

Use when configuring, running, sharding, or setting the threshold for Stryker mutation testing over a logic layer exercised by both the unit and integration Jest suites.

Use BEFORE building or changing any UI — components, layout, color, spacing, typography, interaction states, or visual styling — to verify the planned change matches the Figma design via the Figma MCP. Run this gate before writing or editing UI code.

Use when running or fixing formatting, lint, TypeScript, markdown, or metrics.

Use when choosing or interpreting frontend quality gates.

Use when touching the pinned user-service contracts — bumping USER_SERVICE_VERSION, editing a gql document under src/features, or fixing a red `make lint-contracts` / contract-testing.yml run. Covers the single upstream pin, the committed artifacts under…

Use when validating website changes before commit, push, or PR — picking which Makefile suites to run, in what order (make format, then focused tests, then make lint), and how to react to failures. Triggers: "ready to commit", "before PR", "is this CI-green",…

Use when authoring or updating documentation in the VilnaCRM website repo — feature READMEs under src/features, agent guides and SKILL.md skill docs under .claude/skills, or any Markdown that must pass make lint-md and make format. Covers website conventions…

Use when a change touches Makefile targets, the Next.js/Apollo/MUI stack, a src/features feature, the GraphQL schema or Apollo resolvers, i18n en/uk copy, dependency-cruiser boundaries, or .claude/skills, and the matching docs (agents.md, CLAUDE.md,…

Use when deciding which website test suite to run, picking the Jest client vs server vs integration env, or triaging a failing `make test-*` run — unit, e2e, visual, mutation, memory-leak, or load. Triggers on "which test should I run", "test-unit-client",…

Use when tuning website frontend performance or accessibility — running make lighthouse-desktop / make lighthouse-mobile, reading lighthouserc desktop/mobile budgets, reasoning about Core Web Vitals (LCP, CLS, INP), fixing MUI 9 / next-export-optimize-images…

Use when creating, running, or debugging K6 load tests under src/test/load (homepage.js, swagger.js) with make test-load / make load-tests / make test-load-swagger — covering the smoke, average, stress, and spike scenario types, config.json tuning, p(99)…

Use when wiring website frontend telemetry — Sentry browser init in pages/_app.tsx (@sentry/react), error boundaries, captureException with feature/route tags, the no-PII payload contract, sampling rates (tracesSampleRate / session replay), Next.js…

Add or extend API Platform resources in php-service-template using DDD and CQRS-friendly patterns.

Run the current php-service-template verification stack and fix failures without lowering quality thresholds.

Preserve PHPInsights quality standards for php-service-template without lowering thresholds.

Fix architectural boundary violations without editing deptrac.yaml.

Keep template-facing documentation and generated artifacts aligned with code changes.

Create or update K6-based load tests in php-service-template.

Maintain exported OpenAPI and GraphQL snapshots for php-service-template.

Reference the current protected quality gates for php-service-template.