ts-dev-kit

TypeScript coding conventions for strict, type-safe projects. Use when: (1) writing or reviewing TypeScript code, (2) choosing between `any` and `unknown`, (3) structuring imports with verbatimModuleSyntax, (4) defining types, interfaces, unions, or generics, (5) naming functions, booleans, queries, and commands, (6) handling errors with guard clauses and early returns, (7) narrowing types with guards and discriminated unions, or (8) avoiding common anti-patterns like primitive obsession, magic strings, and premature abstraction.

BullMQ queue system reference for Redis-backed job queues, workers, flows, and schedulers. Use when: (1) creating queues and workers with BullMQ, (2) adding jobs (delayed, prioritized, repeatable, deduplicated), (3) setting up FlowProducer parent-child job hierarchies, (4) configuring retry strategies, rate limiting, or concurrency, (5) implementing job schedulers with cron/interval patterns, (6) preparing BullMQ for production (graceful shutdown, Redis config, monitoring), or (7) debugging stalled jobs or connection issues

Adapts ts-dev-kit plugin files to the host project where it is installed. Use when: (1) installing ts-dev-kit in a new project for the first time, (2) project tech stack or structure has changed, (3) agents reference wrong paths, unavailable skills, or missing MCPs, (4) the user says 'adapt the plugin', 'configure ts-dev-kit for this project', 'sync plugin to this codebase', or 'update plugin context'. Surgically edits specific sections in plugin skills and agent definitions — domain area tables, skill/MCP references, quality gate commands, project paths, and package names — without touching any workflow logic, execution protocols, or dispatch patterns.

React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.

Core Web Vitals reference for measuring, diagnosing, and improving LCP, INP, and CLS. Use when: (1) auditing page performance against Google's thresholds, (2) implementing the web-vitals JS library for field monitoring, (3) diagnosing slow LCP, high INP, or layout shifts, (4) choosing between field and lab measurement tools, (5) optimizing specific metrics with the Chrome team's top recommendations, (6) explaining what each metric measures to non-technical stakeholders, or (7) generating a visual CWV report from metric values or a Lighthouse JSON file.

Docker containerization reference — multi-stage builds, Compose configs, image optimization, and container security for Yarn 4 monorepos. Use when: (1) creating or optimizing Dockerfiles, (2) configuring docker-compose for dev or production, (3) reducing image size with multi-stage builds, (4) hardening container security, or (5) setting up health checks and resource limits.

Drizzle ORM reference for PostgreSQL — schema definition, typesafe queries, relations, and migrations with drizzle-kit. Use when: (1) defining pgTable schemas with column types, indexes, constraints, or enums, (2) writing select/insert/update/delete queries or joins, (3) defining relations and using the relational query API (db.query.*), (4) running drizzle-kit generate/migrate/push/pull, (5) configuring drizzle.config.ts, (6) using the sql`` template operator, or (7) working with PostGIS/pg_vector extensions.

Fastify 5 best practices, API reference, and patterns for routes, plugins, hooks, validation, error handling, and TypeScript. Use when: (1) writing new Fastify routes, plugins, or hooks, (2) looking up Fastify API signatures or options, (3) debugging Fastify issues (lifecycle, encapsulation, validation, plugin timeout), (4) reviewing Fastify code for anti-patterns. Triggers: 'add a route', 'create plugin', 'Fastify hook', 'validation schema', 'Fastify error', 'setErrorHandler', 'fastify-plugin'.

"Generates a complete, structured, and implementation-ready Product Requirements Document (PRD). Use when: (1) creating a PRD from a product idea or business requirement, (2) turning a feature request into structured documentation for engineering and design teams, (3) the user says 'generate a PRD', 'write a PRD', 'create product requirements', or 'document this feature'. Covers vision, problem statement, objectives, scope, personas, user journeys, functional and non-functional requirements, constraints, success metrics, assumptions, risks, and acceptance criteria.'

ioredis v5 reference for Node.js Redis client — connection setup, RedisOptions, pipelines, transactions, Pub/Sub, Lua scripting, Cluster, and Sentinel. Use when: (1) creating or configuring Redis connections (standalone, cluster, sentinel), (2) writing Redis commands with ioredis (get/set, pipelines, multi/exec), (3) setting up Pub/Sub or Streams, (4) configuring retryStrategy, TLS, or auto-pipelining, (5) working with Redis Cluster options (scaleReads, NAT mapping), or (6) debugging ioredis connection issues. Important: use named import `import { Redis } from 'ioredis'` for correct TypeScript types with NodeNext.

Next.js App Router best practices — file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling. Use when writing, reviewing, or debugging Next.js App Router code.

Review code and architectures against the OWASP Top 10:2025 — the ten most critical web application security risks. Use when: (1) reviewing code for security vulnerabilities, (2) auditing a feature or codebase against OWASP categories, (3) providing remediation guidance for identified vulnerabilities, (4) writing new code and needing secure coding patterns. Triggers: 'review for security', 'OWASP audit', 'check for vulnerabilities','security checklist', 'is this code secure', 'security review', 'fix vulnerability'.

PostgreSQL 16+ reference for writing queries, designing schemas, managing indexes, and optimizing performance. Use when: (1) writing SQL queries (SELECT, INSERT, UPDATE, DELETE, CTEs, window functions, subqueries), (2) designing or altering table schemas (CREATE TABLE, constraints, sequences, data types), (3) choosing or creating indexes (B-tree, GIN, GiST, BRIN, partial, expression), (4) managing transactions and isolation levels (BEGIN/COMMIT, savepoints, MVCC), (5) working with JSONB data and jsonpath, (6) analyzing query performance with EXPLAIN ANALYZE, or (7) using the psql CLI.

React and Next.js performance patterns. Use when writing, reviewing, or optimizing React components.

Service Worker API implementation guide — registration, lifecycle management, caching strategies, push notifications, and background sync. Use when: (1) creating or modifying service worker files (sw.js), (2) implementing offline-first caching (cache-first, network-first, stale-while-revalidate), (3) setting up push notifications or background sync, (4) debugging service worker registration, scope, or update issues, (5) implementing navigation preload, (6) user mentions 'service worker', 'sw.js', 'offline support', 'cache strategy', 'push notification', 'background sync', 'workbox alternative', or 'PWA caching'.

TanStack Query v5 (React Query) reference for data fetching, caching, and server state management in React. Use when: (1) writing useQuery, useMutation, or useInfiniteQuery hooks, (2) setting up QueryClient and queryOptions, (3) implementing optimistic updates or cache invalidation, (4) configuring SSR/hydration with Next.js App Router or Pages Router, (5) testing React Query hooks, (6) working with TypeScript types, Suspense, or advanced patterns like dependent queries and infinite scroll.

Review UI code for Web Interface Guidelines compliance. Use when asked to review UI, check accessibility, audit design, review UX, or check against best practices.

Sets up and launches a Claude Code devcontainer with --dangerously-skip-permissions for fully autonomous, unattended operation inside a sandboxed environment. Use when: (1) user wants to run Claude Code without permission prompts, (2) setting up a secure development container for autonomous coding, (3) user says 'yolo', 'yolo mode', 'run without permissions', 'autonomous mode', 'skip permissions safely', or 'devcontainer setup'.

Executes a task, either from a TASK_N.md file or a free-form description. Use when: (1) implementing a task from a TASK_N.md file, (2) the user provides a task file path or says 'execute this task', 'implement TASK_02', or 'run this task', (3) the user describes a task directly without a document. Accepts a file path or a free-form description — if the task document is missing required sections (scope, success criteria, verification plan), automatically calls /generate-tasks to produce it before executing.

End-to-end debugging workflow that triages, reproduces, and fixes bugs across the full stack using multi-agent orchestration. Use when: (1) encountering runtime errors in the API or web app, (2) investigating failed requests or broken user flows, (3) debugging production issues via Sentry/PostHog, (4) tracing data flow across backend and frontend, or (5) the user reports a bug that spans multiple layers.

Write, review, and validate commit messages following the Conventional Commits v1.0.0 specification. Use when: (1) crafting a git commit message for any change, (2) reviewing or correcting an existing commit message, (3) choosing the right commit type for a change, (4) deciding how to mark a breaking change, (5) writing multi-line commits with body and footers, or (6) understanding how commits map to SemVer bumps (PATCH/MINOR/MAJOR). Covers all standard types: feat, fix, docs, chore, refactor, perf, test, build, ci, style, revert.

Breaks a PRD into ordered, production-ready engineering tasks ready for execution by /execute-task. Use when: (1) converting a PRD document into executable engineering tasks, (2) planning feature delivery as a sequence of mergeable, self-contained pull requests, (3) the user says 'generate tasks', 'break down this PRD', 'create tasks from PRD', 'plan the implementation tasks', or 'task breakdown'. Each generated task document embeds its own success criteria, baseline checks, post-change tests, performance benchmarks, and non-functional requirements — making it directly executable by /execute-task.