Claude Skills by aiFabricoCom

Create a new custom skill (.claude/skills/<name>/SKILL.md) for Claude Code. Analyzes existing skills for patterns, guides through design decisions, creates the skill file with supporting resources, and validates against best practices.

Design the architecture to solve a given task. Propose the solutions to be used to deliver the task following the best practices and standards.

Builds and reviews admin dashboards with the mandatory Laravel, MySQL 8, Redis, Docker, Vue 3, Inertia, TypeScript, Tailwind, and shadcn-vue stack. Use for every greenfield admin panel, back-office, operations console, internal dashboard, CRUD console, or material admin UI extension; flags existing-stack conflicts before implementation.

Builds repeatable Laravel admin CRUD resources from versioned field and table definitions using shadcn-vue, VeeValidate/Zod, TanStack Table, and server-side Laravel validation and querying. Use when creating CRUD forms, dynamic forms, data tables, filters, resource pages, schema-driven admin modules, or reusable admin blocks; keeps database-stored JSON schemas limited to genuinely runtime-configurable forms.

Builds cost-efficient, high-quality applications using a modular-monolith default, explicit service and dependency budgets, reusable golden paths, risk-based tests, and evidence-based scaling triggers. Use for every new application, material feature, architecture plan, deployment design, build-versus-buy decision, or cost and complexity review; prevents speculative microservices, Kubernetes, paid services, and premature infrastructure.

Performs extremely strict code and maintainability reviews against requirements, implementation plans, project conventions, and executable quality gates. Use for code reviews, thermo-nuclear or thermonuclear reviews, deep code-quality audits, and harsh maintainability reviews that must uncover structural regressions, spaghetti branching, weak abstractions, oversized files, boundary or type problems, security risks, and missing tests.

Analyse the codebase of the system. Look for dependencies. Understand how the business logic is implemented. Look for duplications.

Create custom subagents (.claude/agents/*.md) for Claude Code. Provides templates, guidelines, and a structured process for building subagent definitions that describe behavior, personality, responsibilities, and problem-solving approaches. Use when creating, reviewing, or updating Claude Code subagent files.

Creates Claude Code memory files (CLAUDE.md) for Claude Code. Covers the root project memory (CLAUDE.md) and nested, directory-scoped memory files, plus @import references. Provides templates and a decision framework for memory vs. skill placement. Use when creating, reviewing, or updating CLAUDE.md memory files.

Create custom slash commands (.claude/commands/*.md) for Claude Code. Provides templates, guidelines, and a structured process for building command files that trigger specific workflows, optionally delegating to the right subagent. Use when creating, reviewing, or updating .claude/commands/*.md files.

Creates and reviews repository skills under .claude/skills using gerund naming, concise routing descriptions, progressive disclosure, templates, and validation checklists. Use when creating, reviewing, updating, or organizing SKILL.md files.

Evaluate code changes for quality, correctness, and adherence to project standards. Use when reviewing pull requests, verifying implementations against acceptance criteria, or auditing code for best practices.

Design multi-cloud architectures using a decision framework to select and integrate services across AWS, Azure, and GCP. Use when building multi-cloud systems, avoiding vendor lock-in, or leveraging best-of-breed services from multiple providers.

E2E testing patterns, verification procedures, and CI readiness checklists using Playwright. Use for writing, debugging, or reviewing end-to-end tests, fixing flaky tests, creating Page Objects, mocking external APIs.

LLM prompt engineering patterns: structure, optimization, security, templates, evaluation, and anti-patterns. Use when designing, writing, optimizing, or reviewing prompts for LLM applications (system prompts, user prompts, RAG templates, agent instructions, chatbot personas). NOT for Claude Code customization — use fabrico-creating-prompts for that.

WCAG 2.1 AA compliance, semantic HTML, ARIA patterns, keyboard navigation, focus management, screen reader support, and color contrast requirements. Use when implementing accessible components, auditing UI for accessibility issues, reviewing frontend code for a11y compliance, or building inclusive forms and interactive widgets.

Implementation gap analysis. Verify what has to be implemented. Verify what was implemented. Compare plan to current state.

Backend service implementation patterns, standards, and procedures. Use for building REST/GraphQL APIs, implementing CRUD endpoints, database handling, authentication, testing strategies, external service integrations, filtering/pagination (DataGrid), logging, Docker setup, and modular architecture. Applies to Node.js, PHP, .NET, Java, and Go backends.

CI/CD pipeline design patterns and deployment strategies. Use when designing pipelines, implementing deployment strategies, or setting up automated delivery.

Form architecture, schema-based validation, field composition, error handling, multi-step form flows, and accessible form patterns. Use when building forms, implementing validation, creating multi-step wizards, or integrating form fields with a component library.

Frontend component patterns, composition, design token integration, barrel file organization, error handling, and Figma-to-code workflow. Use when implementing UI components, translating Figma designs into code, managing component state, or integrating with a design system.

Kubernetes deployment patterns, Helm charts, and cluster management. Use when deploying applications to K8s, designing workload configurations, implementing scaling strategies, or managing cluster resources.

Observability patterns for logging, monitoring, alerting, and distributed tracing. Use when implementing metrics collection, log aggregation, alerting rules, or distributed tracing across services.

Build reusable Terraform modules for AWS, Azure, and GCP infrastructure following infrastructure-as-code best practices. Use when creating infrastructure modules, standardizing cloud provisioning, or implementing reusable IaC components.

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to i...

Audit and verify existing web, iOS, Android, and shared-mobile UIs using runtime evidence, platform conventions, accessibility, prioritized findings, and before/after comparisons. Use for UI improvement audits, mobile visual reviews, responsive checks, or cross-platform UI verification without requiring Figma.

Transform extracted epics and user stories into Jira-ready format following a benchmark template. Handles field mapping, formatting for Jira markdown compatibility, two-gate user review, and guidance for Jira issue creation via Atlassian tools.

Secrets management patterns for cloud and Kubernetes environments. Use when implementing secure credential storage, rotation, or CI/CD authentication.

Optimize cloud costs through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.

Frontend rendering optimization, code splitting, memoization strategies, bundle size control, asset optimization, and memory management. Use when optimizing component rendering, reducing bundle size, debugging performance issues, implementing lazy loading, or reviewing code for performance regressions.

Plan the migration of a legacy web app to a modern target — modern web (Next.js/React), native iOS (SwiftUI), or cross-platform mobile (React Native/Expo). Maps old behavior to a target stack, builds a feature-parity matrix, plans data and auth migration, adapts desktop UX to mobile where needed, and flags risks. Use after reverse-engineering a SPEC.md and before rebuilding with /fabrico-autopilot.

Prepares application architecture, data flows, operations, and quality gates for safe AI capabilities without coupling the product to one model provider. Use whenever building a new application, materially extending an existing application, adding LLM or agent features, or reviewing whether a system is AI-ready.

Prepares applications for SaaS delivery through tenant isolation, identity, roles, entitlements, metering, billing boundaries, auditability, lifecycle operations, and production safeguards. Use whenever building a new application, materially extending an existing application, adding organizations or subscriptions, or reviewing SaaS readiness.

Reverse-engineer a complete, platform-agnostic SPEC.md from a running legacy web application by inspecting it with the Playwright MCP (Chrome automation): crawl routes, capture every screen, infer the data model, roles, flows, and integrations, then synthesize features into user stories with acceptance criteria. Use when modernizing an old web app to a newer stack or porting it to mobile/iOS. Produces a SPEC.md compatible with /fabrico-autopilot.

Frontend-specific code review criteria, component anti-patterns, hooks quality, rendering correctness, accessibility and performance spot-checks, and module organization issues. Use when reviewing frontend pull requests, auditing component quality, or identifying UI-specific code smells beyond general code review.

SQL writing and database engineering patterns, standards, and procedures. Use for designing database schemas, writing performant SQL queries, normalisation strategies, indexing, joins optimisation, locking mechanics, transactions, query debugging with EXPLAIN, and ORM integration. Applies to PostgreSQL, MySQL, MariaDB, SQL Server, and Oracle. Covers ORM usage with TypeORM, Prisma, Doctrine, Eloquent, Entity Framework, Hibernate, and GORM.

Analyse task description, performs gap analysis, expand the context for the task, analyse the current state of the system in the context of the task, helps build PRD, creates a context for the task, gathers information about the task from different sources.

Identify and structure epics and user stories from workshop materials (cleaned transcripts, Figma designs, codebase analysis, and other documents). Produces a business-oriented task breakdown with dependencies, assumptions, and open questions.

Analyze extracted epics and user stories for quality gaps, missing edge cases, and improvement opportunities. Runs domain-agnostic analysis passes, optionally enriches findings with Jira board context, and produces accept/reject suggestions that refine the task list before Jira formatting.

Discover and establish technical context before implementing any feature. Prioritize project instructions, existing codebase patterns, and external documentation in that order. Use for any task requiring understanding of project conventions, coding standards, architecture patterns, and established practices before writing code.

Clean raw workshop or meeting transcripts from small talk, filler words, and off-topic tangents. Extract and structure business-relevant content into a standardized format with discussion topics, key decisions, action items, and open questions.

UI verification criteria, structure checklists, severity definitions, and tolerance rules for comparing implementations against Figma designs. Use for verifying UI matches design, understanding what to check, and determining acceptable differences.

Custom hook and composable patterns — naming, composition, stable return shapes, lifecycle cleanup, and testing strategies. Use when writing reusable logic units (React hooks, Vue composables), refactoring logic into hooks, debugging hook behavior, or reviewing hook implementations.