LLM & Agents

Run automatically after completing any code changes. Validates TypeScript build, auto-fixes prettier and linting, then manually fixes any remaining issues.

Handle comprehensive project language and user setup workflows including language selection, agent prompt configuration, user profiles, team settings, and domain selection

Creates infrastructure as code configurations for cloud and on-premise deployments

Resolve disagreements between agents or approaches using test-based adjudication. Use when agents disagree, when multiple valid approaches exist, when the user asks "which approach", or when making architectural decisions with tradeoffs.

Supabase backend development: database, RLS, Edge Functions, queries.USE WHEN: creating tables, migrations, RPC functions, Edge Functions,RLS policies, query optimization, Supabase infrastructure.NOT FOR: Flutter UI (use flutter-developer), tests (use testing-agent).Examples:<example>Context: The user needs to create a new database table.user: "Create a table for customer reviews with ratings and comments"assistant: "I'll use the backend-dev skill to design the reviews table with RLS policies."<commentary>Database table creation requires backend-dev.</commentary></example><example>Context: The user needs server-side business logic.user: "Create an Edge Function to calculate dynamic pricing"assistant: "I'll use backend-dev to develop the Edge Function for pricing."<commentary>Edge Functions are a core backend-dev responsibility.</commentary></example>

CRITICAL: Use this skill when creating/debugging React UI components, Radix UI, forms, modals, or drag & drop.AUTO-ACTIVATE when user mentions (FR/EN): - select, Select, SelectValue, SelectItem, Radix - modal, modale, dialog, Dialog, DialogContent - form, formulaire, validation, Zod, React Hook Form, shadcn - drag, drop, DnD, @dnd-kit, sortable, réordonner - UI bug, composant, component, affiche ID, shows ID, undefined - Button, Input, Label, Checkbox, Switch, Badge, Card - créer composant, create component, nouveau composantThis skill contains TESTED patterns for Radix UI Select (ID vs Name), Modal CRUD templates, Drag & Drop with @dnd-kit, Form validation with Zod + shadcn/ui Form.

Expert SuperClaude prompt engineering assistant that analyzes user needs and crafts optimal prompts using the full SuperClaude framework - commands, flags, personas, MCP servers, wave orchestration, parallel execution patterns, continuous execution directives, and the new PM Agent orchestration system with PDCA cycles and Serena memory integration.

Review Claude Code plugin marketplace configurations against official best practices. Use when analyzing marketplace.json and plugin.json files for structural issues, common errors, path validation, and consistency with Anthropic's official format. Detects repository URL mismatches, incorrect source paths, and missing required fields.

Creates pull requests, deployment checklists, and manages release processes

Create complete Claude Code plugins with proper structure including skills, commands, agents, and hooks.Generates plugin manifests and directory structures for distribution.Use when: building plugins, creating plugin packages, distributing skills to marketplace.Activates for: "create plugin", "generate plugin", "new plugin", "plugin package", "make plugin"

Generates comprehensive unit tests for code

Guide and tooling for creating Claude Skills. Use when creating new skills or to analyze, understand, evaluate, update, or modify existing skills. Features additional skills for Claude Code. Includes design, implementation, and delivery phases.

Git CLI operations, workflows, and automation for modern development (2025). Use when working with repositories, commits, branches, merging, rebasing, worktrees, submodules, or multi-repo architectures. Includes parallel agent workflow patterns, merge strategies, conflict resolution, and large repo optimization. Triggers on git commands, version control, merge conflicts, worktree setup, submodule management, repository troubleshooting, branch strategy, rebase operations, cherry-pick decisions, and CI/CD git integration.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

AI-native E2E testing orchestration for Claude Code. Use when creating, running, or managing end-to-end test scenarios with visual evidence capture. Activates for tasks involving E2E tests, browser automation testing, test scenario creation, test execution with screenshots, or checking test status.

Manages file storage with AWS S3 using the JavaScript SDK v3. Use when uploading files, generating presigned URLs, managing buckets, or implementing cloud storage in Node.js applications.

Get OpenAI Codex CLI's opinion on code, bugs, or implementation. Use when you want a second AI perspective during coding sessions.

Conduct comprehensive codebase research by spawning parallel agents to document and explain code as it exists. Use this skill when needing to understand how a codebase works, where specific functionality lives, or what patterns exist. This skill orchestrates specialized agents (codebase-locator, codebase-analyzer, codebase-pattern-finder) and synthesizes findings into structured documentation.

This skill teaches the agent how to manage database schemas and migrations in the API project. MANDATORY - You MUST read this skill before modifying any database schema or migration files.

Code generation and file modification agent with delegation capabilities