ThibautBaissac/rails_ai_agents
Agent Claude Code
Creates idempotent, well-tested background jobs using Solid Queue with proper error handling and retry logic. Use when creating async tasks, scheduled jobs, or when user mentions background jobs, Solid Queue, or async processing. WHEN NOT: Synchronous operations that don't need background processing, real-time…
ThibautBaissac/rails_ai_agents
Agent Claude Code
Automatically corrects Ruby and Rails code style using RuboCop, ERB lint, and formatting tools. Use proactively after code changes to ensure style compliance. Use when fixing lint errors, standardizing code style, or when user mentions linting, RuboCop, code formatting, or style violations. WHEN NOT: Changing business…
ThibautBaissac/rails_ai_agents
Agent Claude Code
Creates Action Mailer emails with previews, templates, and delivery tests following Rails conventions. Use when building transactional emails, notifications, password resets, or when user mentions mailer, email, or notifications. WHEN NOT: Real-time notifications (use Action Cable), background processing logic (use…
ThibautBaissac/rails_ai_agents
Agent Claude Code
Creates safe, reversible database migrations with proper indexes, constraints, and zero-downtime strategies. Use when creating tables, adding columns, modifying schema, or when user mentions migrations, database changes, or schema updates. WHEN NOT: Model validations and associations (use model-agent), seeding data…
ThibautBaissac/rails_ai_agents
Agent Claude Code
Creates well-structured ActiveRecord models with validations, associations, scopes, and callbacks. Use when creating models, adding validations, defining associations, or when user mentions ActiveRecord, model design, or database schema. WHEN NOT: Adding business logic beyond data/persistence (use service-agent)…
ThibautBaissac/rails_ai_agents
Agent Claude Code
Creates secure Pundit authorization policies with comprehensive RSpec tests and scope restrictions. Use when adding authorization, restricting access, defining permissions, or when user mentions Pundit, policies, or role-based access. WHEN NOT: Implementing authentication (use authentication-flow skill), business…
ThibautBaissac/rails_ai_agents
Agent Claude Code
Creates presenter objects using SimpleDelegator for clean view formatting and display logic. Use when extracting view logic from models, formatting data, creating badges, or when user mentions presenters, decorators, or view models. WHEN NOT: Complex reusable UI elements (use viewcomponent-agent), business logic (use…
ThibautBaissac/rails_ai_agents
Agent Claude Code
Creates encapsulated, reusable query objects for complex database queries with composable scopes. Use when building reports, dashboards, aggregations, or when user mentions query objects, complex queries, or statistics. WHEN NOT: Simple one-liner queries that belong as model scopes, business logic (use service-agent)…
ThibautBaissac/rails_ai_agents
Agent Claude Code
Writes comprehensive RSpec tests for Rails models, controllers, services, and components with FactoryBot and Capybara. Use proactively after new code is written to ensure test coverage. Use when writing tests, adding test coverage, TDD RED phase, or when user mentions RSpec, specs, testing, or red-green-refactor. WHEN…
ThibautBaissac/rails_ai_agents
Agent Claude Code
Creates well-structured Rails service objects following SOLID principles with callable interface and error handling. Use when extracting business logic, creating complex operations, or when user mentions service objects, interactors, or PORO. WHEN NOT: Simple CRUD without business logic (use controller-agent…
ThibautBaissac/rails_ai_agents
Agent Claude Code
Creates accessible Stimulus controllers following Hotwire patterns with targets, values, and actions. Use when adding client-side behavior, form interactions, toggles, or when user mentions Stimulus, JavaScript controllers, or frontend interactions. WHEN NOT: Server-side rendering (use turbo-agent), simple show/hide…
ThibautBaissac/rails_ai_agents
Agent Claude Code
Styles Rails ERB views and ViewComponents using Tailwind CSS 4 utility classes and responsive design patterns. Use when styling views, building layouts, adding responsive design, or when user mentions Tailwind, CSS, styling, or UI design. WHEN NOT: Component Ruby logic (use viewcomponent-agent), JavaScript behavior…
ThibautBaissac/rails_ai_agents
Agent Claude Code
Improves code structure while keeping all tests green during the TDD REFACTOR phase using proven refactoring patterns. Use proactively after tests pass to clean up implementation code. Use when refactoring, extracting methods, reducing complexity, or when user mentions refactor phase, clean code, or code smells. WHEN…
ThibautBaissac/rails_ai_agents
Agent Claude Code
Implements Turbo Drive, Turbo Frames, and Turbo Streams for fast, responsive Rails applications with minimal JavaScript. Use when adding partial page updates, live updates, inline editing, or when user mentions Turbo, frames, or streams. WHEN NOT: Complex JavaScript interactions needing Stimulus controllers (use…
ThibautBaissac/rails_ai_agents
Agent Claude Code
Creates reusable ViewComponents with slots, previews, and comprehensive tests for Rails UI elements. Use when building cards, tables, badges, modals, or when user mentions ViewComponent, components, or reusable UI. WHEN NOT: Simple formatting logic (use presenter-agent), one-off view snippets that won't be reused, or…
ThibautBaissac/rails_ai_agents
Command Claude Code
Summarize what happened on the current branch since the developer's last contribution (commits, authors, stats, key changes).
ThibautBaissac/rails_ai_agents
Command Claude Code
Analyzes feature specifications and creates detailed TDD implementation plans with incremental PR breakdown and specialist agent assignments. Use when the user wants to plan feature implementation, break down a feature into tasks, or mentions implementation plan, feature planning, or TDD workflow. WHEN NOT: Writing…
ThibautBaissac/rails_ai_agents
Command Claude Code
Reviews feature specifications for completeness, clarity, and quality. Scores specs, identifies gaps, generates missing Gherkin scenarios, and provides actionable improvement suggestions. Use when the user wants to review a feature spec, validate requirements, or mentions spec review, specification quality, or…
ThibautBaissac/rails_ai_agents
Command Claude Code
Creates or refines feature specifications with Gherkin scenarios, edge cases, and PR breakdown. Use when specifying a new feature, refining a draft spec, writing requirements, or when user mentions feature specification, requirements gathering, user stories, or specification refinement. WHEN NOT: Reviewing existing…
ThibautBaissac/rails_ai_agents
Command Claude Code
Guides Test-Driven Development workflow with Red-Green-Refactor cycle. Use when the user wants to implement a feature using TDD, write tests first, follow test-driven practices, or mentions red-green-refactor.
ThibautBaissac/rails_ai_agents
Command Claude Code
Challenges stakeholder requests to identify real needs and propose optimal solutions. Use when receiving vague feature requests, reframing a problem before implementation, or when user mentions problem framing, XY problem, stakeholder request, or solution discovery. WHEN NOT: Well-defined technical tasks with clear…
ThibautBaissac/rails_ai_agents
Command Claude Code
Creates one polished, self-contained HTML artifact from a plan, PRD, roadmap, strategy, migration, rollout, research, operations, or implementation proposal. Use when the user asks for a visual plan explanation, walkthrough, artifact, or presentation.
ThibautBaissac/rails_ai_agents
Command Claude Code
Creates one polished, self-contained HTML artifact that explains a pull request or code change for reviewers, maintainers, product partners, and stakeholders.
ThibautBaissac/rails_ai_agents
Command Claude Code
Transforms vague or unstructured prompts into specific, actionable Claude Code prompts with clear objectives, constraints, and verification steps. Use when the user has a rough idea and wants a better prompt before running it, wants to optimize prompt quality, or mentions prompt improvement or prompt rewriting. WHEN…