By igmarin
Curated library of AI agent skills for Ruby on Rails development. Includes code review, architecture, security, testing (RSpec), engines, service objects, DDD patterns, and workflow automation.
Orchestrates the full Rails TDD cycle with hard gates: test MUST exist, be run, and FAIL for the correct reason (e.g. undefined method, not syntax error) before any implementation code — propose minimal implementation and wait for user approval → verify test PASSES → run full suite with rubocop, brakeman, rspec all green → produce YARD documentation and self-reviewed PR; phases context/test design→implementation→iterate→finish. Use when practicing test-driven development, red-green-refactor, TDD workflow, writing tests before code, adding tests first, or building a Rails feature where specs must gate implementation.
Use when planning tests for a Rails change — must present a Test Design Review checkpoint, pick the smallest strong slice matched to where the real risk lives, write exactly one minimal failing example as the initial TDD gate (list additional cases as follow-up), verify that the test fails because behavior is missing rather than broken setup, and use assets/first_slice_template.md to document the plan. TDD, first failing test, spec selection, vertical slice planning.
Use when creating or modifying REST API endpoints — must create or update the corresponding API collection JSON file using the {{base_url}} variable, ensure each request includes a description and at least one basic test script, validate the collection JSON using python -m json.tool or jq, and verify it imports into compatible API clients without errors. Sync API collections with REST endpoints. Trigger words: endpoint, API route, controller action, API collection, request collection.
Use when building or reviewing GraphQL APIs in Rails with graphql-ruby — must follow the TDD gates by writing a failing spec in spec/graphql/ using AppSchema.execute rather than HTTP controller dispatch, define arguments/return types without leaking internal model names (use connection_type for pagination), implement resolver/mutation classes that delegate to services, prevent N+1 queries by using and priming the dataloader on association loads, and ensure mutations return result and errors shapes on failure. Trigger words: graphql, graphql-ruby, resolver, mutation, dataloader, schema.
Use when applying code conventions to Rails files — must run linter (detect .rubocop.yml/.standard.yml, note absence, and state which linter was detected and that style defers to it), apply area-specific rules per path with concrete per-path recommendations, verify tests gate (state the failing spec, run command, expected failure, minimal implementation step, and passing rerun) BEFORE new behavior, chain to specialised skills, only recommend let_it_be if test-prof already in Gemfile.lock (otherwise default to let, reach for "let!" only if lazy evaluation breaks example, do not introduce test-prof), and load extended files (assets/checklist.md, assets/snippets.md) only when needed. Use when writing, reviewing, or refactoring Ruby on Rails code. Trigger words: code review, refactor, RoR, clean code, best practices.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Executables (bin/) — files in this plugin's bin/directory are added to the Bash tool's PATH while the plugin is enabled.
It is a curated library of public Rails agent skills and callable personas that teach AI tools how to test, implement, document, and review Rails work using production-minded conventions. This repository acts as a pure Domain Knowledge Registry and asset catalog of specialized Rails & Ruby AI Skills/Personas, consumable by external MCP or CLI runtimes.
The project is built around one non-negotiable rule:
Write test -> run test -> verify it fails for the right reason -> implement -> verify it passes
That TDD gate is encoded directly into the skills and personas, so agents do not just produce plausible Rails code. They follow a repeatable engineering process.
This repo is one of 6 in a composable AI skill ecosystem:
| Repo | Role |
|---|---|
ruby-core-skills | 15 shared Ruby skills + process discipline |
rails-agent-skills | 28 atomic skills + 9 personas |
hanakai-yaku | 35 atomic skills + 10 personas |
agnostic-planning-skills | 10 atomic skills + 4 personas |
agent-mcp-runtime | Rust CLI runtime (pack resolution, MCP) |
ruby-skill-bench | Benchmark/eval engine |
See the Ecosystem Overview for the full architecture.
This repo depends on ruby-core-skills. See Migration Guide.
Supported agent environments
Official distribution
Agent Skills are a lightweight, open format for extending AI agent capabilities with specialized knowledge and workflows. At its core, a skill is a folder containing a SKILL.md file. This file includes metadata (name and description, at minimum) and instructions that tell an agent how to perform a specific task.
This repository follows the Agent Skills standard, meaning you can install the entire catalog of Rails skills atomically into any compatible agent (e.g., Cursor, Claude Code, Goose, OpenCode, Gemini CLI) using:
npx skills add igmarin/rails-agent-skills
Note: You may see a harmless warning at the end of the install:
✗ rails-agent-skills → PromptScript: PromptScript does not support global skill installationThis is a known bug in the skills.sh CLI where the PromptScript agent is incorrectly included in the global install target list despite not supporting it. All 37 skills install successfully to every other supported agent — the warning can be safely ignored.
npx claudepluginhub igmarin/rails-agent-skillsHanami 2.x development skills for Claude Code
Integrated Rust development skills for multiple domains (UI, Robotics, etc.)
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
A la carte AI skills for LLM-assisted development
Professional skill creation with TDD workflow. Features dual-mode (fast/full), behavioral validation, and automated quality gates for 9.0/10+ scores.
Core ACE workflow with TDD-based skills, task enforcement, and quality reviewers
Editorial "Agent Architect" bundle for Claude Code from Antigravity Awesome Skills.