Server data from the Official MCP Registry
Rails development skills, docs, and workflows exposed through MCP stdio.
Rails development skills, docs, and workflows exposed through MCP stdio.
Valid MCP server (2 strong, 3 medium validity signals). No known CVEs in dependencies. Imported from the Official MCP Registry.
8 files analyzed · No issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
From the project's GitHub README.
Rails Agent Skills turns AI coding assistants into disciplined Rails collaborators.
It is a curated library of 42 public Rails agent skills and 5 callable workflows that teach AI tools how to plan, test, implement, document, and review Rails work using production-minded conventions.
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 workflows, so agents do not just produce plausible Rails code. They follow a repeatable engineering process.
Supported agent environments
Official distribution
| Reader | What you get |
|---|---|
| Rails developers | Agent instructions for common Rails work: tests, services, APIs, GraphQL, migrations, jobs, Hotwire, engines, security, and review. |
| Team leads | A repeatable workflow that makes AI-assisted work easier to review because tests, docs, and self-review are part of the process. |
| Junior developers | Step-by-step Rails workflow guidance that explains what to do next instead of dumping generic code. |
| Senior developers | Opinionated guardrails for TDD, architecture, review, DDD, engines, performance, and production-safe changes. |
| Recruiters and evaluators | A concrete example of AI tooling designed around engineering discipline, validation, and distribution. |
| Area | Purpose |
|---|---|
skills/ and build/ | 42 public atomic skills. Each skill has a SKILL.md entry point with task-specific instructions. |
workflows/ | 5 callable workflows that chain skills into full development loops. |
docs/ | Public documentation, architecture, workflow guides, skill catalog, and evaluation policy. |
mcp_server/ | Official Ruby MCP server exposing docs, workflows, and use_skill. |
tessl-evals/ | Tessl-native eval scenarios for publishable skills in tile.json. |
personal-evals/ | Open examples for the upcoming ruby-skill-bench full-context evaluator. |
The skills are not long-form tutorials. They are executable instructions for AI agents: when to gather context, when to stop for a checkpoint, how to write the first failing test, what Rails conventions to apply, and how to review the result.
The recommended way to use this library is through the MCP server. MCP keeps the agent context small: docs and workflows are exposed as resources, and individual skills are loaded on demand. The use_skill tool returns a specific skill's SKILL.md only when the agent needs it.
| Path | Best for | Start here |
|---|---|---|
| Official MCP Registry | Finding the verified MCP server metadata and latest published version | MCP registry entry |
| Docker Hub image | Running without a local Ruby toolchain | Docker image |
| Cloudflare Worker | Hosted Streamable HTTP MCP for registries and hosted clients | health check |
| Smithery | Discovering and connecting through Smithery's MCP gateway | Smithery listing |
| Local Ruby/Bundler | Local development, debugging, and repository checkout workflows | mcp_server/README.md |
| GitHub CLI skills | Installing selected skills into a specific agent host | GitHub CLI install |
For hosted MCP clients and registries that support Streamable HTTP, use the Cloudflare Worker endpoint:
https://rails-agent-skills-mcp.ismael-marin.workers.dev/mcp
Useful public checks:
Health: https://rails-agent-skills-mcp.ismael-marin.workers.dev/health
Server card: https://rails-agent-skills-mcp.ismael-marin.workers.dev/.well-known/mcp/server-card.json
For repeatable team installs, prefer the versioned Docker image published from a Git release tag:
{
"mcpServers": {
"rails-agent-skills": {
"type": "stdio",
"command": "docker",
"args": ["run", "--rm", "-i", "igmarin/rails-agent-skills-mcp:5.1.5"]
}
}
}
For local development, clone the repo and run the Ruby server:
git clone https://github.com/igmarin/rails-agent-skills.git ~/rails-agent-skills
cd ~/rails-agent-skills/mcp_server
bundle install
bundle exec ruby server.rb
See mcp_server/README.md for host-specific MCP configuration for Claude Code, Cursor, Windsurf, RubyMine, OpenCode, and other stdio MCP clients.
When configuring MCP in external tools, use absolute paths for cwd and BUNDLE_GEMFILE. Relative paths and ~ are a common cause of gem-loading and timeout failures.
Most Rails work should start with the TDD feature loop:
load-context
-> plan-tests
-> write-tests
-> verify failing test
-> implement
-> verify passing test
-> write-yard-docs
-> code-review
For a new feature from scratch:
create-prd -> generate-tasks -> TDD feature loop
For a bug:
triage-bug -> plan-tests -> failing reproduction spec -> minimal fix -> code-review
For a Rails engine:
create-engine -> test-engine -> document-engine -> review-engine -> release-engine
See docs/workflow-guide.md and docs/workflows/ for the full workflow guide.
The library contains 42 public skills organized by Rails development concern.
| Category | Examples |
|---|---|
| Planning | create-prd, generate-tasks, plan-tickets |
| Testing | plan-tests, write-tests, test-service, triage-bug |
| Code quality | code-review, respond-to-review, security-check, refactor-code |
| Architecture and DDD | define-domain-language, review-domain-boundaries, model-domain, review-architecture |
| Rails implementation | create-service-object, implement-background-job, implement-authorization, implement-hotwire |
| APIs | generate-api-collection, implement-graphql, integrate-api-client, version-api |
| Engines | create-engine, test-engine, document-engine, release-engine, upgrade-engine |
| Infrastructure | review-migration, optimize-performance, seed-database |
| Orchestration | skill-router, build |
Use docs/reference/skill-catalog.md for the complete catalog and docs/reference/integration-matrix.md for skill chaining.
This repo uses two complementary evaluation layers.
| Layer | Status | What it validates |
|---|---|---|
| Tessl | Public and active | Tessl-native scenarios in tessl-evals/ validate the quality of publishable skills from tile.json. Tessl does not validate repository workflows today. |
ruby-skill-bench | Coming soon | The upcoming Ruby gem will run personal-evals/ examples with full skill or workflow context, including SKILL.md plus companion resources bundled as XML. |
Root evals/ is generated Tessl staging output and must stay untracked. tessl-evals/ is the tracked Tessl source. personal-evals/ is the tracked source for open custom-evaluator examples.
See docs/eval-provenance.md for the canonical eval ownership policy and docs/skill-optimization-guide.md for the baseline-vs-context optimization loop.
Requires GitHub CLI v2.90.0+ with gh skill.
# Install all skills interactively
gh skill install igmarin/rails-agent-skills
# Install a specific skill for the current project
gh skill install igmarin/rails-agent-skills code-review --scope project
# Install a specific skill globally
gh skill install igmarin/rails-agent-skills code-review --scope user
# Install pinned to a release tag
gh skill install igmarin/rails-agent-skills code-review --pin v5.1.5 --scope user
# Search this repository's skills
gh skill search rails --owner igmarin
To target a specific agent host:
gh skill install igmarin/rails-agent-skills plan-tests --agent claude-code --scope user
gh skill install igmarin/rails-agent-skills plan-tests --agent cursor --scope user
gh skill install igmarin/rails-agent-skills plan-tests --agent codex --scope user
gh skill install igmarin/rails-agent-skills plan-tests --agent gemini-cli --scope user
gh skill install igmarin/rails-agent-skills plan-tests --agent windsurf --scope user
Update installed skills:
gh skill update --dry-run
gh skill update --all
gh skill update --force --all
gh skill update --unpin
Pinning to a tag or commit SHA gives you reproducible installs. Provenance metadata is written into each installed SKILL.md frontmatter.
| Need | Document |
|---|---|
| Understand the docs system | docs/README.md |
| Install and configure MCP | mcp_server/README.md |
| Browse all skills | docs/reference/skill-catalog.md |
| Understand skill chaining | docs/reference/integration-matrix.md |
| Follow workflow guides | docs/workflow-guide.md |
| Understand repository structure | docs/architecture.md |
| Understand eval ownership | docs/eval-provenance.md |
| Optimize skill eval quality | docs/skill-optimization-guide.md |
When contributing skills, workflows, docs, or MCP behavior:
evals/ output.tile.json, server.json, and the latest release tag.Huge thanks to Mumo Carlos (@mumoc). His mentorship shaped many of the habits reflected here, especially the discipline around quality, clarity, and thoughtful use of tools.
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.