Curated library of 39 AI agent skills for Ruby on Rails development. Organized by category: planning, testing, code-quality, ddd, engines, infrastructure, api, patterns, context, orchestration, and workflows. Includes 5 callable workflow skills (rails-tdd-loop, rails-review-flow, rails-setup-flow, rails-quality-flow, rails-engines-flow) for complete development cycles. Covers code review, architecture, security, testing (RSpec), engines, service objects, DDD patterns, and TDD automation.
95
98%
Does it follow best practices?
Impact
95%
1.20xAverage score across 35 eval scenarios
Passed
No known issues
Use this template when creating a new skill for the library.
For detailed guidance on skill design, read the official Skill Design Principles.
Prefer improving an existing skill before creating a new one. Create a new skill only when the workflow has a distinct trigger, a different decision tree, or a HARD-GATE that would bloat another skill.
Capture these decisions first:
If you cannot answer those five clearly, refine an existing skill instead of creating a new one.
rails-agent-skills/
└── your-skill-name/
├── SKILL.md # Required: main skill file
├── reference.md # Optional: supplementary reference material
└── examples.md # Optional: example outputs or edge cases---
name: your-skill-name
description: >
[Concise paragraph (1-3 sentences). First sentence states primary purpose.
Focus on trigger words and outcomes for LLM discovery].
---
# Your Skill Title
Use this skill when [brief one-line trigger].
**Core principle:** [One sentence that captures the skill's philosophy]
## Quick Reference
| Aspect | Rule |
|--------|------|
| Key concept 1 | Brief rule |
| Key concept 2 | Brief rule |
| Key concept 3 | Brief rule |
## HARD-GATE
<!-- Only include if the skill has non-negotiable rules -->
\```
DO NOT [forbidden action that must never be skipped].
ALWAYS [required action that must always happen].
\```
## Checkpoints
<!-- Only include if the skill introduces a pause-and-confirm step (not a hard blocker).
Checkpoints differ from HARD-GATEs: they pause for collaboration, not to enforce a rule. -->
### [Checkpoint Name]
1. Present: [what to show the user]
2. Ask: [specific questions to confirm before proceeding]
3. Confirm: [what approval looks like — only proceed once confirmed]
## When to Use
- Trigger condition 1
- Trigger condition 2
- **Next step:** [What to suggest after this skill completes]
## Process
1. **Step name:** Description of what to do.
2. **Step name:** Description of what to do.
3. **Step name:** Description of what to do.
4. **Verify:** Run verification and confirm results with evidence.
## Examples
**Good:**
\```ruby
# Good example with explanation
\```
**Bad:**
\```ruby
# Bad example with explanation of why it's bad
\```
## Common Mistakes
| Mistake | Reality |
|---------|---------|
| "Common excuse or bad practice" | Why it's wrong and what to do instead |
| "Another common mistake" | The correct approach |
## Red Flags
- Signal that the skill is being violated
- Another warning sign
- Pattern that indicates a problem
## Integration
| Skill | When to chain |
|-------|---------------|
| **related-skill-1** | When [condition triggers the related skill] |
| **related-skill-2** | When [condition triggers the related skill] |Refer to the Skill Design Principles for all naming, description, content, and formatting conventions.
Refer to the Skill Design Principles for required sections and their priority.
Refer to the Skill Design Principles for guidance on progressive disclosure.
Refer to the Skill Design Principles for guidance on when to create a new skill versus extending an existing one.
Refer to the Skill Design Principles for the comprehensive quality checklist.
README.mdREADME.md if the skill connects to existing skillsrails-skills-orchestrator/SKILL.md discovery tableCLAUDE.md skill catalog (this is the first file Claude reads)docs
evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
scenario-19
scenario-20
scenario-21
scenario-22
scenario-23
scenario-24
scenario-25
scenario-26
scenario-27
scenario-28
scenario-29
scenario-30
scenario-31
scenario-32
scenario-33
scenario-34
scenario-35
mcp_server
skills
api
api-rest-collection
rails-graphql-best-practices
code-quality
rails-architecture-review
rails-code-conventions
rails-code-review
rails-review-response
rails-security-review
rails-stack-conventions
assets
snippets
refactor-safely
context
rails-context-engineering
rails-project-onboarding
ddd
ddd-boundaries-review
ddd-rails-modeling
ddd-ubiquitous-language
engines
rails-engine-compatibility
rails-engine-docs
rails-engine-extraction
rails-engine-installers
rails-engine-release
rails-engine-reviewer
rails-engine-testing
infrastructure
rails-api-versioning
rails-background-jobs
rails-database-seeding
rails-frontend-hotwire
rails-migration-safety
rails-performance-optimization
orchestration
rails-skills-orchestrator
patterns
ruby-service-objects
strategy-factory-null-calculator
yard-documentation
planning
create-prd
generate-tasks
ticket-planning
testing
rails-bug-triage
rails-tdd-slices
rspec-best-practices
rspec-service-testing