Curated library of 28 public AI agent skills for Ruby on Rails development. Organized by category: testing, code-quality, engines, infrastructure, api, and context. Covers code review, architecture, security, testing (RSpec), engines, Hotwire, and TDD automation. Shared Ruby skills (YARD docs, DDD, service objects) have moved to ruby-core-skills. Repository agents remain documented in GitHub but are intentionally excluded from the Tessl tile.
93
95%
Does it follow best practices?
Impact
93%
1.78xAverage score across 28 eval scenarios
Passed
No known issues
Step-by-step guides for each stage of Rails development. Each stage defines a chain of skills executed in order.
Note: This repository depends on igmarin/ruby-core-skills for foundational Ruby skills. Install both repositories for complete functionality. Skills marked with *(from core)* are provided by the core dependency.
flowchart TD
START([What do you need to do?]) --> DECISION{What stage are you at?}
DECISION -->|New project or setup| DISCOVERY[discovery]
DECISION -->|Configure CI/CD or environment| SETUP[setup]
DECISION -->|Develop code| DEV[development]
DECISION -->|Review quality| QUALITY[quality]
DECISION -->|Code review| REVIEW[review]
DECISION -->|Build engine| ENGINES[engines]
DISCOVERY --> NEXT{What next?}
SETUP --> DEV
NEXT -->|Implement| DEV
NEXT -->|Done| END([PR / Merge])
DEV -->|Tests pass| YARD[write-yard-docs *(from core)*]
DEV -->|Need review| REVIEW
YARD --> REVIEW
REVIEW -->|Feedback received| RESPOND[respond-to-review *(from core)*]
RESPOND -->|Re-implement| DEV
RESPOND -->|OK| END
QUALITY --> REVIEW
ENGINES --> REVIEW| Stage | Guide | Description | Primary Skills |
|---|---|---|---|
| Discovery | Discovery & Context | Understand codebase, project onboarding | load-context, setup-environment |
| Setup | Setup & Configuration | Configure CI/CD, environment, deploy | setup-environment (plus roadmap setup-ci-cd) |
| Development | Development | TDD development, implementation | plan-tests, testing skills, implementation |
| Quality | Code Quality | Conventions, refactoring, documentation | Local: apply-code-conventions, refactor-code. Core: write-yard-docs, refactor-process, review-process |
| Review | Review & Validation | Code review, security, architecture | code-review, security-check, review-architecture, respond-to-review (from core) |
| Engines | Engine Development | Create and maintain Rails engines | engine skills |
This directory contains reference guides describing each stage. For executable orchestration, use the callable agents in agents/:
| Stage Doc | Callable Skill | Status |
|---|---|---|
| development.md | tdd | Active |
| review.md | review | Active |
| setup.md | setup | Active |
| quality.md | quality | Active |
| engines.md | engine | Active |
| discovery.md | (none — linear, no orchestration needed) | Doc only |
When to use which: Read the stage doc to understand the full context and rationale. Invoke the callable agent when you want the agent to execute the orchestration automatically.
| Situation | Agent | Quick Entry |
|---|---|---|
| Bug fix | bug-fix | triage-bug (from core) → reproduce test → fix → verify |
| Refactoring | Refactor Safely | refactor-code → characterization tests → extract |
| Performance | Performance Optimization | optimize-performance |
| GraphQL | graphql | domain modeling (from core) → schema → TDD → security |
| Authorization | Authorization Setup | implement-authorization |
| External API | API Integration | integrate-api-client (from core) |
| Database migration | migration | plan → test → staging → production |
| Background job | background-job | design → TDD → retry config → monitoring |
New to the project?
├─ Yes → load-context → setup-environment
└─ No → What do you need to do?
Implement?
Bug or refactor?
├─ Bug → triage-bug *(from core)*
├─ Refactor → refactor-code
└─ New feature → plan-tests → write-tests
Code type?
├─ Service → create-service-object *(from core)*
├─ REST API → integrate-api-client *(from core)*
├─ GraphQL → implement-graphql
├─ Migration → review-migration
├─ Background job → implement-background-job
└─ Engine → create-engine
Authorization/roles?
└─ implement-authorization
Performance?
└─ optimize-performanceAll code-producing agents include this gate:
Write test → Run test → Verify it FAILS → Implement → Verify it PASSESSee details in each specific agent.
agents
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
skills
api
generate-api-collection
implement-graphql
code-quality
apply-code-conventions
apply-stack-conventions
assets
snippets
code-review
refactor-code
review-architecture
security-check
context
load-context
setup-environment
engines
create-engine
create-engine-installer
document-engine
extract-engine
release-engine
review-engine
test-engine
upgrade-engine
infrastructure
implement-background-job
implement-hotwire
optimize-performance
review-migration
seed-database
version-api
testing
plan-tests
test-service
write-tests