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
Purpose: compact, copy-paste ready spec templates and common matchers for this repo.
Before using any template for new behavior, pair it with tdd_proof_checklist.md so the final artifact shows the focused command, expected RED failure, GREEN rerun, and broader verification.
Proof example:
- First command: `bundle exec rspec spec/models/user_spec.rb`
- Expected RED: `NoMethodError: undefined method 'admin?'` because `User#admin?` does not exist yet
- GREEN rerun: `bundle exec rspec spec/models/user_spec.rb`RSpec.describe "API::V1::Users", type: :request do describe 'GET /api/v1/users' do it 'returns list of users' do create_list(:user, 2) get '/api/v1/users' json = JSON.parse(response.body)
aggregate_failures do
expect(response).to have_http_status(:ok)
expect(json['data'].length).to eq(2)
end
endend end
RSpec.describe User, type: :model do it 'validates presence of email' do user = build(:user, email: nil)
aggregate_failures do
expect(user).not_to be_valid
expect(user.errors[:email]).to include("can't be blank")
endend end
RSpec.describe MyService, type: :unit do describe '.call' do subject(:result) { described_class.call(params) }
context 'with valid input' do
let(:params) { { key: 'value' } }
it 'returns success' do
aggregate_failures do
expect(result[:success]).to be true
expect(result[:response]).to be_present
end
end
end
context 'with invalid input' do
let(:params) { {} }
it 'returns failure with error message' do
aggregate_failures do
expect(result[:success]).to be false
expect(result[:response][:error][:message]).to be_present
end
end
endend end
perform_enqueued_jobs for background jobstravel_to for time-dependent testsexpect { }.to change { Model.count }.by(1) for side effectsagents
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