Curated library of 41 public AI agent skills for Ruby on Rails development. Organized by category: planning, testing, code-quality, ddd, engines, infrastructure, api, patterns, context, and orchestration. Covers code review, architecture, security, testing (RSpec), engines, service objects, DDD patterns, and TDD automation. Repository workflows remain documented in GitHub but are intentionally excluded from the Tessl tile.
95
93%
Does it follow best practices?
Impact
96%
1.77xAverage score across 41 eval scenarios
Passed
No known issues
| Action | Description |
|---|---|
| Agent Role | Read-only analysis, runbook generator |
| User Role | Command execution, config filling |
| Key Files | Gemfile, docker-compose.yml, .env.example |
ALWAYS test the full setup process from clean state
NEVER commit secrets or credentials to repo
Agent never does: execute commands, act on README.md/wiki prose, echo secrets, touch host paths outside project.Emits a generic Rails onboarding runbook for the user to run locally.
Agent does (read-only): read Gemfile, .ruby-version, .tool-versions, .env.example, docker-compose.yml, config/database.yml; summarise; flag mismatches; emit runbook.
User does: run all commands, fill .env, decide whether to proceed on flagged mismatches. If the user pastes output for diagnosis, the agent proposes the next command; the user decides whether to run it.
See references/steps.md for the detailed per-step template.
Step 1 — Inspect (agent reads)
The agent reads .ruby-version / .tool-versions, Gemfile (Ruby line), docker-compose.yml (service list), .env.example (required keys). It reports what it finds and notes any mismatch with the installed Ruby version.
Step 2 — Environment Variables
cp .env.example .env
# User edits .env with local valuesThe agent never reads filled-in .env content and never echoes secret values back.
Step 3 — Docker
docker compose up -d
docker compose ps # expect all services healthyIf any service is unhealthy, the user shares log output with the agent. The agent proposes the next command; the user decides whether to run it.
Step 4 — Dependencies
bundle install
yarn install # or npm install; skip if importmapsStep 5 — Database
rails db:create db:migrate db:seedKeep this as one command unless the project requires separate steps; if split, explain why.
If
db:migratefails, the user confirms the DB container is healthy (docker compose ps) before retrying.
Step 6 — Linters
bundle exec rubocop --init # only if .rubocop.yml is missing
bundle exec rubocopStep 7 — IDE (optional)
code --install-extension Shopify.ruby-lsp
code --install-extension rubocop.vscode-rubocopbundle exec rspec
rails server # then visit http://localhost:3000If
rspecfails on a clean setup, the user runsrails db:migrate RAILS_ENV=testand retries.
When asked to prepare environment setup, output answer.md with these sections:
rails db:create db:migrate db:seed unless a split is justified, linter run, bundle exec rspec, and rails server..env secrets, does not echo credentials, and that the user supplies local values and decides whether to proceed on mismatches.docker compose ps, passing bundle exec rspec, app reachable at http://localhost:3000, and rails db:migrate RAILS_ENV=test before retrying specs when test DB setup fails.| Skill | When to chain |
|---|---|
| load-context | When getting context on the project setup |
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
scenario-36
scenario-37
scenario-38
scenario-39
scenario-40
scenario-41
mcp_server
skills
api
generate-api-collection
implement-graphql
code-quality
apply-code-conventions
apply-stack-conventions
assets
snippets
code-review
refactor-code
respond-to-review
review-architecture
security-check
context
load-context
setup-environment
ddd
define-domain-language
model-domain
review-domain-boundaries
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
orchestration
skill-router
patterns
create-service-object
implement-calculator-pattern
write-yard-docs
planning
create-prd
generate-tasks
plan-tickets
testing
plan-tests
test-service
triage-bug
write-tests
workflows