Curated library of 16 public Ruby AI agent skills: 10 atomic skills (YARD docs, service objects, calculator pattern, API clients, DDD, bug triage, code review, skill routing), 5 process-discipline skills (TDD, refactoring, review, security, test planning), and 1 planning skill (TDD task generation). Zero agents — this is a foundational library consumed by framework-specific tiles like rails-agent-skills and hanakai-yaku.
95
96%
Does it follow best practices?
Impact
95%
1.05xAverage score across 16 eval scenarios
Passed
No known issues
Extended patterns for this skill. Read SKILL.md first.
"When a customer books a vehicle, the system should create a hold so fleet managers can confirm the reservation before it expires. The booking service currently calls
HoldServicebut the controller isReservationsControllerand the model isBooking."
Terms spotted: books, hold, reservation, booking, Booking (model), ReservationsController, HoldService.
A Rails app has Booking (model), ReservationsController, and HoldService all referring to the same concept. The resulting glossary resolves it:
| Canonical term | Aliases | Definition | Invariant | Context |
|---|---|---|---|---|
| Reservation | Booking, Hold | A customer claim on an inventory slot for a future date | Must expire or be confirmed within 24h | Fleet Booking |
Open questions: Does "Hold" ever refer to a separate short-lived state before a Reservation is created, or is it always the same concept? If separate, it needs its own entry.
Once the glossary is agreed, rename code toward the canonical term incrementally — do not rename all 50 call sites in one PR.
| Mistake | Reality |
|---|---|
| Keeping every synonym alive forever | Pick one preferred business term or the codebase stays muddy |
| Using technical class names as domain truth | Domain language comes from the business, not from current code accidents |
| Jumping to aggregates before agreeing on words | Overloaded terms produce bad boundaries and bad models |
| One term meaning different things in different screens | Flag it early — it usually signals multiple bounded contexts |
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
skills
code-quality
respond-to-review
ddd
define-domain-language
model-domain
review-domain-boundaries
docs
write-yard-docs
orchestration
skill-router
patterns
create-service-object
implement-calculator-pattern
planning
generate-tdd-tasks
process
testing
triage-bug