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
| Topic | Rule |
|---|---|
| Canonical term | Pick one business term for one concept |
| Synonyms | Capture them, then choose one preferred term |
| Overloaded words | Flag them early; split meanings explicitly |
| Naming | Prefer business meaning over technical shorthand |
| Output | Return a usable glossary, not abstract theory |
DO NOT introduce DDD terminology without grounding it in the user's real domain language.
DO NOT rename code concepts until the glossary is explicit enough to justify the change.
ALWAYS flag overloaded or conflicting terms before recommending modeling changes.Core principle: Agree on business language before choosing models, services, or boundaries.
grep -rh "^class \|^module " lib/ app/ --include="*.rb" | sortThe codebase uses Customer, Client, and Account interchangeably. After collecting usages:
Customer with a migration note.Result: one canonical term (Customer) replaces two aliases, and one overloaded term (Account) is split before any model changes are made.
When using this skill, return:
| Canonical term | Aliases | Definition | Invariant | Context |
|---|---|---|---|---|
| Shipment | Parcel, Package | Physical goods sent to a customer address | Must reference a valid Order | Fulfillment |
Load only when the task needs examples or a reusable glossary schema:
| Skill | When to chain |
|---|---|
| review-domain-boundaries | When the glossary suggests multiple bounded contexts or language leakage |
| model-domain | When the terms are clear enough to decide entities, value objects, and services |
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