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
| Aspect | Rule |
|---|---|
| Pre-requisite | Characterization tests must exist and be Green before any edits |
| Step Size | One atomic transformation at a time (rename variable, extract method, etc.) |
| Verification | Run tests after every single step |
| No Behavior Changes | No new features, bug fixes, or changed return values during refactoring |
| Rollback | If tests turn Red, undo immediately — do not debug in a broken state |
For each planned step:
git checkout or undo), analyze the root cause, and try a smaller step.Pause and align with the user:
Baseline (Green):
class ReportGenerator
def generate(data)
# Formats raw data to report
formatted = data.map { |row| "#{row[:id]}: #{row[:name].strip.capitalize}" }
# Renders report
"=== Report ===\n" + formatted.join("\n") + "\n=============="
end
endStep 1: Extract Formatter Logic (Atomic Edit):
class ReportGenerator
def generate(data)
formatted = format_rows(data)
"=== Report ===\n" + formatted.join("\n") + "\n=============="
end
private
def format_rows(data)
data.map { |row| "#{row[:id]}: #{row[:name].strip.capitalize}" }
end
endAction: Run tests immediately. Confirm Green.
| Context | Next Skill |
|---|---|
| Establishing baseline coverage | test-planning-process → tdd-process |
| Documenting newly extracted APIs | write-yard-docs |
| Post-refactoring review | review-process |
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