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
When to use: Apply conventions, refactor existing code, or maintain quality during development.
graph TB
subgraph Prepare [🧪 Phase 1: Prepare]
direction TB
A[Refactor needed] --> B[refactor-code]
B --> C[Characterization tests]
C --> D{Tests pass?}
end
subgraph Refactor [🔧 Phase 2: Refactor]
direction TB
D -- Yes --> E[Extract/refactor]
E --> F{Tests pass?}
F -- No --> G[Revert + fix]
G --> E
end
subgraph Iterate [🔄 Phase 3: Iterate]
direction TB
F -- Yes --> H{More to refactor?}
H -- Yes --> E
end
H -- No --> I[code-review]
%% Styling
style Prepare fill:#f5f5f5,stroke:#333,stroke-dasharray: 5 5
style Refactor fill:#e1f5fe,stroke:#01579b
style Iterate fill:#fff3e0,stroke:#e65100
style D fill:#ffd54f
style F fill:#ffd54f
style H fill:#ffd54fGoal: Change structure without changing behavior.
Key rule: Separate behavior changes from structural changes. Never both.
Goal: Clean code following Rails principles.
| Path | Rules |
|---|---|
app/controllers | Thin controllers, 1 line actions, strong params |
app/models | No complex business logic, scopes for queries |
app/services | .call pattern, response contract, YARD |
app/jobs | Idempotency, retry strategy, log context |
config/routes | Resourceful, shallow nesting |
Goal: Document public API after implementation.
# @param params [Hash] :user_id, :amount
# @return [Hash] { success: Boolean, response: Hash }
# @raise [ArgumentError] when user_id is nilLanguage: All YARD in English unless user requests otherwise.
| Skill | Description | Trigger words |
|---|---|---|
| refactor-code | Restructure preserving behavior | "refactor", "extract", "restructure" |
| apply-code-conventions | Clean code principles | "code review", "conventions", "DRY", "YAGNI" |
| write-yard-docs | Inline API docs | "YARD", "documentation", "@param", "@return" |
agents
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