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
app/models/user.rb).DO NOT skip Task 0.0 (Create feature branch) unless the user explicitly overrides.
DO NOT use vague references instead of exact file paths.
DO NOT summarize the task list in a table instead of producing the actual checklist artifact.
DO NOT combine the TDD quadruplet sub-tasks into a single task. They must be broken out:
a) Write spec
b) Run spec (verify fails)
c) Implement
d) Run spec (verify passes)
Each c-step is one implementation action in one primary file. Split route,
controller, view, model, migration, service, and concern work into separate
quadruplets or separate follow-up tasks.bundle exec rspec or npm test).spec/..., app/..., config/...); documentation and review tasks should include relevant paths where applicable.tasks-[feature-name].md in /tasks/. Use the same [feature-name] as the PRD if one was provided.tasks-[feature-name].md checklist content in the response or answer.md; do not only describe the file or summarize it in a table.Load these files only when their specific guidance is required:
When asked to generate tasks, your output MUST include:
tasks-[feature-name].md content, not a summary table about the file.git checkout -b feature/name).X.Xa Write spec for [behavior] at spec/...X.Xb Run bundle exec rspec spec/... — verify it failsX.Xc Implement [behavior] at app/...X.Xd Run bundle exec rspec spec/... — verify it passes
Every a/b/c/d line must include the concrete file path or command path for that slice.tasks-[feature-name].md in /tasks/ folder.HEURISTICS.md and/or TASK_TEMPLATES.md were used, and why.For endpoint work, the first TDD quadruplet should normally be the request spec slice. Add model or service slices after the request boundary is established unless the PRD is explicitly persistence-only.
| Skill | When to chain |
|---|---|
| create-prd | Generate PRD first, then derive tasks from it |
| plan-tests | When planning the best first failing spec for a Rails change |
| plan-tickets | When the same initiative also needs ticket drafts |
| triage-bug | When the request starts from a bug report |
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