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
This repository uses two public eval source areas and one generated staging area.
| Path | Purpose | Commit policy |
|---|---|---|
tessl-evals/ | Tessl-native scenarios for publishable skills in tile.json. | Tracked. |
personal-evals/ | Open examples for the upcoming ruby-skill-bench full-context evaluator. | Tracked. |
evals/ | Generated Tessl staging output produced from tessl-evals/. | Ignored; do not commit. |
Tessl currently validates skills, not repository workflows. Tessl-native scenarios must target only publishable skills from tile.json.
ruby-skill-bench is planned as a Ruby gem for validating skills and workflows with full context. Its personal-evals/ examples load SKILL.md plus companion resources as XML. They do not need to be Tessl-compatible while Tessl only consumes SKILL.md.
Generated scenarios from third-party services or private workflows must stay out of tracked paths. Store them locally in ignored directories such as private-evals/ when needed for private validation.
Root evals/ is generated Tessl staging output only. The release workflow stages tessl-evals/ into evals/ immediately before publishing.
Public eval examples must meet one of these criteria:
Do not rename generated scenarios to make them look original. Provenance must describe where the scenario came from and why it can be redistributed.
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