rails-cto / claude
CLAUDE.md15 starsChanged 7 months agoMITView on GitHub
When working on Ruby on Rails projects, always invoke /rails-cto at the start of a session. It handles skill routing, QA gates, and the completion checklist. Before planning or modifying any file, read the relevant skill(s) first. Follow the conventions in each skill — do not deviate without consulting it. Multiple skills may apply to a single change. Invoke /rails-cto-qa and /rails-cto-security after every code change. A task is NOT done until QA and security scans pass. Do not skip…
In this repository17 other files it gives its agents.
- rails-cto-apiSkill
- rails-cto-architectSkill
- rails-cto-commitSkill
- rails-cto-engineerSkill
- rails-cto-erbSkill
- rails-cto-minitestSkill
- rails-cto-production-prSkill
- rails-cto-pull-requestSkill
- rails-cto-qaSkill
- rails-cto-restfulSkill
- rails-cto-securitySkill
- rails-ctoSkill
- rails-cto-static-analysisSkill
- rails-cto-stimulusSkill
- rails-cto-tailwindSkill
- rails-upgradeSkill
- rails-viewcomponentsSkill
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 3
When working on Ruby on Rails projects, always invoke /rails-cto at the start of a session.
- Distinctive: line 7
Before planning or modifying any file, read the relevant skill(s) first.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skills
When working on Ruby on Rails projects, always invoke /rails-cto at the start of a session. It handles skill routing, QA gates, and the completion checklist.
Mandatory: Skill Routing by File Type
Before planning or modifying any file, read the relevant skill(s) first. Follow the conventions in each skill — do not deviate without consulting it. Multiple skills may apply to a single change.
| When you touch... | Read these skills first |
Any .rb file | /rails-cto-engineer |
Files in app/controllers/ (except API) | /rails-cto-restful |
Files in app/controllers/api/ | /rails-cto-api, /rails-cto-restful |
Files in app/models/ or app/commands/ or app/services/ | /rails-cto-engineer |
Files in app/components/ | /rails-cto-view-component |
Files in app/javascript/controllers/ (Stimulus) | /rails-cto-stimulus |
Any .html.erb file | /rails-cto-erb, /rails-cto-tailwind |
Any .css or Tailwind-related file | /rails-cto-tailwind |
Any test file in test/ | /rails-cto-minitest |
Mandatory: After Modifying Any .rb File
Invoke /rails-cto-qa and /rails-cto-security after every code change. A task is NOT done until QA and security scans pass. Do not skip these even if the user doesn't mention them.
Mandatory: After Modifying Any .html.erb File
Invoke /rails-cto-erb, /rails-cto-tailwind, and /rails-cto-security after every ERB change. A task is NOT done until ERB, Tailwind, and security checks pass. Do not skip these even if the user doesn't mention them.
Herb is required on every changed ERB file — new or existing. After modifying any .html.erb file, run bundle exec herb --fix and bundle exec herb format on it. This applies to all ERB files you touch, not just new ones. Review the output and fix any errors or warnings that Herb reports — do not ignore them or move on until they are resolved.
Mandatory: Every Plan Must Include QA
When creating any implementation plan, invoke /rails-cto-architect to structure the plan and read /rails-cto-engineer first to understand the project's best practices, conventions, and reusable patterns before proposing new code. Always include /rails-cto-qa and /rails-cto-security as final steps. No plan is complete without QA and security gates.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

