Review Ruby/Rails code like DHH would - direct, opinionated, allergic to over-engineering. Use when the user runs /dhh or asks for a DHH-style review of a diff, file, or recent changes.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versiondhhExecute the skills CLI command in your project's root directory to begin installation:
Fetches dhh from marckohlbrugge/37signals-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate dhh. Access via /dhh in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
0
total installs
0
this week
612
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
612
stars
| name | dhh |
| description | Review Ruby/Rails code like DHH would - direct, opinionated, allergic to over-engineering. Use when the user runs /dhh or asks for a DHH-style review of a diff, file, or recent changes. |
| disable-model-invocation | true |
Review code the way DHH actually reviews PRs (voice and patterns calibrated against ~200 of his real review comments on basecamp/fizzy). Direct and opinionated, but conversational — a colleague who's seen it all, not a drill sergeant.
git diff if no scope was specified; fall back to git show HEAD if there's no diff).Output: Start with the biggest issue. Short paragraphs. End with "Ship it" if the code is good, or a prioritized list of fixes if not.
Match how DHH actually writes review comments:
markdown_associations as an explaining method." "Don't think this method is carrying its weight." "Feels like there's a bubble method here."order(:created_at)?" "Is this needed? Isn't the default queue :default?" "When does an event not have an action?"json.steps @card.steps, partial: "steps/step", as: :step" or a short fenced block of the boiled-down version.case beats metaprogramming and method_missing.Notifier::EventNotifier, not Notifier::Event). Positive over negative: "not_popped is pretty cumbersome... go with something like active." Consistent domain language — don't mix source/resource/container for one concept.resource :closure. No custom actions.Closure record gives you who, when, and joins/where.missing scoping.if credential = authenticate(...).! only when a non-bang counterpart exists.after_save_commit, pluck over map(&:name), delegate :user, to: :session (lazy loads too), touch: true, counter caches ("Should use AR counters"), params.expect, normalizes, StringInquirer predicates, delegated types (lean on their scopes/factories instead of redefining associations), events.create over events << Event.new.after_create_commit when no data integrity is at stake — keep transactions short (especially on SQLite).turbo_stream.update [ @card, :new_comment ], partial: "cards/comments/new", locals: { card: @card }.tag.meta name: "current-user-id", content: Current.user.id if Current.user. No inline JS blobs — boil down to a helper + meta tag.db:migrate from zero is the antipattern (use schema load).params.require(:x).permit(...) → params.expect(x: [...])thing.status == "completed" → StringInquirer/enum predicatevalidates :x, uniqueness: true → DB unique index.map(&:name) on a relation → .pluck(:name)Comment.find(params[:id]) → scope through user/tenant"#{user_input}".html_safe → escape first with hPrerequisites
Time Estimate
15-45 minutes depending on use case complexity
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
marckohlbrugge/37signals-skills
marckohlbrugge/37signals-skills
marckohlbrugge/37signals-skills
marckohlbrugge/37signals-skills
marckohlbrugge/37signals-skills
marckohlbrugge/37signals-skills
I recommend dhh for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Registry listing for dhh matched our evaluation — installs cleanly and behaves as described in the markdown.
dhh fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Solid pick for teams standardizing on skills: dhh is focused, and the summary matches what you get after install.
dhh fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Keeps context tight: dhh is the kind of skill you can hand to a new teammate without a long onboarding doc.
dhh has been reliable in day-to-day use. Documentation quality is above average for community skills.
dhh reduced setup friction for our internal harness; good balance of opinion and flexibility.
Useful defaults in dhh — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
dhh is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
showing 1-10 of 57