37signals-style

Rails coding patterns derived from analysis of 37signals' Fizzy codebase. Use when writing Rails code in 37signals/Basecamp style or when asked to follow 37signals patterns. Covers controllers, models, views, Hotwire, testing, database, security, and team philosophy.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplar of progressive disclosure: a lean, well-categorized index pointing to real one-level-deep reference files with concrete descriptors. The body is purely navigational, so actionability and workflow clarity are limited by design — the actual guidance lives in the references.

Suggestions

Add a short 'How to use this guide' note in the body stating the workflow (identify the topic category, open the matching reference, apply the pattern) so the navigation action is explicit rather than implied.

Inline 1-2 of the most common patterns (e.g., a thin-controller skeleton or a scope/query-object example) directly in the body so the skill is actionable without always requiring a file read for high-frequency cases.

For the few reference files that cover destructive or batch operations (e.g., database migrations, webhooks), note in their descriptors that validation steps are documented inside, so a reader knows checkpoints exist before opening the file.

Dimension	Reasoning	Score
Conciseness	The body is a lean two-sentence intro followed by a pointer-per-line topic map with one-line descriptors; it assumes Claude's competence, explains no basic Rails concepts, and every line earns its place, matching the 'lean and efficient' anchor 5.	5 / 5
Actionability	Each reference carries a concrete descriptor (e.g., 'Thin controllers, concerns, authentication, authorization') giving specific navigational guidance, but the body itself contains no executable code, commands, or steps — Claude must open a reference file for any actual pattern, fitting anchor 3's 'some concrete guidance but incomplete' rather than the executable anchor 4.	3 / 5
Workflow Clarity	No multi-step workflow is described, but this is a read-only reference index with no destructive or batch operations, so no validation checkpoints are required; the browse-by-category-then-open-file navigation is unambiguous and well-organized, placing it above the 'sequence present but checkpoints missing' anchor 3 via the simple-skill exception rather than at anchor 5 which demands explicit validation steps.	4 / 5
Progressive Disclosure	The body is a clear overview that points to 35 one-level-deep reference files, each well-signaled with a path and one-line description and grouped into six named categories; all referenced paths exist on disk, matching the 'clear overview with well-signaled one-level-deep references; easy navigation' anchor 5.	5 / 5
	Total	17 / 20 Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-scoped description that clearly states both what it covers and when to use it, with distinct brand-specific triggers. Its only weakness is that the stated actions are generic ('writing code in style', 'follow patterns') rather than concrete operations.

Dimension	Reasoning	Score
Specificity	Names the Rails domain and lists eight concrete coverage areas (controllers, models, views, Hotwire, testing, database, security, team philosophy), but the stated actions ('writing Rails code in style', 'follow patterns') are generic verbs rather than specific operations, fitting the 'names domain and concrete actions but not comprehensive' anchor rather than the action-listing anchor 4.	3 / 5
Completeness	It explicitly answers 'what' ('Rails coding patterns derived from analysis of 37signals' Fizzy codebase... Covers...') and 'when' ('Use when writing Rails code in 37signals/Basecamp style or when asked to follow 37signals patterns') with concrete trigger phrases, matching the anchor 5 example pattern exactly.	5 / 5
Trigger Term Quality	The 'Use when writing Rails code in 37signals/Basecamp style or when asked to follow 37signals patterns' clause supplies natural trigger terms with synonyms (37signals, Basecamp), but it omits common variations a user might say (e.g., 'Rails conventions', 'Hotwire', 'Stimulus'), matching anchor 4's 'good keyword coverage; a few natural terms missing' rather than the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The niche is brand-specific (37signals/Basecamp/Fizzy codebase) and both triggers require 37signals/Basecamp context, giving a clear niche with minimal conflict risk against generic Rails skills, matching anchor 5.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: lucianghinda/superpowers-ruby
Path: skills/37signals-style/SKILL.md
Commit: 99fac3d

Reviewed: 11 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.