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

63%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/37signals-style/SKILL.md

Quality

Content

37%

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

This SKILL.md is essentially a well-organized table of contents with no substantive content of its own. While the progressive disclosure structure is sound in theory, the complete absence of any actionable guidance, code examples, quick-start patterns, or workflow descriptions means Claude would gain almost nothing from this file alone. The skill desperately needs either inline content (at minimum a quick-start section with key patterns) or the actual bundle reference files to have any value.

Suggestions

Add a 'Quick Start' or 'Key Patterns' section with 3-5 concrete, executable code examples showing the most important 37signals conventions (e.g., thin controller pattern, model concern pattern, Turbo Frame usage).

Include a brief workflow or decision tree: 'When building a new feature, consult these references in order: 1) routing → 2) controllers → 3) models → 4) views → 5) testing'.

Add at least a summary of the most critical anti-patterns or 'what they avoid' inline, so Claude has actionable constraints even without loading reference files.

Provide the actual bundle reference files, or at minimum include substantive inline content for the top 3-5 most commonly needed reference areas.

Dimension	Reasoning	Score
Conciseness	The content is extremely lean — it's essentially a topic map with brief descriptors for each reference file. No unnecessary explanations, no padding, no concepts Claude already knows. Every line serves as navigation.	3 / 3
Actionability	The SKILL.md contains zero concrete code, commands, examples, or executable guidance. It is purely a table of contents pointing to reference files. Without those reference files being available, there is nothing actionable here — no patterns, no code snippets, no specific instructions Claude can follow.	1 / 3
Workflow Clarity	There are no workflows, sequences, or processes described. The content is a flat list of references with no guidance on when to consult which file, no decision trees, and no validation steps. For a skill covering controllers, models, testing, and multi-step processes, the complete absence of any workflow guidance is a significant gap.	1 / 3
Progressive Disclosure	The structure is well-organized with clear categories and one-level-deep references, which is good progressive disclosure design. However, since no bundle files were provided, none of the 30+ referenced files actually exist, making this an empty shell. The navigation is clearly signaled but leads nowhere verifiable.	2 / 3
	Total	7 / 12 Passed

Description

89%

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

This is a solid skill description with excellent trigger terms and clear when/what guidance. Its main weakness is that the capabilities are listed as topic categories rather than specific concrete actions, making it slightly vague about what the skill actually does beyond providing 'patterns'. The distinctiveness is excellent due to the specific 37signals/Basecamp niche.

Suggestions

Replace the category list with specific concrete actions, e.g., 'Generates controllers following thin-controller patterns, structures models with 37signals conventions, implements Hotwire Turbo/Stimulus patterns, writes tests in 37signals style.'

Dimension	Reasoning	Score
Specificity	Names the domain (Rails coding patterns) and lists topic areas (controllers, models, views, Hotwire, testing, database, security, team philosophy), but these are categories rather than concrete actions. It doesn't describe specific actions like 'generates controller code' or 'structures models with concerns'.	2 / 3
Completeness	Clearly answers both what ('Rails coding patterns derived from analysis of 37signals' Fizzy codebase' covering multiple areas) and when ('Use when writing Rails code in 37signals/Basecamp style or when asked to follow 37signals patterns').	3 / 3
Trigger Term Quality	Includes strong natural trigger terms: 'Rails', '37signals', 'Basecamp', 'Hotwire', 'Fizzy', plus domain terms like 'controllers', 'models', 'views', 'testing'. Users asking about 37signals-style Rails code would naturally use these terms.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive due to the specific niche of 37signals/Basecamp/Fizzy coding patterns. Unlikely to conflict with generic Rails skills because of the explicit 37signals scoping.	3 / 3
	Total	11 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: lucianghinda/superpowers-ruby
Commit: 712d734

Reviewed: 24 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.