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.
56
63%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/37signals-style/SKILL.mdQuality
Discovery
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 clear trigger terms, explicit 'Use when' guidance, and a highly distinctive niche. Its main weakness is that the capabilities are listed as topic categories rather than concrete actions—saying what areas it covers but not what specific actions it performs (e.g., 'generates controllers following thin-controller patterns' vs. just 'covers controllers').
Suggestions
Replace the category list ('Covers controllers, models, views...') with specific concrete actions, e.g., 'Generates thin controllers, applies Hotwire Turbo/Stimulus patterns, writes system tests following 37signals conventions'.
| 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 'applies Hotwire Turbo patterns'. | 2 / 3 |
Completeness | Clearly answers both what ('Rails coding patterns derived from analysis of 37signals' Fizzy codebase') and when ('Use when writing Rails code in 37signals/Basecamp style or when asked to follow 37signals patterns'). The explicit 'Use when...' clause with clear trigger conditions is present. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'Rails', '37signals', 'Basecamp', 'Hotwire', 'controllers', 'models', 'views', 'testing', 'database', 'security'. Users asking about 37signals-style Rails code would naturally use these terms. Also mentions 'Fizzy codebase' which is a specific reference. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific niche of 37signals/Basecamp-style Rails patterns from the Fizzy codebase. This is unlikely to conflict with generic Rails skills or other coding pattern skills because of the very specific organizational and codebase references. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
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 pure table of contents with no substantive content of its own. While it's admirably concise and well-organized, it provides zero actionable guidance — no code examples, no key patterns inline, no workflow instructions, and no quick-start section. Without the bundle files (none were provided), this skill gives Claude nothing to work with. A good SKILL.md should include at least a brief summary of the most important patterns inline before delegating to references.
Suggestions
Add a 'Quick Start' or 'Key Patterns' section with 3-5 of the most important 37signals conventions inline (e.g., thin controllers, fat models, Hotwire-first), each with a brief concrete code example.
Include a workflow section explaining how to apply these patterns: e.g., 'When writing a new feature: 1. Start with the route (see routing.md), 2. Create a thin controller (see controllers.md), 3. Push logic to the model...'
Add at least one concrete, executable code example showing a canonical 37signals-style controller or model pattern so Claude has something actionable even without loading reference files.
Provide the actual bundle reference files so the progressive disclosure structure can function as intended — currently all 30+ references point to files that don't exist in the bundle.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely lean — it's essentially a topic map with one-line descriptions pointing to reference files. No unnecessary explanations, no padding, no concepts Claude already knows. Every line serves as navigation. | 3 / 3 |
Actionability | The SKILL.md contains zero executable guidance, no code examples, no concrete commands, and no specific patterns. It is purely a table of contents with no actionable content in itself. Without the bundle files to back it up, there is nothing Claude can act on. | 1 / 3 |
Workflow Clarity | There are no workflows, sequences, or processes described. No guidance on when to apply which pattern, no decision trees, no validation steps. It's a flat list of references with no procedural content. | 1 / 3 |
Progressive Disclosure | The structure is well-organized with clear categories and one-level-deep references to specific files, which is good progressive disclosure design. However, since no bundle files were provided, we cannot verify that any of the 30+ referenced files actually exist, and the SKILL.md itself contains no substantive quick-start content — it's entirely delegation with no overview content to orient Claude. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
100%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
9ae52eb
- Reviewed
Table of Contents
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.