Content
7%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a list of well-known software engineering principles that Claude already understands deeply—Clean Architecture, DDD, separation of concerns, early returns, etc. It provides no concrete, executable guidance, no code examples, no decision workflows, and no novel information that would change Claude's behavior. The content would need to be dramatically restructured around specific, actionable patterns with concrete examples to be useful.
Suggestions
Replace abstract principles with concrete, executable examples—e.g., show a before/after refactoring from a 'utils.js' anti-pattern to domain-specific modules with actual code.
Add a decision workflow: a clear sequence for how to approach an architecture task (e.g., 1. Identify bounded contexts → 2. Define domain entities → 3. Map use cases → 4. Validate dependency direction).
Remove content Claude already knows (what DDD is, what separation of concerns means, what early returns are) and focus only on project-specific conventions or non-obvious preferences.
Remove the boilerplate 'When to Use' and 'Limitations' sections which add no actionable value to the skill body.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is verbose and largely explains concepts Claude already knows well—Clean Architecture, DDD, separation of concerns, early returns, avoiding deep nesting, etc. Much of this is general software engineering wisdom that doesn't need to be spelled out. The anti-patterns section restates the same points made in the best practices section. The 'When to Use' and 'Limitations' sections are boilerplate filler. | 1 / 3 |
Actionability | The skill provides no concrete code examples, no executable commands, no specific architectural templates, and no copy-paste-ready patterns. It reads as a collection of abstract principles and guidelines rather than actionable instructions. Statements like 'Follow domain-driven design and ubiquitous language' are vague direction, not concrete guidance. | 1 / 3 |
Workflow Clarity | There is no workflow or sequenced process described. The skill is a flat list of principles with no steps, no decision trees for when to apply which pattern, no validation checkpoints, and no feedback loops. For an architecture skill, there should be a clear process for evaluating design decisions. | 1 / 3 |
Progressive Disclosure | The content is organized with headers and sub-sections, which provides some structure. However, it's a monolithic document with no references to external files, and content that could be split (e.g., anti-patterns, naming conventions, library-first approach) is all inline. No bundle files are provided, but the content length and breadth would benefit from splitting. | 2 / 3 |
Total | 5 / 12 Passed |