software-architecture
Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development.
47
35%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/software-architecture/SKILL.mdQuality
Discovery
32%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 description is far too broad and vague to be useful for skill selection. It essentially claims to cover all of software development without specifying any concrete capabilities or distinct niche. The 'quality focused software architecture' framing is undermined by the catch-all trigger clause that encompasses any software-related task.
Suggestions
Narrow the scope to specific architectural concerns (e.g., 'Guides design of system architecture including component decomposition, dependency management, design patterns, and scalability planning') rather than claiming all of software development.
Add a focused 'Use when...' clause with specific trigger scenarios like 'Use when the user asks about system design, microservices vs monolith decisions, API design, or code structure review'.
Remove the catch-all phrase 'in any case that relates to software development' as it destroys distinctiveness and would cause this skill to conflict with virtually every other development-related skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'write code, design architecture, analyze code' without listing any concrete, specific actions. These are extremely broad categories rather than specific capabilities. | 1 / 3 |
Completeness | It has a weak 'what' ('quality focused software architecture') and a 'when' clause ('when users want to write code, design architecture, analyze code'), but the 'when' is so broad it essentially says 'use for anything software-related', which provides little actionable guidance. | 2 / 3 |
Trigger Term Quality | It includes some relevant keywords like 'write code', 'design architecture', 'analyze code', and 'software development', but these are overly broad and lack specific variations or natural user phrases (e.g., specific languages, frameworks, refactoring, debugging, code review). | 2 / 3 |
Distinctiveness Conflict Risk | The description covers virtually all of software development ('any case that relates to software development'), making it extremely generic and highly likely to conflict with any other coding, architecture, or development-related skill. | 1 / 3 |
Total | 6 / 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 provides a reasonable collection of software architecture principles and coding style rules, but it reads more like a general best-practices document than an actionable skill. It lacks executable examples, concrete workflows for making architectural decisions, and assumes Claude doesn't already know common principles like separation of concerns and DDD. The boilerplate 'When to Use' and 'Limitations' sections add no value.
Suggestions
Add a concrete workflow for architectural decision-making (e.g., '1. Identify the domain boundary → 2. Search for existing libraries → 3. Evaluate build-vs-buy → 4. Define module structure → 5. Validate separation of concerns').
Replace principle descriptions with executable code examples showing before/after patterns (e.g., a concrete refactoring from a utils.js anti-pattern to domain-specific modules).
Remove explanations of concepts Claude already knows (Clean Architecture basics, what DDD is, why separation of concerns matters) and focus only on project-specific conventions and decisions.
Remove the boilerplate 'When to Use' and 'Limitations' sections, which add no actionable information beyond what the frontmatter description already conveys.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity and explains concepts Claude already knows well (e.g., what Clean Architecture and DDD are, basic anti-patterns like mixing business logic with UI). Some sections are redundant—'Poor Architectural Choices' repeats points already made in 'Separation of Concerns'. The 'When to Use' and 'Limitations' sections are boilerplate filler. | 2 / 3 |
Actionability | The skill provides specific naming examples and concrete anti-patterns (e.g., 'use cockatiel instead of writing your own retry logic'), which is helpful. However, it lacks executable code examples, specific architectural templates, or copy-paste-ready patterns. It mostly describes principles rather than providing concrete implementation guidance. | 2 / 3 |
Workflow Clarity | There is no clear workflow or sequenced process for how to approach software architecture decisions. The content is a collection of principles and rules without any step-by-step process, decision trees, or validation checkpoints for architectural decisions. | 1 / 3 |
Progressive Disclosure | The content is reasonably organized with headers and sub-sections, but it's a monolithic document with no references to external files for deeper topics. Topics like Clean Architecture, DDD, and library evaluation could benefit from separate detailed references. The structure is adequate but not optimally organized for discovery. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
bae2be5
- 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.