software-architecture
tessl i github:sickn33/antigravity-awesome-skills --skill software-architectureGuide 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.
Validation
75%| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 12 / 16 Passed | |
Implementation
50%This skill provides a solid foundation of software architecture principles with good coverage of Clean Architecture and DDD concepts. However, it reads more like a style guide than an actionable skill—it tells Claude what to do but rarely shows how with concrete examples. The lack of executable code snippets and explicit decision workflows limits its practical utility.
Suggestions
Add concrete code examples demonstrating key patterns (early returns, proper error handling, component decomposition) rather than just describing them
Include a decision flowchart or explicit steps for the 'Library-First Approach' with validation checkpoints (e.g., 'Check npm → Evaluate 3+ options → Document decision → Proceed')
Replace generic library mentions with specific usage examples (e.g., show cockatiel retry pattern code instead of just naming it)
Consider splitting detailed anti-patterns and DDD principles into separate reference files, keeping SKILL.md as a concise overview with links
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some explanatory text that could be tightened. Phrases like 'Remember: Every line of custom code is a liability' and some of the anti-pattern explanations add bulk without adding actionable value. | 2 / 3 |
Actionability | Provides guidelines and principles but lacks concrete, executable examples. Mentions specific libraries (cockatiel, Redux/Zustand) but doesn't show how to use them. No code snippets demonstrating the early return pattern or proper error handling it advocates. | 2 / 3 |
Workflow Clarity | The 'Library-First Approach' section has implicit sequencing (search → evaluate → decide), but lacks explicit validation checkpoints. No clear workflow for how to apply Clean Architecture principles or when to decompose components. | 2 / 3 |
Progressive Disclosure | Content is organized into logical sections with headers, but everything is inline in one document. For a comprehensive architecture guide, references to separate files for DDD patterns, code examples, or anti-pattern deep-dives would improve navigation. | 2 / 3 |
Total | 8 / 12 Passed |
Activation
32%This description is too vague and overly broad to be useful for skill selection. It lacks concrete actions, specific trigger terms, and would conflict with nearly any software-related skill due to its catch-all 'any case that relates to software development' clause. The 'quality focused' framing is not explained or differentiated.
Suggestions
Define specific concrete actions this skill performs (e.g., 'Reviews code for SOLID principles, suggests design patterns, creates architecture diagrams, identifies code smells').
Replace the overly broad 'any case that relates to software development' with specific triggers like 'Use when users ask about design patterns, code quality, refactoring, system architecture, or technical debt'.
Clarify what 'quality focused' means - does it focus on maintainability, scalability, performance, or specific methodologies? This would help distinguish it from general coding skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'write code, design architecture, analyze code' without listing concrete actions. It doesn't specify what kind of architecture, what analysis methods, or what outputs are produced. | 1 / 3 |
Completeness | Has a weak 'what' (quality focused software architecture guide) and attempts a 'when' clause, but the trigger is extremely broad ('any case that relates to software development') rather than providing explicit, specific triggers. | 2 / 3 |
Trigger Term Quality | Contains some relevant keywords ('code', 'architecture', 'software development') but these are overly broad. Missing specific variations users might say like 'refactor', 'design patterns', 'system design', 'code review', etc. | 2 / 3 |
Distinctiveness Conflict Risk | The phrase 'any case that relates to software development' is extremely generic and would conflict with virtually any coding, debugging, testing, or development-related skill. No clear niche is established. | 1 / 3 |
Total | 6 / 12 Passed |
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.