architecture-designer
Use when designing new high-level system architecture, reviewing existing designs, or making architectural decisions. Invoke to create architecture diagrams, write Architecture Decision Records (ADRs), evaluate technology trade-offs, design component interactions, and plan for scalability. Use for system design, architecture review, microservices structuring, ADR authoring, scalability planning, and infrastructure pattern selection — distinct from code-level design patterns or database-only design tasks.
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 strong skill description that excels across all dimensions. It provides specific concrete actions, rich natural trigger terms, explicit 'Use when' guidance, and even proactively differentiates itself from adjacent skills. The description is well-structured and concise while being comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'create architecture diagrams', 'write Architecture Decision Records (ADRs)', 'evaluate technology trade-offs', 'design component interactions', and 'plan for scalability'. These are clearly defined, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (create diagrams, write ADRs, evaluate trade-offs, design interactions, plan scalability) and 'when' (designing new architecture, reviewing existing designs, making architectural decisions) with explicit 'Use when' clauses at the beginning and end. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'system architecture', 'architecture diagrams', 'ADRs', 'technology trade-offs', 'scalability', 'microservices', 'system design', 'architecture review', 'infrastructure pattern'. These are terms users would naturally use when seeking architectural guidance. | 3 / 3 |
Distinctiveness Conflict Risk | Explicitly distinguishes itself from related skills with the clause 'distinct from code-level design patterns or database-only design tasks', which directly reduces conflict risk. The focus on high-level system architecture and ADRs creates a clear niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured architecture skill with strong actionability through concrete examples (Mermaid diagram, full ADR), clear workflow with validation checkpoints, and excellent progressive disclosure via the reference table. The main weakness is moderate verbosity in the role definition and 'When to Use' sections, which explain things Claude doesn't need to be told. Overall, it's a solid skill that would benefit from minor trimming.
Suggestions
Remove or significantly condense the 'Role Definition' and 'When to Use This Skill' sections — these duplicate frontmatter metadata and don't add actionable guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The role definition section ('You are a principal architect with 15+ years...') and 'When to Use This Skill' section add little value since Claude doesn't need persona framing or usage triggers in the body. The core content (workflow, templates, examples) is reasonably efficient, but there's room to trim. | 2 / 3 |
Actionability | Provides a concrete Mermaid diagram example, a fully fleshed-out ADR template with realistic content, a clear output checklist, and specific reference files to load. The examples are copy-paste ready and the guidance is specific rather than abstract. | 3 / 3 |
Workflow Clarity | The 5-step core workflow is clearly sequenced with explicit validation checkpoints: 'Verify full requirements coverage before proceeding' at step 1 and 'If review fails, return to step 3 with recorded feedback' at step 5. This provides a clear feedback loop for an inherently non-destructive design process. | 3 / 3 |
Progressive Disclosure | Excellent use of a reference table with clear 'Load When' conditions pointing to separate files for patterns, ADR templates, system design, database selection, and NFR checklists. The main skill stays at overview level with well-signaled one-level-deep references. | 3 / 3 |
Total | 11 / 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
- jeffallan/claude-skills
- Commit
3d95bb1
- 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.