agent-architecture
Agent skill for architecture - invoke with $agent-architecture
Install with Tessl CLI
npx tessl i github:ruvnet/claude-flow --skill agent-architecture26
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
0%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 critically deficient across all dimensions. It provides only a vague domain label ('architecture') and an invocation command, but fails to explain what the skill does, what specific capabilities it offers, or when Claude should select it. Without concrete actions or trigger guidance, Claude cannot effectively choose this skill from a pool of alternatives.
Suggestions
Add specific concrete actions the skill performs (e.g., 'Designs system architectures, creates component diagrams, evaluates scalability patterns, reviews code structure').
Include an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks about system design, microservices, component structure, or architectural decisions').
Clarify the type of architecture (software, cloud, enterprise, etc.) to distinguish from other potentially similar skills and reduce conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for architecture' is completely abstract with no indication of what the skill actually does - no verbs, no specific capabilities listed. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no 'Use when...' clause and no explanation of capabilities - only a vague domain reference and invocation syntax. | 1 / 3 |
Trigger Term Quality | The only potential trigger term is 'architecture' which is extremely generic and could apply to software architecture, building architecture, system design, etc. '$agent-architecture' is a command syntax, not a natural user phrase. | 1 / 3 |
Distinctiveness Conflict Risk | 'Architecture' is extremely broad and could conflict with any skill related to software design, system design, code structure, building design, or infrastructure. No distinguishing characteristics are provided. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a verbose template dump rather than actionable guidance. It provides generic architecture examples (Kubernetes, OpenAPI, SQL) that Claude can already generate, while lacking workflow clarity on how to actually perform architecture design. The content would benefit from being 80% shorter with clear decision-making guidance instead of boilerplate templates.
Suggestions
Remove generic templates (Kubernetes, OpenAPI, SQL schemas) that Claude already knows - replace with decision criteria for when to use each pattern
Add explicit workflow with validation checkpoints: e.g., 'Before proceeding to Refinement phase, verify: [ ] All component interfaces defined, [ ] Data flow documented, [ ] Security review complete'
Split detailed examples into separate reference files (e.g., SECURITY_PATTERNS.md, SCALING_PATTERNS.md) and keep SKILL.md as a concise overview
Add concrete guidance on how to gather requirements from the Pseudocode phase and translate them into architecture decisions
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive boilerplate examples (Kubernetes manifests, OpenAPI specs, SQL schemas) that Claude already knows how to generate. The 400+ lines of generic architecture templates add little value beyond what Claude can produce on demand. | 1 / 3 |
Actionability | Contains concrete code examples (SQL, YAML, Mermaid diagrams), but they are generic templates rather than project-specific guidance. The skill describes what architecture artifacts look like rather than instructing how to create them for a specific context. | 2 / 3 |
Workflow Clarity | The SPARC Architecture Phase lists 5 high-level steps but provides no sequencing, validation checkpoints, or feedback loops. No guidance on when architecture is 'complete' or how to verify designs before proceeding. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with all content inline. No references to external files for detailed specifications. The 7 major sections with extensive code blocks should be split into separate reference documents. | 1 / 3 |
Total | 5 / 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.
- 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.