architect-review
Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.
28
Quality
12%
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 ./docs/v19.7/configuration/agent/skills_external/antigravity-awesome-skills-main/skills/architect-review/SKILL.mdQuality
Discovery
N/ABased on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
Something went wrong
Implementation
12%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a job description or persona definition than actionable guidance. It extensively lists architectural concepts Claude already knows while providing almost no concrete, executable instructions for how to actually perform architectural reviews. The content would benefit from dramatic reduction and replacement with specific templates, checklists, and example outputs.
Suggestions
Replace the verbose 'Capabilities' and 'Knowledge Base' lists with a concise checklist of what to evaluate during an architectural review (e.g., '□ Service boundaries align with bounded contexts □ Data consistency strategy documented')
Add concrete example inputs and outputs showing what a good architectural review looks like, including specific questions to ask and format for recommendations
Create a structured template for architectural decision records (ADRs) that Claude should produce, with actual field names and example content
Move reference material (pattern definitions, technology lists) to separate files and keep SKILL.md focused on the review workflow with clear validation steps
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive lists of concepts Claude already knows (SOLID principles, design patterns, cloud technologies). The 'Capabilities' section reads like a resume rather than actionable guidance, explaining basic concepts like 'Single Responsibility' that Claude understands. | 1 / 3 |
Actionability | No concrete code examples, commands, or executable guidance. The 'Instructions' section is vague ('Gather system context', 'Evaluate architecture decisions') without specific steps, templates, or examples of what good output looks like. | 1 / 3 |
Workflow Clarity | The 4-step instruction workflow exists but lacks validation checkpoints and concrete criteria. 'Evaluate architecture decisions and identify risks' provides no framework for how to actually do this or what constitutes a risk worth flagging. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. The massive 'Capabilities' and 'Knowledge Base' sections should be split into separate reference documents, leaving SKILL.md as a concise overview with clear navigation. | 1 / 3 |
Total | 5 / 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 |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- duclm1x1/Dive-Ai
- Commit
20ba150
- 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.