architect-review
Master software architect specializing in modern architecture
19
0%
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/antigravity-architect-review/SKILL.mdQuality
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 essentially a title or role label rather than a functional skill description. It lacks any concrete actions, trigger terms, or usage guidance, making it nearly impossible for Claude to correctly select this skill from a pool of alternatives. It also uses a noun-phrase style rather than describing capabilities in third person.
Suggestions
Replace the role label with specific actions the skill performs, e.g., 'Designs system architectures, evaluates trade-offs between microservices and monoliths, creates architecture diagrams, and reviews code for architectural patterns.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about system design, microservices, design patterns, scalability, architecture reviews, or service decomposition.'
Include concrete domain keywords users would naturally say, such as 'microservices', 'monolith', 'API design', 'scalability', 'design patterns', 'event-driven', 'domain-driven design'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language ('Master software architect') with no concrete actions listed. It doesn't describe what the skill actually does—no verbs like 'designs', 'reviews', or 'generates'. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. There is no 'Use when...' clause and no description of capabilities. | 1 / 3 |
Trigger Term Quality | 'Modern architecture' is overly generic and not a natural phrase users would say when seeking help. There are no specific trigger terms like 'microservices', 'system design', 'architecture diagram', or 'design patterns'. | 1 / 3 |
Distinctiveness Conflict Risk | 'Software architect' and 'modern architecture' are extremely broad and could overlap with virtually any coding, design, or engineering skill. There is nothing to distinguish this from other development-related skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a persona description and knowledge catalog rather than actionable guidance. It extensively lists architecture concepts, patterns, and technologies that Claude already knows, consuming significant token budget without adding value. It lacks any concrete examples, templates, code snippets, decision frameworks, or structured output formats that would make architectural reviews consistent and actionable.
Suggestions
Remove the entire 'Capabilities', 'Knowledge Base', and 'Behavioral Traits' sections — Claude already knows these concepts. Replace with a concise checklist or decision framework for conducting architectural reviews.
Add concrete output templates: e.g., an Architecture Decision Record (ADR) template, a review findings format with severity levels, or a structured JSON/markdown schema for architectural assessments.
Provide at least one complete worked example showing input (e.g., a proposed architecture change) and the expected review output with specific findings, risk ratings, and recommendations.
Add explicit validation checkpoints to the workflow: e.g., 'Before recommending changes, verify you have: system context, non-functional requirements, current architecture diagram or description. If missing, ask the user.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and padded with information Claude already knows. The 'Capabilities' section is essentially a catalog of architecture concepts (SOLID principles, design patterns, cloud-native patterns, etc.) that Claude is already deeply familiar with. The 'Knowledge Base' and 'Behavioral Traits' sections add no actionable value. The entire skill could be reduced to under 30 lines without losing any useful guidance. | 1 / 3 |
Actionability | No concrete code, commands, templates, or executable examples anywhere. The instructions are entirely abstract ('Gather system context', 'Evaluate architecture decisions', 'Recommend improvements'). The 'Example Interactions' section lists prompts but provides no example outputs or response formats. There is nothing copy-paste ready or specifically instructive. | 1 / 3 |
Workflow Clarity | The 4-step 'Instructions' workflow is extremely vague ('Gather system context, goals, and constraints' — how?). The 'Response Approach' provides 8 steps but they are abstract descriptions without validation checkpoints, feedback loops, or concrete criteria for decision-making. No verification steps exist for architectural reviews, which are inherently high-risk operations. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files and no bundle files. All content is inline in a single massive document. The extensive 'Capabilities' catalog should either be removed (Claude knows this) or split into referenced files. No navigation structure or clear hierarchy beyond flat section headers. | 1 / 3 |
Total | 4 / 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
- boisenoise/skills-collections
- Commit
431bfad
- 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.