architect-review

Master software architect specializing in modern architecture

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

20%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body functions as a persona definition rather than actionable guidance: it catalogs well-known architectural concepts and lists abstract steps without concrete examples, validation, or external references. It is well-sectioned but token-inefficient and not executable.

Suggestions

Replace the long capability/knowledge-base catalogs with concise, novel review guidance (e.g., a concrete checklist or ADR template) instead of restating SOLID, DDD, and cloud-native concepts Claude already knows.

Add an executable worked example: a sample architecture-review output showing the High/Medium/Low impact assessment and a sample ADR.

Introduce validation checkpoints into the workflow (e.g., "Confirm requirements and constraints before assessing", "Re-validate assumptions with the user before recommending high-risk changes") and consider moving the reference catalogs into a separate bundled file.

Dimension	Reasoning	Score
Conciseness	The body is verbose and enumerates concepts Claude already knows (e.g., "Single Responsibility, Open/Closed, Liskov Substitution principles", "Container orchestration with Kubernetes"), padding the context window with unnecessary reference lists rather than adding novel guidance.	1 / 3
Actionability	The skill describes rather than instructs: "Clean Architecture and Hexagonal Architecture implementation" and "Evaluate architecture decisions and identify risks" give no concrete code, commands, templates, or worked examples, matching the vague/abstract score-1 anchor.	1 / 3
Workflow Clarity	Two sequenced step lists ("Instructions" and "Response Approach") are present, but they stay high-level and include no validation checkpoints or feedback loops, fitting the score-2 anchor of "steps listed but validation gaps" rather than the validated score-3 anchor.	2 / 3
Progressive Disclosure	The document has section headers giving it structure, but ~170 lines of capability and knowledge-base lists are inlined in SKILL.md with no external file references, matching the score-2 anchor where content that should be separate is inline.	2 / 3
	Total	6 / 12 Passed

Description

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is a generic persona statement with no concrete actions, no natural trigger terms, and no "Use when" guidance, making it weak on completeness and specificity. It has a recognizable architecture niche but is not distinctive enough to reliably trigger over similar skills.

Suggestions

Rewrite the description in third person naming concrete actions, e.g., "Reviews system architecture and major design changes, evaluates scalability and resilience tradeoffs, and produces architectural decision records."

Add an explicit "Use when..." clause with natural trigger terms users would say ("architecture review", "system design", "scalability assessment").

Avoid persona framing ("Master software architect") in the description; lead with what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	The description "Master software architect specializing in modern architecture" states a persona rather than concrete actions; it names no specific tasks, matching the vague/abstract anchor ("Helps with documents") and falling below the score-2 anchor that names a domain and some actions.	1 / 3
Completeness	The "what" is only a weak persona statement and the "when" is entirely missing, hitting the "both very weak" condition of the score-1 anchor; it does not reach score 2 because there is no clear statement of concrete capabilities.	1 / 3
Trigger Term Quality	There are no natural trigger keywords a user would say when needing this skill and no "Use when" guidance; "master software architect" and "modern architecture" are generic persona phrases rather than the natural terms (e.g., "architecture review", "system design") users would actually invoke.	1 / 3
Distinctiveness Conflict Risk	The architecture focus provides a niche, but the generic persona phrasing could still overlap with general code-review or software-engineering skills, matching the "somewhat specific but could still overlap" anchor rather than the clearly-distinct score-3 anchor.	2 / 3
	Total	5 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Commit: 9fc5f98

Reviewed: about 2 hours ago

Table of Contents

Discovery Implementation Validation

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.