architect-review

Master software architect specializing in modern architecture

1.09x

Quality

26%

Does it follow best practices?

Impact

92%

1.09x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/architect-review/SKILL.md

The canonical home for this skill is architect-review in rmyndharis/antigravity-skills

Quality

Content

27%Weight 40%Scale 1-5

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

The body is a verbose persona profile rather than an actionable skill: it pads the context with domain knowledge Claude already has and offers only abstract guidance with no executable steps, templates, or validation. Section structure exists but everything is inlined with no progressive disclosure.

Suggestions

Replace the Capabilities/Knowledge Base/Behavioral Traits buzzword lists with a concrete review checklist or template (e.g. an ADR template, a bounded-context review checklist, or a scalability assessment rubric with specific questions).

Make the workflow executable by adding concrete commands or artifacts to each step, such as "Produce an ADR using the template in references/adr-template.md" with a validation checkpoint like "Confirm each decision lists its tradeoffs and a validation plan".

Move the capability catalogs into reference files (e.g. references/patterns.md, references/quality-attributes.md) and keep SKILL.md as a lean overview that links to them, establishing one-level-deep progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Large Capabilities, Knowledge Base, and Behavioral Traits sections enumerate concepts Claude already knows (SOLID, Kafka, service mesh, DDD, C4 model) as padded lists, making the body noticeably verbose with several unnecessary sections.	2 / 5
Actionability	The Instructions are entirely abstract ("Gather system context", "Evaluate architecture decisions", "Recommend improvements") with no code, commands, templates, or concrete artifacts, matching the anchor for vague description with no executable guidance.	1 / 5
Workflow Clarity	A sequenced workflow is present (4-step Instructions and an 8-step Response Approach) but the steps are high-level with no validation checkpoints or feedback loops, matching the anchor for steps listed with checkpoint gaps.	3 / 5
Progressive Disclosure	The 165-line body has good section headers but no references at all, and the large capability/knowledge walls that belong in separate files are fully inlined, matching the anchor for some structure with content that should be split kept inline.	3 / 5
	Total	9 / 20 Passed

Description

25%Weight 40%Scale 1-5

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 tagline rather than a trigger-oriented skill description: it states a role and domain but gives no concrete actions, no natural trigger phrases, and no "use when" guidance. This makes it weak on completeness, trigger quality, and distinctiveness.

Suggestions

Rewrite the description to lead with concrete actions, e.g. "Reviews system architecture and design changes, assesses scalability/resilience tradeoffs, and flags architectural violations and anti-patterns."

Add an explicit "Use when..." clause naming natural triggers, e.g. "Use when reviewing system architecture, evaluating a major design change, or assessing scalability and resilience impacts."

Narrow the niche and add distinguishing trigger terms (e.g. "architecture decision records", "bounded context", "service boundaries") to reduce overlap with general code-review skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ("software architect specializing in modern architecture") but lists no concrete actions, matching the anchor where the domain is named yet actions are minimal or generic.	2 / 5
Completeness	It offers a vague "what" (a master architect persona) with no "when" guidance at all, matching the anchor for a vague what and absent when, and the missing "Use when" clause caps it below 3.	2 / 5
Trigger Term Quality	"software architect" and "modern architecture" are role labels rather than natural phrases a user would say when needing this skill, and there is no "use when" trigger language, leaving only generic keywords.	2 / 5
Distinctiveness Conflict Risk	The broad persona framing overlaps heavily with code-review and security-review skills and lacks a clear niche, matching the very-broad / high-overlap-risk anchor.	2 / 5
	Total	8 / 20 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/architect-review/SKILL.md
Commit: 900c504

Reviewed: 7 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.