architect-review

Master software architect specializing in modern architecture

1.09x

Quality

28%

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/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 an expert-persona manifesto: extensive enumerations of architecture concepts Claude already knows, with abstract process steps and no executable guidance, templates, or validation checkpoints. It is monolithic with no progressive disclosure into reference files.

Suggestions

Cut the capability/knowledge catalogs (SOLID, design patterns, cloud services) — Claude knows these — and keep only the review process and decision criteria specific to this skill.

Add concrete, actionable artifacts: an ADR template, an architecture-review checklist, or a worked example of assessing a microservice design with explicit pass/fail criteria.

Insert validation checkpoints into the workflow (e.g. 'confirm bounded-context boundaries against domain model before scoring isolation') and move detailed pattern catalogs into a reference file referenced one level deep.

Dimension	Reasoning	Score
Conciseness	The ~165-line body is largely catalogs of well-known concepts (SOLID principles, GoF patterns, Kafka, Kubernetes) that Claude already knows, making it noticeably verbose with several padded sections despite clear headers.	2 / 5
Actionability	Instructions are abstract ('Gather system context', 'Evaluate architecture decisions and identify risks') with no concrete code, commands, templates, or worked examples — it describes rather than instructs, matching the 'entirely vague or abstract' anchor.	1 / 5
Workflow Clarity	Two sequenced lists (Instructions and Response Approach) provide a recognizable order, but steps are high-level and lack any validation checkpoints or feedback loops for verifying an architectural assessment.	3 / 5
Progressive Disclosure	Section headers give some structure, but the file is a single monolithic document with large inlined capability/reference catalogs and no external reference files, fitting 'some structure but content that should be separate is inline'.	3 / 5
	Total	9 / 20 Passed

Description

28%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 persona tagline rather than a functional skill description: it declares an identity but lists no concrete actions and provides no trigger guidance for when to invoke it. It is only moderately distinct from adjacent coding/design skills.

Suggestions

Rewrite the description as concrete actions, e.g. 'Reviews system architecture, evaluates scalability and resilience tradeoffs, and recommends design improvements'.

Add an explicit 'Use when...' clause naming natural trigger phrases such as 'architecture review', 'system design', or 'scalability assessment'.

Include specific trigger terms users would say (e.g. 'microservices', 'bounded contexts', 'event-driven design') instead of the generic 'modern architecture'.

Dimension	Reasoning	Score
Specificity	The description 'Master software architect specializing in modern architecture' names the domain but offers no concrete actions — it states a role/title rather than any verb of what the skill does, fitting the 'names domain but actions minimal or generic' anchor.	2 / 5
Completeness	It gives a vague 'what' (a persona, not actions) and entirely omits any 'when'/'Use when' trigger clause, which caps completeness at 3 and lands it at the 'vague what and no when' anchor.	2 / 5
Trigger Term Quality	Only one or two generic keywords ('software architect', 'modern architecture') appear, missing the natural phrases a user would actually say ('review my architecture', 'system design', 'scalability'), matching the 'one or two generic keywords' anchor.	2 / 5
Distinctiveness Conflict Risk	'Software architecture' is a recognizable niche distinguishable from generic code skills, but 'modern architecture' is broad enough to overlap with general code-review or design skills, fitting 'somewhat specific but could still overlap'.	3 / 5
	Total	9 / 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/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.