architect-review

Master software architect specializing in modern architecture

Quality

28%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/antigravity-architect-review/SKILL.md

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-and-catalog document: it restates expertise and enumerates architecture topics Claude already knows instead of giving concrete review methodology. Workflow and file structure are present but loose, with no validation checkpoints or reference-file split.

Suggestions

Delete the Capabilities, Behavioral Traits, and Knowledge Base sections (or move them to a reference file) since they restate concepts Claude already knows; keep only review-specific methodology Claude would not infer.

Replace the vague Instructions with a concrete, sequenced review workflow: define the artifacts to request, a checklist of architecture dimensions to score, and an ADR/output template to produce.

Add an explicit validation checkpoint (e.g. 'confirm assumptions and constraints with the user before rating impact') and reconcile the duplicate Instructions and Response Approach step lists into one sequence.

Dimension	Reasoning	Score
Conciseness	The body is heavily padded: the ~80-bullet Capabilities catalog, Knowledge Base (Fowler/Evans/Uncle Bob), and Behavioral Traits extensively enumerate concepts Claude already knows, matching the severely-verbose anchor.	1 / 5
Actionability	Guidance is high-level hints ("Gather system context", "Evaluate architecture decisions and identify risks") with no concrete methodology, checklist, or ADR template despite mentioning ADRs, fitting the minimal-concrete-guidance anchor.	2 / 5
Workflow Clarity	A sequence exists but two overlapping step lists (Instructions vs Response Approach) compete, and validation is only vaguely implied ("follow up on validation") without explicit checkpoints or a fix-and-retry loop.	3 / 5
Progressive Disclosure	Headers and subsections provide real structure, but the ~170-line file is monolithic with the large capabilities/knowledge catalog inlined rather than split into reference files, matching the some-structure-but-inline-content anchor.	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 reads as a persona title rather than a capability/trigger statement: it names a domain but gives no concrete actions and no 'use when' guidance. It is distinguishable but weak on specificity, triggers, and completeness.

Suggestions

Rewrite in third-person action voice listing concrete capabilities, e.g. "Reviews system architecture, evaluates scalability/resilience tradeoffs, and recommends pattern-based improvements."

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

Tighten distinctiveness by scoping to architectural impact (e.g. "for changes with cross-module or system-wide architectural impact") to avoid overlap with routine code-review skills.

Dimension	Reasoning	Score
Specificity	The description "Master software architect specializing in modern architecture" names the domain specifically but lists zero concrete actions (no review/evaluate/assess verbs), making it more abstract than the score-3 anchor that expects named actions.	2 / 5
Completeness	It offers a vague 'what' (a persona, not actions) and no 'when'/Use-when clause at all, hitting the "vague what and no when" anchor; the missing trigger guidance caps completeness at 3 and this sits below it.	2 / 5
Trigger Term Quality	Only "software architect" and "modern architecture" appear as keywords; the natural phrases users actually say ("architecture review", "design review", "system design") are missing, matching the one-or-two-generic-keywords anchor.	2 / 5
Distinctiveness Conflict Risk	The architecture-review niche is somewhat specific, but the generic "software architect" framing could still overlap with general code-review or design skills, matching the "somewhat specific but could still overlap" anchor.	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: boisenoise/skills-collections
Path: skills/antigravity-architect-review/SKILL.md
Commit: 19c310e

Reviewed: about 22 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.