architecture-strategist

Analyzes code changes from an architectural perspective for pattern compliance and design integrity. Use when reviewing PRs, adding services, or evaluating structural refactors.

Quality

67%

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 ./.agents/skills/architecture-strategist/SKILL.md

Quality

Content

55%

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 well-organized, clearly sequenced instruction set for an architecture-review agent, but it leans on generic software-engineering explanations Claude already knows and lacks executable tooling or validation loops. Structure is adequate but monolithic with no progressive disclosure.

Suggestions

Trim well-known exposition (e.g., spelling out all five SOLID principles, generic coupling/cohesion definitions) and keep only skill-specific guidance to improve token efficiency.

Add concrete, executable signals or commands (e.g., specific import-graph or coupling-analysis commands, a circular-dependency check) to make the guidance copy-paste ready.

Add an explicit validation/feedback checkpoint (e.g., 're-run dependency check after recommendations to confirm no new circular dependencies') to strengthen the workflow.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient directive guidance, but restates well-known concepts (explaining SOLID principles by name, generic advice on 'coupling, cohesion, separation of concerns') that Claude already knows, so it could be tightened; not verbose enough for a 1 but not lean enough for a 3.	2 / 3
Actionability	It gives concrete categories of what to inspect (import statements, coupling metrics, API contracts) and a structured output format, but offers no executable commands, tooling, or specific heuristics — guidance is directional rather than copy-paste ready.	2 / 3
Workflow Clarity	A clear 4-step sequence is present (Understand → Analyze → Identify → Consider), but there are no validation checkpoints or feedback loops; for an analysis-only (non-destructive) skill this is acceptable, yet the explicit 'must verify' checklist is asserted without a verify-and-retry loop.	2 / 3
Progressive Disclosure	Content is well sectioned with no bundle files present, but everything lives in a single monolithic body with no external references or navigation pointers; reasonable for a short skill but not optimally structured for deeper material.	2 / 3
	Total	8 / 12 Passed

Description

80%

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 cleanly answers both what and when with an explicit trigger clause and natural phrasing. Its main weakness is modest specificity and some overlap with general code-review skills.

Suggestions

Add a couple concrete actions (e.g., 'maps service boundaries, detects coupling and circular dependencies, checks SOLID compliance') to raise specificity.

Tighten the 'when' clause to emphasize architectural intent (e.g., 'when changes affect service boundaries or cross-component contracts') to reduce overlap with general code review.

Dimension	Reasoning	Score
Specificity	It names the domain ('architectural perspective') and concrete review actions ('pattern compliance and design integrity'), but stays at a summary level rather than enumerating multiple specific actions; closest to 'names domain and some actions, but not comprehensive'.	2 / 3
Completeness	It answers both 'what' (analyzes code changes for pattern compliance and design integrity) and 'when' via an explicit 'Use when reviewing PRs, adding services, or evaluating structural refactors' clause, matching the top anchor.	3 / 3
Trigger Term Quality	It includes natural user phrases ('reviewing PRs, adding services, or evaluating structural refactors') that a user would plausibly say, giving good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	The 'architectural perspective' niche is reasonably distinct, but the trigger 'evaluating structural refactors' overlaps with general code-review skills, so it could still trigger competing reviewers.	2 / 3
	Total	10 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/architecture-strategist/SKILL.md
Commit: 45116fd

Reviewed: about 15 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.