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

51%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.

A well-structured agent persona with a clear workflow and output format, but it is held back by abstract, non-executable guidance and some over-explanation of architectural concepts Claude already knows. Adding concrete detection commands or tooling and trimming redundant concept explanations would materially raise quality.

Suggestions

Make guidance executable: name specific commands or tools for detecting coupling, circular dependencies, or boundary violations (e.g. a dependency-graph command or a lint rule to run), rather than 'Analyze coupling metrics including import depth.'

Trim redundant concept restatement — the SOLID principles, 'coupling/cohesion/separation of concerns,' and the 'architectural smells' list largely overlap; consolidate to reduce tokens.

Add an explicit validation checkpoint in the workflow, e.g. a step to verify findings against documented architecture before producing the final structured report.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient prose for an instruction-only agent definition, but it explains architectural concepts Claude already knows (SOLID principles listed out, generic 'coupling, cohesion, separation of concerns' framing) and repeats similar guidance across the 'Analyze,' 'must verify,' and 'architectural smells' sections.	3 / 5
Actionability	Guidance is high-level and abstract ('Map component dependencies by examining import statements,' 'Analyze coupling metrics') with no concrete commands, code, tooling, or specific detection steps, leaving Claude without executable instructions.	2 / 5
Workflow Clarity	The 4-step 'systematic approach' is a clear sequence and the output format is specified as a 5-part structure, but there are no explicit validation checkpoints or error-recovery feedback loops within the analysis steps.	4 / 5
Progressive Disclosure	Content is well-organized into clearly signaled sections (approach, analysis checklist, evaluation criteria, output format, smells) with no nested references and no bundle files to misroute; it is slightly long for an overview but structured for easy navigation.	4 / 5
	Total	13 / 20 Passed

Description

83%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.

A solid description that clearly states both what it does and when to use it, with natural trigger terms and mostly concrete language. It could be more specific by enumerating discrete actions and tightening the trigger to reduce overlap with generic code-review skills.

Suggestions

Replace abstract phrases ('pattern compliance and design integrity') with concrete actions, e.g. 'Detects architectural anti-patterns, coupling and boundary violations, and SOLID principle breaks in code changes.'

Narrow the 'Use when' clause to architectural triggers (e.g. 'evaluating structural refactors, adding services, or reviewing cross-cutting design changes') to reduce overlap with generic code-review skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('code changes from an architectural perspective') and several concrete actions implied by 'pattern compliance and design integrity,' though it leans on abstract phrasing rather than enumerating discrete actions, leaving minor coverage gaps.	4 / 5
Completeness	It explicitly answers both 'what' ('Analyzes code changes... for pattern compliance and design integrity') and 'when' ('Use when reviewing PRs, adding services, or evaluating structural refactors') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user-facing terms ('reviewing PRs,' 'adding services,' 'structural refactors') that a developer would actually say, though it lacks synonyms and the phrase 'architectural perspective' is somewhat technical.	4 / 5
Distinctiveness Conflict Risk	The architecture-review niche is reasonably distinct from general code-review skills, though the broad trigger 'reviewing PRs' creates minor overlap risk with generic review skills.	4 / 5
	Total	17 / 20 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: cce36d3

Reviewed: 1 day 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.