aiox-architect

Activate Aria (architect) for Architect. Use for system architecture (fullstack, backend, frontend, infrastructure), technology stack selection (technical evaluation), API design (REST/GraphQL/tRPC/WebSocket), security architecture, perf...

Quality

58%

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 ./.claude/skills/AIOX/agents/architect/SKILL.md

Quality

Content

42%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 content is a large agent-definition bundle: strong on CodeRabbit integration specifics but padded with persona flourishes and a monolithic inline YAML config. Architecture-task guidance stays abstract while operational mechanics are detailed, leaving workflow and disclosure only partially realized.

Suggestions

Move the full agent-definition YAML (persona_profile, commands, dependencies, coderabbit_integration) into a referenced file and keep SKILL.md as a lean overview with a Quick start and a one-level-deep reference, improving both conciseness and progressive disclosure.

Replace the abstract one-line command descriptions for the core architecture commands with concrete, executable guidance (inputs, expected output artifact, an example invocation).

Add an explicit validation checkpoint to the architecture workflow (e.g., run the architect-checklist and verify the output against NFRs before handing off to @dev), and trim persona flourishes (zodiac, Portuguese vocabulary, archetypal greetings) that do not aid the task.

Dimension	Reasoning	Score
Conciseness	The ~490-line body is noticeably verbose: persona flourishes (zodiac sign, Portuguese vocabulary list, archetypal greetings), repeated CRITICAL/MANDATORY rule statements, and very detailed CodeRabbit severity examples pad the skill well past what Claude needs to act.	2 / 5
Actionability	Concrete where it covers CodeRabbit (real CLI commands, timeout, error handling) but the core architecture commands carry only one-line descriptions with no executable design steps, leaving the primary task guidance incomplete.	3 / 5
Workflow Clarity	A five-step Typical Workflow and a CodeRabbit workflow with error handling are present, but the architecture-design sequence lacks explicit validation checkpoints and feedback loops for reviewable outputs.	3 / 5
Progressive Disclosure	No bundle/reference files exist and the entire agent configuration is inlined as one large YAML block rather than split into separate files; section headers provide some structure but the monolithic inline config keeps navigation weak.	3 / 5
	Total	11 / 20 Passed

Description

75%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 covers a clear, specific architect domain with strong technical trigger terms and an explicit Use-for clause. Its main weakness is the truncated "perf..." ending, which leaves both completeness and trigger coverage slightly short of comprehensive.

Suggestions

Complete the truncated "perf..." (e.g., "performance optimization, deployment strategy, and cross-cutting concerns") so the description reads as a finished sentence.

Add the NOT-for boundaries (e.g., "NOT for market research, PRD creation, or database schema design") from the body to reduce overlap with sibling agents.

Drop the redundant "Activate Aria (architect) for Architect." opener, which restates the name without adding capability information.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions across distinct domains ("system architecture (fullstack, backend, frontend, infrastructure)", "technology stack selection", "API design (REST/GraphQL/tRPC/WebSocket)", "security architecture"), but the truncated "perf..." leaves coverage incomplete rather than comprehensive.	4 / 5
Completeness	Has a clear "what" ("Activate Aria (architect)...") and an explicit "Use for..." trigger clause, but the description is cut off mid-sentence at "perf..." so the "when" guidance is not fully delivered, keeping it below a 5.	4 / 5
Trigger Term Quality	Good keyword coverage with concrete technical terms (REST, GraphQL, tRPC, WebSocket, security architecture, tech stack) that users would naturally say, though natural synonyms are missing and the "perf..." truncation drops likely trigger terms.	4 / 5
Distinctiveness Conflict Risk	Targets a specific architect niche with concrete technology triggers, making it mostly distinct from sibling agents; minor overlap risk remains because the description omits the NOT-for delegation boundaries the body defines.	4 / 5
	Total	16 / 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: SynkraAI/aiox-core
Path: .claude/skills/AIOX/agents/architect/SKILL.md
Commit: 4ef6530

Reviewed: 19 days 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.