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

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

Quality

Content

50%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete commands and platform-specific CLI guidance, but it is bloated with persona/astrology fluff and an inlined monolithic agent definition that hurts token efficiency. Architecture-design workflows also lack explicit validation checkpoints.

Suggestions

Strip persona decoration (zodiac, Portuguese vocabulary, archetypal greetings, emoji-laden activation ceremony) that does not help Claude architect systems; keep only operating parameters.

Move the large agent-definition YAML into a reference file and keep SKILL.md as a lean overview pointing to it, so progressive disclosure is one level deep.

Add explicit validation/feedback-loop checkpoints to the architecture design workflow (e.g., verify the produced architecture against NFRs and the checklist before handoff).

Dimension	Reasoning	Score
Conciseness	The body is padded with persona fluff Claude does not need — zodiac sign ("♐ Sagittarius"), a Portuguese vocabulary list ("arquitetar, conceber..."), archetypal greetings, and a multi-screen activation pipeline — matching the verbose anchor that explains/surrounds the actual task with unnecessary context.	1 / 3
Actionability	It provides concrete, executable guidance: exact git allowed/blocked operations, platform-specific CodeRabbit CLI invocations (macOS/Linux vs WSL), timeout values, and named commands with `*` prefixes, matching the copy-paste-ready anchor.	3 / 3
Workflow Clarity	Activation is sequenced with numbered steps and some validation (Greenfield Guard, CodeRabbit error-handling branches), but the core architecture workflow is a loose 5-step list without validation checkpoints on the design output, fitting the anchor for steps present but checkpoints missing.	2 / 3
Progressive Disclosure	No bundle files (references/scripts/assets) exist, yet the body references external dependency paths (`.aiox-core/development/{type}/{name}`) that are not part of this skill, and a large monolithic YAML agent definition is inlined rather than split — matching the anchor for some structure but content that should be separate is inline.	2 / 3
	Total	8 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 specific and complete with explicit use-when triggers and clear niche boundaries, though the trigger term list is somewhat technical and cut off mid-word. It is strong but would benefit from completing the truncated tail and adding a few more natural phrasings.

Suggestions

Complete the truncated description ("perf...") so the full capability list and any closing trigger clause is visible.

Add more natural user-facing phrasings alongside the technical terms (e.g., "Use when designing a new system", "Use when choosing a tech stack") to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete domains — "system architecture (fullstack, backend, frontend, infrastructure)", "API design (REST/GraphQL/tRPC/WebSocket)", "security architecture" — matching the anchor for listing several specific capabilities rather than vague language.	3 / 3
Completeness	It states what it does ("Activate Aria (architect) for Architect") and gives an explicit "Use for..." trigger clause enumerating when to invoke it, satisfying both the what and the when.	3 / 3
Trigger Term Quality	Terms like "Use for system architecture", "technology stack selection", and "API design" are reasonable but lean technical and are truncated ("perf..."); coverage of common user phrasings is partial, matching the anchor for some relevant keywords but missing common variations.	2 / 3
Distinctiveness Conflict Risk	It carves a clear architecture niche and the fuller body specifies delegation boundaries (NOT for market research → @analyst, PRD → @pm), making it unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 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: 0b32b68

Reviewed: 7 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.