aiox-architect

Architect (Aria). Use for system architecture (fullstack, backend, frontend, infrastructure), technology stack selection (technical evaluation), API design (REST/GraphQL/tRPC/WebSocket), security architecture, perfo... Triggers: architecture, architect, @architect, tech stack, API design, system design, impact analy...

Quality

75%

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 ./.grok/skills/aiox-architect/SKILL.md

Quality

Content

76%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 compact, action-oriented activation protocol with concrete shell commands and clear section structure. It loses points on workflow clarity for lacking validation checkpoints on state-mutating steps, and references external files that are not part of any bundle.

Suggestions

Add a validation step after Protocol step 1 (e.g., verify .aiox/active-agent contains 'architect') before proceeding to persona load.

Bundle the referenced persona/source files (.grok/agents/aiox-architect.md, .aiox-core/development/agents/architect.md) in references/ so the skill is self-contained.

Clarify what happens if the source-of-truth files are missing beyond the single fallback path, to close the gap in the load chain.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: terse protocol steps, exact shell commands, and compact lists with no padding or explanation of concepts Claude already knows.	5 / 5
Actionability	Provides executable shell commands (mkdir, printf, export) and concrete file paths, but several key commands reference external files the agent must load rather than including them inline.	4 / 5
Workflow Clarity	Steps are clearly numbered but the workflow involves mutating session/git state (registering active agent) with no validation checkpoint confirming the files were written or agent switched; cap applies.	3 / 5
Progressive Disclosure	Well-organized sections point one level deep to source-of-truth files (.grok/agents, .aiox-core), but the actual referenced files are not bundled, so structure is clear yet references are unverifiable.	4 / 5
	Total	16 / 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.

A well-targeted architecture skill description with concrete capabilities and explicit trigger terms. Its main weakness is the ellipsis truncation that cuts off the capability list mid-sentence, slightly degrading completeness and specificity.

Suggestions

Replace the 'perfo...' and 'impact analy...' ellipsis truncations with the full text so the capability and trigger lists are complete.

Expand trigger synonyms for less-technical users (e.g., 'design the system', 'pick technologies', 'choose a stack').

Dimension	Reasoning	Score
Specificity	Lists concrete domains/actions (fullstack/backend/frontend architecture, tech stack selection, API design across REST/GraphQL/tRPC/WebSocket, security architecture) with minor coverage gaps from the ellipsis-truncated text.	4 / 5
Completeness	Explicit 'Use for...' states the what and a 'Triggers:' clause states the when, but the when guidance is somewhat compressed and the description is truncated mid-sentence.	4 / 5
Trigger Term Quality	Includes natural user phrases (architecture, architect, @architect, tech stack, API design, system design, impact analysis, ADR) covering common variations, though synonyms are limited.	4 / 5
Distinctiveness Conflict Risk	Scoped to a clear architecture niche with distinct triggers; minor overlap risk with adjacent dev agents (backend/frontend/data-engineer).	4 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

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

	Total	14 / 16 Passed

Repository: SynkraAI/aiox-core
Path: .grok/skills/aiox-architect/SKILL.md
Commit: 4ef6530

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.