aiox-architect

Activate the AIOX Architect agent (Aria). Use for system architecture (fullstack, backend, frontend, infrastructure), technology stack selection (technical evaluation), API design (REST/GraphQL/tRPC/WebSocket), security architecture, performance optimization, deployment strategy, and cross-cutting concerns (logging, monitoring, error han... Trigger when user asks to architect, or says 'activate architect', 'switch to architect', '@architect'.

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.kimi/skills/aiox-architect/SKILL.md

Quality

Content

46%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.

An instruction-rich agent-activation skill with strong actionability (concrete CLI commands, command catalog, git guardrails) undermined by significant verbosity and poor progressive disclosure — the entire agent definition is inlined as a monolithic YAML block and the command list is repeated three times. Splitting the YAML and command catalog into referenced files and de-duplicating would substantially improve it.

Suggestions

Move the full agent-definition YAML and the command catalog into separate reference files (e.g. references/agent-definition.yaml, references/commands.md) and keep SKILL.md as a concise overview that links to them one level deep.

De-duplicate the command list: keep it in a single canonical location and have the Star Commands table and Quick Commands section reference or summarize it rather than re-listing every entry.

Trim persona padding that does not affect behavior (zodiac, Portuguese vocabulary, multiple greeting levels) to recover context-window budget.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: the command set is duplicated three times (Star Commands table, the YAML 'commands' block, and the Quick Commands section), and persona padding (zodiac sign, Portuguese vocabulary list, three greeting levels) does not earn its context-window cost.	2 / 5
Actionability	Gives concrete, executable guidance — exact star-command names, platform-specific CodeRabbit CLI invocations with a 900000ms timeout, explicit git allow/block lists — with only minor gaps where commands defer to external task files not present in the bundle.	4 / 5
Workflow Clarity	Activation is sequenced as STEP 1–5 and the CodeRabbit review workflow has numbered steps with error handling, but the core architecture-creation workflow is delegated to external task files that are not shown, leaving the central process with implicit rather than explicit checkpoints.	3 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets are absent), and the body inlines a ~390-line monolithic YAML agent definition plus repeated command tables; content that belongs in separate, one-level-deep reference files is buried inside SKILL.md.	2 / 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.

A well-structured description that follows the 'what + when + triggers' template with comprehensive, specific capabilities and natural trigger phrases. Its one clear defect is the mid-word truncation 'error han...', which cuts off the final capability and slightly weakens completeness and specificity.

Suggestions

Restore the truncated tail of the description so the 'cross-cutting concerns' item reads completely (e.g. 'logging, monitoring, error handling') instead of 'error han...'.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability areas ('system architecture (fullstack, backend, frontend, infrastructure)', 'API design (REST/GraphQL/tRPC/WebSocket)', 'security architecture', 'performance optimization', 'deployment strategy'), but the final 'cross-cutting concerns (logging, monitoring, error han...' is truncated mid-word, leaving a minor coverage gap.	4 / 5
Completeness	Explicitly answers both 'what' ('Use for system architecture...') and 'when' ('Trigger when user asks to architect...') with concrete trigger phrases, matching the strong anchor; held at 4 rather than 5 only because the 'what' list is cut off mid-item by the 'error han...' truncation.	4 / 5
Trigger Term Quality	Provides natural trigger phrases users would actually say — 'asks to architect', 'activate architect', 'switch to architect', '@architect' — giving good keyword coverage, though a few common synonyms (e.g. 'design the system', 'system design') are absent.	4 / 5
Distinctiveness Conflict Risk	The persona-scoped '@architect' / 'activate architect' triggers carve a clear niche within the AIOX multi-agent system, with only minor overlap risk against adjacent dev/architecture skills.	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
skill_md_line_count	SKILL.md is long (545 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

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

Reviewed: 2 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.