CtrlK
BlogDocsLog inGet started
Tessl Logo

aiox-master

AIOX Master Orchestrator & Framework Developer (Orion). Use when you need comprehensive expertise across all domains, framework component creation/modification, workflow orchest...

52

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/aiox-master/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

27%

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 monolithic, heavily duplicated agent definition that violates progressive disclosure and token efficiency, despite offering a genuinely concrete command catalog. Sequences are present but validation checkpoints are weak or explicitly advisory.

Suggestions

Eliminate the duplicated command catalog: keep the Star Commands table and remove the second copy embedded in the YAML 'commands:' block (or vice-versa).

Move the full agent YAML definition and persona_profile material into a bundled reference file (e.g. references/agent-definition.yaml) and have SKILL.md point to it one level deep, instead of inlining everything.

Add explicit validation checkpoints (e.g. run *validate-component / *validate-workflow after create/modify) as blocking steps in the Typical Workflow rather than leaving IDS hooks advisory-only.

DimensionReasoningScore

Conciseness

The ~470-line body duplicates the entire command catalog twice (the Star Commands table and again inside the inlined YAML block) and is padded with persona material (zodiac, vocabulary, emoji frequency) that does not earn its tokens.

1 / 3

Actionability

The Star Commands table with concrete args ('*create agent {name}', '*validate-workflow {name|path} [--strict]') is copy-paste ready, but it is buried under large amounts of abstract descriptive and persona content rather than executable guidance.

2 / 3

Workflow Clarity

Sequences exist (Activation Protocol, Typical Workflow, STEP 1-5) but validation checkpoints are implicit, and the IDS pre-action hooks are explicitly 'advisory (non-blocking)' with no validate->fix->retry feedback loop.

2 / 3

Progressive Disclosure

The body declares 'NO EXTERNAL FILES NEEDED' and inlines the complete agent YAML definition rather than splitting it, and its references point to external framework files (.aiox-core/...) that are absent from the empty bundle — a monolithic wall rather than an overview with one-level-deep references.

1 / 3

Total

6

/

12

Passed

Description

90%

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 well-structured with explicit what/when triggers and natural activation phrases, making it highly complete and distinctive. Its only weakness is mild over-claiming fluff ('comprehensive expertise across all domains') alongside otherwise concrete actions.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Activate the AIOX Master Orchestrator & Framework Developer agent', 'framework component creation/modification, workflow orchestration'), but pads them with vague over-claims like 'comprehensive expertise across all domains'.

2 / 3

Completeness

Explicitly answers both 'what' ('Activate the AIOX Master Orchestrator & Framework Developer agent (Orion)') and 'when' ('Use when...', 'Trigger when...').

3 / 3

Trigger Term Quality

Provides good natural trigger coverage users would actually say: 'asks to aiox-master', 'activate aiox-master', 'switch to aiox-master', '@aiox-master'.

3 / 3

Distinctiveness Conflict Risk

A clearly named, niche agent ('AIOX Master Orchestrator') with distinct trigger phrases unlikely to fire for the wrong skill.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (583 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
SynkraAI/aiox-core
Reviewed

Table of Contents

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.