CtrlK
BlogDocsLog inGet started
Tessl Logo

aiox-devops

Activate Gage (devops) for GitHub Repository Manager & DevOps Specialist. Use for repository operations, version management, CI/CD, quality gates, and GitHub push operations. ONLY agent authorized to push to remote repository.

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

The body is highly actionable and workflow-clear, with concrete commands and well-sequenced validation-gated processes. Its main weaknesses are severe verbosity from duplicated command/identity blocks and poor progressive disclosure from the monolithic inline YAML and unverifiable external references.

Suggestions

Collapse the duplicated command listings: the Star Commands table and the commands YAML block enumerate the same ~45 commands twice, and identity/persona is described three times — keep a single command list and one identity definition to roughly halve the file length.

Move the inline agent-definition YAML (lines 81-586) into a bundled reference file and reduce SKILL.md to a concise overview that links to it, turning the monolithic wall into one-level-deep, clearly signaled references.

Remove persona content with no operational value (zodiac sign, Portuguese vocabulary such as 'deployar'/'automatizar', signature closings) to respect the token budget.

DimensionReasoningScore

Conciseness

The ~697-line body is heavily padded: the 45 commands are duplicated across the Star Commands table and the commands YAML block, the identity/persona is stated three times, and non-operational fluff (zodiac '♈ Aries', Portuguese vocabulary like 'deployar', signature closings) competes for the context window.

1 / 3

Actionability

Provides concrete, executable guidance — quality-gate commands (npm run lint/test/typecheck/build), CodeRabbit CLI invocations with per-OS variants, and a release SOP grounded in real specifics (ruleset id 13330052, 4-site version coordination, 240s npm propagation budget).

3 / 3

Workflow Clarity

Workflows (standard_push, release_creation, repository_cleanup) are clearly sequenced with explicit validation checkpoints — gates must PASS, user confirmation required, and a greenfield-guard error branch handles the no-git-repo case.

3 / 3

Progressive Disclosure

Some section structure exists, but the entire agent definition sits as a monolithic inline YAML block (content that should be separate is inline), references point to absent non-bundled files, and a 2-level task→SOP chain (release-management.md → release-procedure.md) is present.

2 / 3

Total

9

/

12

Passed

Description

100%

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, uses third-person voice, covers natural trigger terms, and explicitly states both capabilities and activation conditions. It is a strong, concise skill description with no over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'repository operations, version management, CI/CD, quality gates, and GitHub push operations' — matching the anchor for several specific capabilities rather than vague language.

3 / 3

Completeness

Explicitly answers both what ('Use for repository operations, version management, CI/CD...') and when ('Trigger when user asks to devops, or says...'), with an explicit trigger clause.

3 / 3

Trigger Term Quality

Includes natural trigger phrases a user would actually say — 'activate devops', 'switch to devops', '@devops' — giving good coverage of natural terms.

3 / 3

Distinctiveness Conflict Risk

The 'ONLY agent authorized to push to remote repository' claim carves out a clear, distinct niche unlikely to conflict with other skills.

3 / 3

Total

12

/

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 (698 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.