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.

Quality

66%

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

Quality

Content

45%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.

The body is well-sequenced with solid validation checkpoints in its push/release workflows, but it is hurt by a large inlined YAML config block (content that belongs in separate files) and padding that inflates token cost. References to external task/template files are clear, but no actual bundle files ship alongside the skill.

Suggestions

Move the embedded agent YAML (persona, vocabulary, greeting levels, command catalog, coderabbit integration) into a referenced bundle file and keep SKILL.md as a lean overview, which would substantially improve both conciseness and progressive disclosure.

Cut persona scaffolding that does not change Claude's behavior (zodiac, emoji_frequency, Spanish vocabulary list) unless it is genuinely load-bearing for the task.

Either ship the referenced task/template/checklist bundle files under references/ or document explicitly that they live in .aiox-core/ and are loaded on demand, so progressive disclosure is verifiable rather than dangling.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose and padded — a large embedded YAML block restates config Claude can derive from the referenced files, plus extensive persona/vocabulary/greeting scaffolding ('vocabulary: deployar, automatizar...', zodiac, emoji_frequency) that does not earn its tokens, fitting the 'noticeably verbose; several unnecessary explanations or padded sections' anchor better than the leaner 3.	2 / 5
Actionability	It provides concrete commands (pre-push, push, *release) and named quality gates (coderabbit, npm run lint/test/typecheck/build), but execution detail is largely deferred to external task files and templates that are referenced rather than shown, leaving some guidance incomplete — matching the 'some concrete guidance but incomplete' anchor.	3 / 5
Workflow Clarity	Multi-step workflows are clearly sequenced with explicit checkpoints — the typical push/release flows and the CodeRabbit gate ('must have 0 CRITICAL issues', block on CRITICAL, confirm before push) provide validation gates with minor gaps, fitting 'clear sequence with most checkpoints present' above the checkpoint-missing 3.	4 / 5
Progressive Disclosure	Despite many referenced dependency files, the body inlines a massive YAML configuration block (persona, commands list, coderabbit integration, workflow examples) that clearly belongs in separate bundled files, and the actual bundle directories (references/scripts/assets) are empty — so the structure is minimal and content that should be split is inlined, matching the 'minimal structure; content that clearly belongs in separate files is inlined' anchor.	2 / 5
	Total	11 / 20 Passed

Description

87%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.

The description is concrete, trigger-rich, and explicitly states both what it does and when to use it, with a distinctive exclusive-authority clause that sharply reduces conflict risk. Its only weakness is slightly limited synonym/extension coverage in the trigger terms.

Suggestions

Add common synonyms and concrete artifacts to the trigger terms, e.g. 'pull requests, releases, GitHub Actions, semantic versioning, .github/workflows' so natural phrasings map more reliably.

Optionally surface PR creation and release management as explicit capabilities in the description itself, since they are core to the agent but currently only implied.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — 'repository operations, version management, CI/CD, quality gates, and GitHub push operations' — with only minor gaps (e.g., PR/release specifics are implied rather than enumerated), fitting the 'several specific actions; minor gaps' anchor better than the fully comprehensive 5.	4 / 5
Completeness	It explicitly answers 'what' ('Activate Gage (devops) for GitHub Repository Manager & DevOps Specialist') and 'when' ('Use for repository operations, version management, CI/CD, quality gates, and GitHub push operations') with concrete trigger phrases, matching the anchor for clearly and explicitly answering both.	5 / 5
Trigger Term Quality	Includes natural user-facing terms like 'repository operations', 'CI/CD', 'quality gates', and 'push operations', but is missing common synonyms and concrete file extensions a user might say, so it sits just below the comprehensive-synonym coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	The 'ONLY agent authorized to push to remote repository' clause carves out a clear, narrow niche with a distinct trigger that is unlikely to collide with other skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	18 / 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
skill_md_line_count	SKILL.md is long (624 lines); consider splitting into references/ and linking	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: .claude/skills/AIOX/agents/devops/SKILL.md
Commit: 4ef6530

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.