ax-java-ai

Use when writing Java code with `dev.axllm:ax` for named deployment profiles, generic provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, and balancers.

1.00x

Quality

85%

Does it follow best practices?

Impact

100%

1.00x

Average score across 1 eval scenario

Securityby

Passed

No findings from the security scan

Quality

Content

82%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 a lean, well-structured reference for the AxAI Java package: dense specific rules, concrete API symbols, example-path guidance, and clear guardrails. Its main weakness is limited inline executable code beyond the single Core Pattern snippet.

Suggestions

Add 1-2 short copy-paste-ready code snippets for the most common scenarios (e.g. a named factory call and a router/balancer setup) so guidance is executable without opening examples/.

Confirm the referenced bundle files (`API.md`, `axir-api.json`, `axir-capabilities.json`, `examples/`) actually ship with the skill, or remove the references to avoid dead pointers.

Consider moving the long "Relevant API Surface" symbol list into a separate reference file to keep SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and information-rich with no padding or explanation of basic concepts Claude already knows; every bullet states a specific API rule or fact, assuming Claude's competence.	5 / 5
Actionability	Provides concrete option names, specific API symbols in "Relevant API Surface", and example paths (e.g. `examples/adaptive_balancer_no_key`), but only one small inline code block, so most scenarios lack copy-paste-ready code.	4 / 5
Workflow Clarity	Sequencing guidance ("Start with ... then use the cataloged ... example") and the Guardrails section supply clear decision checkpoints; no destructive/batch operation is present, so the missing formal validation loop does not cap the score.	4 / 5
Progressive Disclosure	Well-organized into clear labeled sections with signaled references to `API.md`, `axir-api.json`, `axir-capabilities.json`, and `examples/`; minor gaps because the referenced files are not present in the bundle and the inline "Relevant API Surface" list could live in a separate file.	4 / 5
	Total	17 / 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 well-crafted: it opens with an explicit "Use when" trigger, names the exact package, and enumerates concrete capability areas with natural provider keywords. It is comprehensive, distinct, and free of fluff or voice issues.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability areas ("named deployment profiles, generic provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, and balancers"), but these are feature nouns rather than verb-driven actions, leaving a minor gap versus the fully action-anchored top level.	4 / 5
Completeness	Explicitly answers both what (writing Java code with `dev.axllm:ax` for a concrete list of capabilities) and when ("Use when writing Java code with `dev.axllm:ax`...") with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Natural provider and task terms users would say ("Java code", "OpenAI-compatible", "Gemini", "Anthropic", "model selection", "routers", "balancers") are present with good coverage, though a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Tightly scoped to the specific `dev.axllm:ax` Java package with a distinctive provider/feature niche, giving minimal overlap with other skills.	5 / 5
	Total	18 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: ax-llm/ax
Path: packages/java/skills/ax-java-ai/SKILL.md
Commit: dec4f9e

Reviewed: 5 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.