ax-java-gen

Use when writing Java code with `dev.axllm:ax` for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

68%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.

A well-structured, token-efficient reference for the generated Ax Java package with a concrete core pattern and clear API surface. Its main gaps are the lack of executable examples beyond the core pattern and the absence of explicit validation checkpoints in any workflow.

Suggestions

Add small executable code snippets for the other advertised capabilities (tools via Ax.fn, multi-sampling with a result picker, an MCP client) so actionability reaches copy-paste coverage.

Insert an explicit validate-then-retry feedback loop where relevant — e.g., for structuredOutputMode JSON-object correction or for verifying a forward call against package examples before committing to a call shape.

Move the dense Provider Forward Options / Multi-Sampling semantics into API.md (or a referenced file) and keep SKILL.md as a tighter overview with well-signaled links, improving both conciseness and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept-explanation padding and assumes Java competence, but the dense 'Provider Forward Options' and 'Multi-Sampling' prose paragraphs carry semantics that could be trimmed or deferred.	4 / 5
Actionability	Provides a copy-paste 'Core Pattern' code block and concrete API names (Ax.ax, Ax.fn, AxMCPClient, setSampleCount), but only one code example leaves tools, multi-sampling, and MCP without executable samples.	4 / 5
Workflow Clarity	The Core Pattern implies a loose forward-call sequence and Guardrails give process hints ('Start from package examples'), but there are no explicit validation checkpoints or feedback loops; not a destructive/batch skill so the cap-3 is not forced, yet the sequence is only implicit.	3 / 5
Progressive Disclosure	Well-organized into clear sections with one-level-deep references signaled in Package Facts ('API.md and axir-api.json', 'examples/'), but no bundle files are actually present and some inlined option detail could live in API.md.	4 / 5
	Total	15 / 20 Passed

Description

92%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 strong, specific description that pairs an explicit 'Use when' trigger with a comprehensive list of concrete AxGen capabilities, making it highly distinguishable. It leans slightly technical in its capability terms, which keeps trigger-term naturalness just short of ideal.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing' — giving comprehensive coverage of the AxGen API surface rather than vague abstractions.	5 / 5
Completeness	Explicitly answers both: the 'what' (the enumerated AxGen capabilities) and the 'when' via the concrete 'Use when writing Java code with dev.axllm:ax for AxGen programs' trigger phrase.	5 / 5
Trigger Term Quality	The natural trigger 'writing Java code with dev.axllm:ax for AxGen programs' is something a user would say, but most listed terms (indexed multi-sampling, result pickers) are technical capability names rather than natural synonyms or file extensions.	4 / 5
Distinctiveness Conflict Risk	Scoped tightly to 'Java code with dev.axllm:ax for AxGen programs', a clear niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	19 / 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-gen/SKILL.md
Commit: 781623e

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.