ax-java-llm

Use when writing Java code with `dev.axllm:ax` for using the generated Ax package, factory functions, package docs, examples, and API reference.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/java/skills/ax-java-llm/SKILL.md

Quality

Content

72%

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 clean, concise quick reference that is well organized and points to one-level-deep package artifacts. It is held back by partial actionability — a symbol catalog and pointer-to-examples rather than executable usage — and an implied rather than explicit workflow.

Suggestions

Add one small executable example per major surface (e.g. a signature via Ax.s, an agent via Ax.agent, a flow via Ax.flow) instead of only listing symbol names, so guidance is copy-paste ready.

Make the workflow explicit with a short sequenced recipe (choose entrypoint -> apply core pattern -> verify against examples -> consult API.md) including a checkpoint confirming generated syntax matches package docs.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, covering triggers, package facts, a core pattern, API surface, and guardrails without explaining concepts Claude already knows; every section earns its place.	3 / 3
Actionability	The 'Core Pattern' is a copy-paste-ready executable snippet, but the bulk of 'Relevant API Surface' is a catalog of symbol names with no executable usage, and the skill defers actual syntax to package examples rather than providing it inline, leaving key details incomplete.	2 / 3
Workflow Clarity	Sections like 'When To Use', 'Core Pattern', and 'Guardrails' give structure, but there is no explicit sequenced workflow with validation checkpoints; for a multi-surface reference (signatures, providers, agents, flows, optimizers) the ordering and verification steps are only implied.	2 / 3
Progressive Disclosure	No bundle directories exist, and the skill is under 50 lines organized into well-labeled sections (When To Use, Package Facts, Core Pattern, Relevant API Surface, Guardrails) with one-level-deep references clearly signaled in Package Facts (API.md, axir-api.json, examples/), matching the simple-skill allowance.	3 / 3
	Total	10 / 12 Passed

Description

85%

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 and distinctive, anchored to a concrete package and language with an explicit 'Use when' trigger. Its main weakness is trigger-term naturalness, leaning on technical jargon over the phrasings a user would actually say.

Suggestions

Add natural-language trigger phrasings a user might say (e.g. 'Ax LLM Java SDK', 'Java Ax agent', 'Ax package for Java') alongside the technical terms to improve trigger-term coverage.

Lead with the primary action ('Write Java code using the Ax LLM package') before listing the supporting resources so the core capability reads as an action rather than a catalog.

Dimension	Reasoning	Score
Specificity	It explicitly enumerates multiple concrete capabilities ('writing Java code', 'factory functions, package docs, examples, and API reference') tied to a named package, matching the anchor that lists several specific concrete actions.	3 / 3
Completeness	It states what ('writing Java code with dev.axllm:ax for using the generated Ax package, factory functions, package docs, examples, and API reference') and gives an explicit 'Use when' trigger, clearly answering both what and when.	3 / 3
Trigger Term Quality	'writing Java code' is a natural term a user would say, but the rest ('generated Ax package, factory functions, package docs, API reference') is technical jargon rather than common variations users voice, so it has some relevant keywords but misses common phrasings.	2 / 3
Distinctiveness Conflict Risk	The fully qualified package name 'dev.axllm:ax' combined with the Java language qualifier creates a clear niche with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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-llm/SKILL.md
Commit: fe8baf8

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.