ax-java-agent

Use when writing Java code with `dev.axllm:ax` for agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

76%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 content is concise and well-structured with a usable core code pattern, but it lacks explicit validation checkpoints in its workflow and leans on listing API symbols rather than giving copy-paste-ready usage for the common cases.

Suggestions

Add an explicit validation step (e.g., 'run an example to confirm generated API calls compile/execute before extending') to the workflow for destructive or regeneration operations.

Expand the Relevant API Surface with one short copy-paste snippet per major area (agents, MCP, runtime profiles) instead of only listing symbol names.

Verify and link the referenced bundle files (API.md, axir-capabilities.json, examples/) so the one-level-deep references resolve to real artifacts.

Dimension	Reasoning	Score
Conciseness	The body is lean and bullet-driven with no over-explanation of concepts Claude already knows; every line (Package Facts, Core Pattern, API Surface, Guardrails) earns its place.	5 / 5
Actionability	Provides one executable Java Core Pattern snippet and concrete API symbol names, but most of the API surface is enumerated as names rather than copy-paste-ready usage for common cases, leaving minor gaps.	4 / 5
Workflow Clarity	When-To-Use, Core Pattern, and Guardrails give a recognizable sequence, but there are no explicit validation/checkpoint steps for risky operations like regenerating packages or harvesting run-end failures, which caps it at 3.	3 / 5
Progressive Disclosure	Well-organized sections under 50 lines with signaled references to API.md, axir-capabilities.json, and examples/, but the referenced bundle directories are not present to verify, leaving minor organization gaps.	4 / 5
	Total	16 / 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 a strong, trigger-led sentence that names a specific package and enumerates many concrete capabilities while explicitly answering when to use it. It is distinct and unlikely to fire for unrelated skills.

Dimension	Reasoning	Score
Specificity	Lists many concrete capability areas (agents, child delegation, tools, MCP, citations, playbook learning, stage instructions, runtime state, typed responses, executor skipping), but presents them as capability nouns rather than concrete verbs/actions, leaving minor gaps.	4 / 5
Completeness	Explicitly answers both what (Java code with the ax package across enumerated capabilities) and when ('Use when writing Java code with dev.axllm:ax for...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	'Use when writing Java code with dev.axllm:ax' is a natural trigger phrase and the capability terms (MCP, citations, playbook, child delegation) are terms a user of this package would say, though a few common natural synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	The niche is sharply defined by the generated Java package 'dev.axllm:ax' and its RLM-agent feature set, giving clear distinct triggers and minimal conflict risk 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-agent/SKILL.md
Commit: 3951b05

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.