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

75%

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-agent/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, well-organized API-overview skill that stays lean and signals references clearly. It is held back by delegated-but-absent detail files, an undefined variable in the core example, and the lack of a sequenced workflow with validation.

Suggestions

Include the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) in the skill, or remove the references and inline the essential actionable detail.

Complete the Core Pattern so it is copy-paste ready — define or show how `llm` is constructed, and add one runnable example per major capability (tools, MCP, citations).

Add a short sequenced workflow with validation checkpoints for the riskier tasks (e.g. harvesting run-end failures, restoring runtime state).

Dimension	Reasoning	Score
Conciseness	The body is lean — short bullets, no padding, no explanations of what Java/MCP/libraries are — and every section earns its tokens, matching the 'lean and efficient; assumes Claude's competence' anchor.	3 / 3
Actionability	A concrete Core Pattern snippet is provided, but it relies on an undefined `llm` and the bulk of actionable detail (tools, MCP, citations, playbook) is deferred to API.md/examples/ rather than given as copy-paste-ready code, fitting 'some concrete guidance but incomplete; missing key details'.	2 / 3
Workflow Clarity	It lists use-case scenarios and guardrail ordering hints but offers no sequenced multi-step workflow with validation checkpoints for the tasks it covers, matching 'sequence present but checkpoints missing or implicit'.	2 / 3
Progressive Disclosure	Sections are well organized and references are clearly signaled (API.md, axir-api.json, axir-capabilities.json, examples/), but those referenced files are not present in the skill bundle, so the disclosure structure is only partially realized.	2 / 3
	Total	9 / 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.

A specific, well-triggered description scoped to a single package, with explicit what-and-when structure. Its main weakness is jargon-heavy phrasing in the capability list that reduces natural trigger-term quality.

Suggestions

Soften internal jargon in the capability list (e.g. 'persistent playbook learning', 'direct-respond executor skipping') into terms a user would actually say, or group niche features under a simpler umbrella term.

Add a couple of natural-language variations of the trigger (e.g. 'Java agent', 'Ax agent', 'RLM agent') to broaden how users phrase the need.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete capabilities — 'agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping' — matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	It answers both what (the enumerated capabilities) and when ('Use when writing Java code with `dev.axllm:ax` for...') with an explicit trigger clause, matching the highest anchor.	3 / 3
Trigger Term Quality	It opens with a natural trigger ('Use when writing Java code with `dev.axllm:ax`') and some real user terms (agents, tools, MCP, citations), but much of the list is internal jargon ('persistent playbook learning', 'direct-respond executor skipping', 'stage instructions') a user would rarely say, so it sits at 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The trigger is tightly bound to a single named package (`dev.axllm:ax`) and Java, carving a clear niche 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-agent/SKILL.md
Commit: 16c2119

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.