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

73%

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

80%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 a tight, well-structured quick reference with an executable core pattern and concrete API names, weakened only by limited code coverage of the common cases and the absence of an explicit sequenced workflow with validation.

Suggestions

Add 2-3 short executable snippets covering the other common cases (e.g., an Ax.ax/AxGen signature, an Ax.agent, an Ax.flow) so actionability covers the main usage paths, not just client construction.

Provide a short ordered workflow with a validation checkpoint, e.g., 'Start from examples/ -> match the call shape -> verify against axir-api.json -> only then deviate', to lift workflow clarity above 3.

Dimension	Reasoning	Score
Conciseness	The body is lean bullets and one tight code snippet with no padding and no explanation of concepts Claude already knows (e.g., it does not explain what an LLM client is), matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	The Core Pattern provides a real, executable Java snippet and the API Surface lists concrete symbol names, but only one common case (creating an AI client) is shown while signatures, agents, flows, and optimizers are only named without usage, fitting 'mostly executable guidance with minor gaps' rather than a 5.	4 / 5
Workflow Clarity	There is no sequenced multi-step workflow; the Guardrails section offers soft checkpoints ('Start from package examples...', 'Treat AxIR as the source of truth') but no validate-then-fix feedback loop, matching the 'sequence present but checkpoints implicit/missing' anchor; this is a reference skill rather than a destructive/batch workflow so the 3-cap does not additionally bind.	3 / 5
Progressive Disclosure	No bundle directories exist, so this is a single self-contained SKILL.md under 50 lines with well-organized sections (When To Use, Package Facts, Core Pattern, Relevant API Surface, Guardrails); per the simple-skills note, that organization earns a 5 without external file references.	5 / 5
	Total	17 / 20 Passed

Description

66%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 distinct and trigger-explicit, but its 'what' is expressed as a list of resources rather than concrete actions, leaving it solid but not exemplary on specificity and trigger breadth.

Suggestions

Reframe the 'what' as concrete actions (e.g., 'Build signatures, agents, flows, and optimizers in Java using the generated Ax package') instead of listing resources like 'package docs, examples, and API reference'.

Add natural trigger synonyms a user might say, such as 'LLM', 'prompt programs', or 'DSPy-style optimization in Java', to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('writing Java code with `dev.axllm:ax`') and enumerates 'factory functions, package docs, examples, and API reference', but these are resources rather than concrete actions the skill performs, matching the anchor that names the domain with 1-2 concrete items but is not comprehensive.	3 / 5
Completeness	It has both an explicit 'when' ('Use when writing Java code with `dev.axllm:ax`') and a 'what' ('using the generated Ax package, factory functions, package docs, examples, and API reference'); the 'when' is specific but the 'what' phrasing is circular, so it sits at the 'both present, when could be more explicit' anchor rather than a 5.	4 / 5
Trigger Term Quality	Relevant natural keywords are present ('writing Java code', 'Ax package', 'dev.axllm:ax') but common variations or synonyms a user might say are missing, fitting the 'some relevant keywords but missing variations' anchor; not a 4 because coverage is thin for a niche library.	3 / 5
Distinctiveness Conflict Risk	The package coordinate `dev.axllm:ax` plus the 'Java' language qualifier carve a clear, distinct niche with minimal overlap risk, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	15 / 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-llm/SKILL.md
Commit: 781623e

Reviewed: 3 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.