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

67%

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

50%Weight 40%Scale 1-3

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

A well-organized, fluff-free reference body for a generated Java package, but it over-reliance on an inline symbol dump, a single code example, and absent validation/workflow steps keep most dimensions at the midpoint. Moving the API surface into the referenced API.md and adding a short verified example flow would lift the lower dimensions.

Suggestions

Move the 'Relevant API Surface' symbol enumeration into API.md (already referenced) and replace it with a short pointer plus 2-3 copy-paste examples covering Ax.f, Ax.agent, and Ax.flow.

Add a brief ordered workflow with a verification step, e.g. start from an example -> adapt the call -> run a no-key scripted example to confirm the shape compiles, so workflow_clarity reaches the explicit-checkpoint anchor.

Expand the single Core Pattern snippet into a small, executable no-key example so the actionability dimension hits the copy-paste-ready anchor.

Dimension	Reasoning	Score
Conciseness	The body avoids concept-explanation fluff and is mostly lean, but the 'Relevant API Surface' section is a ~20-symbol inline dump that duplicates what the referenced API.md should hold, fitting 'mostly efficient but could be tightened' rather than the lean score-3 anchor.	2 / 3
Actionability	Only one executable snippet (the Ax.ai core pattern) is provided while the rest of the surface is named but not demonstrated, matching 'some concrete guidance but incomplete' rather than the copy-paste-ready score-3 anchor.	2 / 3
Workflow Clarity	The Guardrails give loose ordering ('Start from package examples... before inventing') but there is no sequenced multi-step workflow or validation checkpoint, fitting 'steps listed but checkpoints missing' rather than the explicit-feedback-loop score-3 anchor.	2 / 3
Progressive Disclosure	Sections are clearly organized and package-artifact references (API.md, examples/) are well signaled at one level, but the large inline API surface is content that should be split out, matching the score-2 'content that should be separate is inline' anchor.	2 / 3
	Total	8 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 well-scoped, trigger-explicit description for a specific generated package, with concrete capabilities and a clear 'Use when' clause. Its main weakness is thin natural-language trigger coverage beyond the generic 'writing Java code'.

Dimension	Reasoning	Score
Specificity	The description names concrete capabilities ("factory functions, package docs, examples, and API reference") tied to a specific package, matching the 'lists multiple specific concrete actions' anchor rather than the partial score-2 anchor.	3 / 3
Completeness	It explicitly answers both what (the generated Ax package and its capabilities) and when ("Use when writing Java code..."), satisfying the explicit-trigger requirement that would otherwise cap completeness at 2.	3 / 3
Trigger Term Quality	"Use when writing Java code" is a genuine natural trigger, but beyond 'Java code' the terms ("dev.axllm:ax", "factory functions") are technical and lack common user phrasings, fitting 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The specific package coordinate `dev.axllm:ax` plus Java scoping carves a clear niche unlikely to trigger unrelated skills, though the broad 'writing Java code' phrase keeps it from being perfectly distinct from generic Java helpers.	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: 9 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.