ax-java-gepa

Use when writing Java code with `dev.axllm:ax` for GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts.

Quality

71%

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-gepa/SKILL.md

Quality

Content

57%

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 concrete core pattern and useful guardrails, but it suffers from broken external references (cited files are absent) and incomplete executable detail, plus no validation checkpoint for the optimization workflow.

Suggestions

Ship the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) or remove the citations, since broken pointers make progressive disclosure unusable.

Expand the Core Pattern into a self-contained runnable example showing how request and evaluator are constructed, not just engine.optimize(request, evaluator).

Add a verification step (e.g. inspect the returned optimizer state / Pareto front or run a no-key scripted example) so the workflow has an explicit validation checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, explains no basic Java/library concepts, and every section (Package Facts, Core Pattern, Guardrails) earns its tokens.	3 / 3
Actionability	The Core Pattern code is concrete, but 'engine.optimize(request, evaluator)' leaves request/evaluator construction undefined and the API Surface is a bare name list rather than executable signatures, so it is not copy-paste ready.	2 / 3
Workflow Clarity	Guardrails give a rough 'start from examples' sequence, but there is no explicit validation/checkpoint loop for the optimization run, so the sequence is present yet checkpoints are implicit.	2 / 3
Progressive Disclosure	Package Facts references 'API.md', 'axir-api.json', 'axir-capabilities.json', and 'examples/', but no references/ or assets/ bundle directories exist, so these pointers resolve to nothing and the overview-to-detail navigation is broken.	1 / 3
	Total	8 / 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, complete, and distinct, with an explicit 'Use when' trigger and third-person voice. Its main weakness is trigger-term quality: the named terms are internal package jargon rather than phrases a user would naturally say.

Suggestions

Add user-facing synonyms alongside the package jargon (e.g. 'prompt optimization', 'few-shot generation', 'Pareto-best candidates') so the description fires when a user describes the task in plain terms.

Clarify that GEPA is an optimizer program, since the acronym alone is not a term users would naturally say.

Dimension	Reasoning	Score
Specificity	It enumerates multiple concrete capabilities—'GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts'—rather than vague abstractions.	3 / 3
Completeness	It answers both 'what' (the listed optimization capabilities) and 'when' with an explicit 'Use when writing Java code with...' trigger clause.	3 / 3
Trigger Term Quality	'writing Java code' is a natural phrase, but the skill name 'GEPA' and 'dev.axllm:ax' are package-specific jargon unlikely to be spoken verbatim by a user, and common variations are missing.	2 / 3
Distinctiveness Conflict Risk	The package identifier 'dev.axllm:ax' plus the GEPA/optimizer niche carve a clear, narrow trigger unlikely to fire for unrelated Java 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-gepa/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.