CtrlK
BlogDocsLog inGet started
Tessl Logo

ax-java-refine

Use when writing Java code with `dev.axllm:ax` for reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns.

63

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/java/skills/ax-java-refine/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The body is concise and well-organized with clearly signaled references, but it falls short on actionability, workflow clarity, and progressive disclosure: the core code example is not self-contained, no validation checkpoint sequences the optimization workflow, and every referenced bundle file is missing.

Suggestions

Make the Core Pattern example self-contained: add imports, show how reflectionClient/request/evaluator are constructed, or copy a complete runnable snippet from examples/ so it is copy-paste ready.

Add a short sequenced workflow with a verification checkpoint for the refine/optimize loop (e.g., run evaluator, inspect score, re-optimize until threshold) rather than only listing when-to-use scenarios.

Provide the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) so the signaled one-level references actually resolve, or remove references to files that are not bundled.

DimensionReasoningScore

Conciseness

The body is a lean set of bullet-point facts, a short code pattern, an API surface list, and guardrails; it assumes Claude's competence and avoids re-explaining known concepts, with no version numbers or dates in the body to pad it — matching the 'lean and efficient' anchor.

3 / 3

Actionability

The Core Pattern is real Java syntax but uses undefined placeholders ('reflectionClient', 'request', 'evaluator') with no imports or setup, and the guardrail itself concedes to 'Start from package examples for exact native syntax', placing it at 'concrete but incomplete' rather than copy-paste ready.

2 / 3

Workflow Clarity

Sections provide a loose structure but there is no sequenced multi-step workflow, and the iterative optimization process has no explicit validation or verification checkpoint, matching the anchor with a present but checkpoint-missing sequence.

2 / 3

Progressive Disclosure

References are clearly signaled one level deep ('API.md', 'examples/', 'axir-api.json') and sections are well organized, but none of the referenced bundle files or directories actually exist, so the disclosed structure does not resolve in practice — better than monolithic but not a fully working one-level reference.

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 strong, specific description that clearly states both what it does and when to use it, with an explicit 'Use when' trigger and a well-scoped niche. Its only weakness is trigger-term naturalness, as parts of the capability list read as technical jargon rather than words a user would naturally say.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities — 'reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns' — matching the anchor that rewards several specific actions rather than vague language.

3 / 3

Completeness

The explicit 'Use when writing Java code with `dev.axllm:ax` for ...' clause answers both what (the four listed capabilities) and when, with an explicit trigger, matching the top anchor.

3 / 3

Trigger Term Quality

'Use when writing Java code with `dev.axllm:ax`' supplies some natural keywords, but phrases like 'reward-scored generation' and 'optimizer-backed refinement patterns' are technical jargon users would rarely say verbatim, and common variations are missing — so it sits at the 'some relevant keywords' anchor rather than full coverage.

2 / 3

Distinctiveness Conflict Risk

Scoping to a specific generated package ('Java code with `dev.axllm:ax`') creates a clear niche with distinct triggers unlikely to fire for unrelated skills, matching the top distinctiveness anchor.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
ax-llm/ax
Reviewed

Table of Contents

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.