ax-java-typesafe

Use when writing Java code with `dev.axllm:ax` for Typesafe Jev boolean/class signatures, value descriptions, configurable Noul conversion, native Noul/Choice/Score, structured criteria and hybrid generation.

Quality

76%

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-typesafe/SKILL.md

Quality

Content

63%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.

A well-structured, fact-dense reference for a generated Java package: the core pattern is executable and the decision guidance is clear. The main weaknesses are run-on multi-topic paragraphs that need tightening and references to bundle files that are not actually provided.

Suggestions

Break the Typesafe/Jev section into focused bullet groups or sub-sections (threshold config, naming variants, native client, probability validation) so each rule is scannable instead of packed into run-on paragraphs.

Add a short executable snippet for the native client (system_one/list_models) and the two-program hybrid pattern, since the referenced src/examples/java/generation/ files are not part of the bundle.

Move the 'Relevant API Surface' class list into the referenced API.md file (or include it in the bundle) and keep SKILL.md focused on when-to-use and the core pattern.

Dimension	Reasoning	Score
Conciseness	Every fact is package-specific with no padding or explanation of concepts Claude already knows, but the Typesafe/Jev section packs 6-8 unrelated facts into run-on prose paragraphs (e.g. one paragraph mixes trueThreshold policy, describe_values naming variants, C++ valueDescriptors, and other-provider behavior), which could be meaningfully tightened.	3 / 5
Actionability	The Core Pattern is concrete, executable Java ('var triage = Ax.ax("ticket:string -> urgent:boolean(...)")' followed by triage.forward) and parameter rules are exact ('finite value in [0,1], default 0.5'), but the native client, Score conversion, and hybrid generation paths get no code and defer to examples under src/examples/java/generation/ that are not present in the bundle.	4 / 5
Workflow Clarity	'When To Use' provides explicit decision branching (Jev for typed decisions, native questions for probabilities/rich criteria/scoring, separate generative program for prose or tools) and sections flow sensibly from facts to core pattern to guardrails with no destructive operations needing validation. Not 5 because the most complex path, the two-program hybrid workflow, is described only in prose with no step sequence.	4 / 5
Progressive Disclosure	Sections are clearly labeled, but the body references API.md, axir-api.json, axir-capabilities.json, and examples/ that do not exist in the provided bundle, while the large 'Relevant API Surface' list and dense constraint prose — content that belongs in those referenced files — is inlined in SKILL.md.	3 / 5
	Total	14 / 20 Passed

Description

78%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.

A strong, specific description with an explicit 'Use when' trigger and highly distinctive package-scoped terms. Its only weakness is merging what and when into one sentence and listing capabilities as opaque feature nouns rather than plain actions.

Dimension	Reasoning	Score
Specificity	The description lists several concrete capability areas ('Typesafe Jev boolean/class signatures, value descriptions, configurable Noul conversion, native Noul/Choice/Score, structured criteria and hybrid generation'), going beyond the 1-2 items of anchor 3, but falls short of anchor 5 because these are feature nouns rather than concrete actions and some terms are opaque without the package context.	4 / 5
Completeness	Both what and when are present: the explicit trigger 'Use when writing Java code with dev.axllm:ax for...' plus the feature list as the what. Not 5 because both are merged into a single sentence with one trigger condition rather than distinct what/when statements with multiple concrete trigger phrases.	4 / 5
Trigger Term Quality	Good keyword coverage including 'writing Java code', 'Typesafe Jev', 'boolean/class signatures', 'Noul conversion', 'Choice/Score', and 'hybrid generation' — terms a user of this package would naturally say — though natural synonyms like 'typed decisions', 'probabilities', or 'Ax package' are missing.	4 / 5
Distinctiveness Conflict Risk	The combination of 'dev.axllm:ax' and 'Typesafe Jev' is an unmistakably niche package-specific trigger with minimal conflict risk against any generic Java skill.	5 / 5
	Total	17 / 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-typesafe/SKILL.md
Commit: 3f630a0

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.