ax-java-agent-rlm

Use when writing Java code with `dev.axllm:ax` for RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles.

Quality

78%

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-agent-rlm/SKILL.md

Quality

Content

72%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 concise, well-organized reference skill with an executable core pattern and clear guardrails. It is held back by incomplete actionability (depends on unbundled package docs) and the absence of an explicit validation-bearing workflow.

Suggestions

Make the Core Pattern snippet self-contained by showing how `llm` is obtained or noting the required import, so the example is copy-paste ready without external files.

Add a short explicit workflow for the regenerate-packages feedback loop (e.g. edit AxIR -> recompile -> regenerate -> re-check package docs) with a validation checkpoint.

Since API.md, axir-api.json, axir-capabilities.json, and examples/ are referenced but not bundled, either include the relevant excerpts inline or clarify that these live in the generated package so navigation expectations are unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned (When To Use, Package Facts, Core Pattern, Relevant API Surface, Guardrails) with no explanation of concepts Claude already knows; every section earns its place.	3 / 3
Actionability	A concrete executable Java snippet and named API surface are provided, but the example references an undefined `llm` and the guardrails defer exact syntax to unbundled `examples/` and `API.md`, leaving key details incomplete rather than copy-paste ready.	2 / 3
Workflow Clarity	Scenarios and guardrails are listed, but there is no explicit sequenced workflow with validation checkpoints; the regenerate-packages feedback loop is mentioned only as a guardrail, not as a validate->fix->retry sequence, leaving checkpoints implicit.	2 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets directories are absent), and the SKILL.md is a concise, well-organized overview under 50 lines with no nested references, satisfying the simple-skill allowance for a top score.	3 / 3
	Total	10 / 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 strong, third-person description with an explicit 'Use when' trigger and concrete named capability surfaces. Its main weakness is trigger-term naturalness: much of the phrasing is internal API jargon rather than terms a user would naturally say.

Suggestions

Add one or two user-natural trigger phrasings (e.g. 'Use when the user asks to build or wire an Ax Java agent or runtime') alongside the technical surface names to improve trigger term quality.

Consider including a common-variation alias such as 'Ax Java' or 'Ax runtime' so the description matches how users actually refer to the package.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete, named capability surfaces ('RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles') rather than vague language, matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	It explicitly states what it is for (the named runtime/API surfaces) and provides an explicit 'Use when writing Java code...' trigger clause, clearly answering both what and when.	3 / 3
Trigger Term Quality	The natural trigger 'writing Java code with `dev.axllm:ax`' is present, but the remaining terms (RLM executor loops, AxCodeRuntime, runtime envelopes) are technical jargon a user would only utter when already deep in the domain, missing common variations, so it sits at 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The specific package identifier `dev.axllm:ax` and the named Ax runtimes carve out a clear niche that is unlikely to trigger for the wrong skill.	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-agent-rlm/SKILL.md
Commit: 16c2119

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.