CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

80%

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-agent-rlm/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 lean, well-organized reference-style skill body: token-efficient, concrete core example, and clear guardrails. The main gaps are the missing executable example for the runtime-wiring use cases it leads with and references to files that are not bundled with the skill.

DimensionReasoningScore

Conciseness

The ~40-line body is dense throughout: Package Facts are flat factual bullets ('Real network support: yes'), the Core Pattern is a minimal code block, and guardrails are one-line directives. Nothing explains concepts Claude already knows and no dated/versioned content appears in the body, so every token earns its place.

5 / 5

Actionability

The Core Pattern gives concrete Java ('Ax.agent("question:string -> answer:string", java.util.Map.of())', 'helper.forward(llm, ...)') and guardrails give specific directives, but `llm` is undefined in the snippet and the headline use cases (AxCodeRuntime/ProcessCodeRuntime wiring) receive only a name list with no executable example — minor gaps that keep it below copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

There is no multi-step or destructive/batch operation, so the validation cap does not apply, and the guidance takes the form of clear decision rules ('Start from package examples for exact native syntax', 'Use `no-key` examples for deterministic local checks'). It falls short of 5 because the single action is not fully unambiguous — no explicit sequence for consulting API.md/examples before writing code is laid out.

4 / 5

Progressive Disclosure

A short, well-sectioned overview (When To Use, Package Facts, Core Pattern, API Surface, Guardrails) with one-level-deep, clearly signaled references ('API.md', 'axir-api.json', 'examples/'). It does not reach 5 because the referenced files are not part of the skill bundle, so navigation from the skill itself is uncertain and the API surface stays inline as a teaser.

4 / 5

Total

17

/

20

Passed

Description

70%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 highly distinctive, keyword-rich trigger description with concrete technical targets, but it is purely a 'when' clause — the skill's actual function is left implicit. Adding a brief explicit 'what' statement would round it out.

Suggestions

Lead with an explicit capability statement (e.g., 'Provides API usage patterns and guardrails for writing Java code with the generated dev.axllm:ax package') before the 'Use when...' clause, so 'what' is stated rather than implied.

Mention the primary API entry points (AxAgent, Ax.agent) in the description so users referencing the core agent API naturally trigger the skill.

Add one or two natural synonyms or variations (e.g., 'Java SDK', 'Ax runtime') to broaden trigger coverage without adding vagueness.

DimensionReasoningScore

Specificity

Names the domain ('writing Java code with `dev.axllm:ax`') and enumerates several concrete technical targets ('RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles'). It is more specific than the 3 anchor's 1-2 concrete actions, but the items are topics rather than actions and the core AxAgent API is not mentioned, so it falls short of anchor 5's comprehensive coverage.

4 / 5

Completeness

The description is a single explicit 'Use when...' trigger clause, so 'when' is fully present, but what the skill actually does (e.g., 'provides API patterns and guardrails for the generated package') is never stated and only implied by the enumerated topics. Scoring only what is explicitly stated places this at one component explicit, the other implied — anchor 3 rather than 4.

3 / 5

Trigger Term Quality

Terms like 'Java code', 'dev.axllm:ax', 'AxCodeRuntime sessions', 'runtime envelopes', and 'runtime profiles' are exactly what a user of this package would say, giving good keyword coverage. A few natural terms are missing (AxAgent/Ax.agent, build-tool or Maven/Gradle phrasing), keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

Triggers are anchored to package-specific identifiers ('dev.axllm:ax', 'AxCodeRuntime') that no other skill would match, giving a clear niche with minimal conflict risk.

5 / 5

Total

16

/

20

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.

Validation — 15 / 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

Path

packages/java/skills/ax-java-agent-rlm/SKILL.md

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.