CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

60

Quality

76%

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 ./website/static/java/.well-known/agent-skills/ax-java-agent-rlm/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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, fact-driven body with a concrete core pattern and genuinely useful guardrails, but no explicit multi-step workflow or validation checkpoints, and every referenced detail file (API.md, axir-api.json, axir-capabilities.json, examples/) is absent from the bundle. It works as a pointer card, but the pointers currently resolve to nothing.

Suggestions

Add a short ordered workflow with an explicit validation checkpoint, e.g.: 1) consult examples/ for exact native syntax, 2) choose transport (no-key for deterministic local checks; provider-api only when the user has explicit credentials), 3) wire the AxCodeRuntime/session, 4) verify with a no-key run before returning code.

Ship the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) or remove the references — as delivered, every 'see X' path in the body is dangling.

Make the Core Pattern self-contained by showing how `llm` is constructed (one line), so the snippet is copy-paste runnable.

DimensionReasoningScore

Conciseness

The body is lean and fact-dense ('Package Facts', the Core Pattern, targeted guardrails) and explains nothing Claude already knows. Minor duplication keeps it from anchor 5: the intro restates the frontmatter purpose, and 'javascript-quickjs', 'python-pyodide', and 'ProcessCodeRuntime' each appear in both 'Package Facts' and 'Relevant API Surface'.

4 / 5

Actionability

Concrete, near-executable Java is provided ('AxAgent helper = Ax.agent("question:string -> answer:string", java.util.Map.of()); ... helper.forward(llm, ...)') alongside specific directives ('Use provider-api examples only when the user explicitly has provider credentials available'). It is not anchor 5 because the snippet's `llm` variable is never defined and no imports/setup are shown, so it is not copy-paste ready.

4 / 5

Workflow Clarity

A workflow is only implicit: 'Start from package examples for exact native syntax before inventing a new call shape' plus the transport-choice rules suggest a sequence (consult examples, choose transport by credentials, wire the runtime, verify locally), but no ordered steps are listed and no validation checkpoint is explicit — anchor 3. The simple-skill exception does not apply because the skill spans multiple scenarios (runtime wiring, profile choice, transport choice) rather than one unambiguous action.

3 / 5

Progressive Disclosure

Sections are well organized and detail locations are clearly signaled ('Package API docs: `API.md` and `axir-api.json`', 'Runnable examples: `examples/`'), but the bundle ships no references/, scripts/, or assets/ directories and none of the referenced files exist, so every disclosure path dangles. Per the guideline to score against the actual bundle structure, this lands at anchor 3 rather than 4.

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 third-person description with an explicit 'Use when' trigger, a concrete package identifier, and a specific enumeration of capability areas. The main gaps are the fused what/when structure and a few missing natural synonyms for the API names.

DimensionReasoningScore

Specificity

'writing Java code with `dev.axllm:ax` for RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles' names the domain and several concrete capability areas plus the exact package coordinate. It is not a 5 because it rests on a single verb ('writing ... for') rather than multiple distinct concrete actions, and it omits coverage the body documents (e.g., streamingForward, no-key transport checks).

4 / 5

Completeness

The 'when' is explicit ('Use when writing Java code with `dev.axllm:ax`') and the 'what' is stated through the enumerated feature list, putting this above anchor 3 where 'when' is only weakly implied. It is below anchor 5 because what and when are fused into a single clause with no standalone capability statement of the form '... . Use when ...'.

4 / 5

Trigger Term Quality

'Java code', 'dev.axllm:ax', 'RLM executor loops', 'AxCodeRuntime sessions', 'runtime envelopes', 'process runtimes', and 'runtime profiles' are exactly the terms a user of this package would say. A few natural variations are missing (e.g., 'AxAgent', plain 'Ax runtime'), so it fits anchor 4 rather than 5, while clearly exceeding anchor 3's bare-keyword level.

4 / 5

Distinctiveness Conflict Risk

'dev.axllm:ax', 'AxCodeRuntime', and 'RLM' name a proprietary package and its APIs, a clear niche no other skill would claim, so conflict risk is minimal. Anchor 4's 'minor overlap risk with closely related skills' does not apply because the package coordinate alone disambiguates it from generic Java skills.

5 / 5

Total

17

/

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
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.