CtrlK
BlogDocsLog inGet started
Tessl Logo

ax-java-agent-observability

Use when writing Java code with `dev.axllm:ax` for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.

65

Quality

78%

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-observability/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

A well-organized, token-efficient reference skill that points cleanly to deeper package materials. Its gaps are incomplete inline code (undefined `llm`, no setup) and the absence of an explicit sequenced workflow with validation for debugging/replay tasks.

Suggestions

Make the Core Pattern snippet self-contained by showing how `llm` is constructed (e.g., an `AxAI` client) or label it as a fragment that presupposes the runnable examples.

Add a short sequenced workflow with a validation checkpoint for the debugging/replay use case (e.g., capture trace -> inspect envelope -> replay against no-key transport -> verify), so workflow clarity reaches the validated-flow anchor.

Confirm the referenced files (API.md, axir-api.json, axir-capabilities.json, examples/) are bundled or note explicitly they ship with the `dev.axllm:ax` package, since the skill bundle's references/ directory is empty.

DimensionReasoningScore

Conciseness

The body is dense and fluff-free: package facts, two compact code patterns, a focused observer section, and a guardrails list, with no explaining of concepts Claude already knows, fitting the lean-and-efficient anchor.

3 / 3

Actionability

It offers real code snippets and many concrete API names and file paths, but the core pattern relies on an undefined `llm` variable and omits setup/imports, so examples are illustrative rather than copy-paste ready — the "some concrete guidance but incomplete" anchor.

2 / 3

Workflow Clarity

"When To Use" lists scenarios and Guardrails give constraints, but there is no sequenced multi-step workflow with validation checkpoints for the tracing/debugging tasks, placing it at the sequence-present-but-checkpoints-implicit anchor rather than a fully validated flow.

2 / 3

Progressive Disclosure

The overview stays in SKILL.md while detailed materials are signaled one level deep ("Package API docs: `API.md` and `axir-api.json`", "Runnable provider example: `src/examples/java/...`"), with clearly labeled sections making navigation easy; the referenced paths are package artifacts rather than missing bundle files.

3 / 3

Total

10

/

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 tight, capability-rich description with an explicit Use-when trigger and a distinct package niche. Its main weakness is a trigger phrase anchored on a technical package name rather than natural user language, which limits trigger-term quality.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging" — matching the anchor for several specific actions rather than vague domain naming.

3 / 3

Completeness

Explicitly answers both what (the enumerated capabilities) and when via the "Use when writing Java code with `dev.axllm:ax` for ..." clause, matching the anchor that requires an explicit trigger.

3 / 3

Trigger Term Quality

The lead trigger "writing Java code with `dev.axllm:ax`" is package-name jargon rather than phrasing a user would naturally say; capability nouns like tracing and debugging are relevant but common natural variations are thin, so it sits at the "some relevant keywords" anchor rather than full coverage.

2 / 3

Distinctiveness Conflict Risk

Scoped to a specific generated Java package with a niche observability purpose, making it unlikely to fire for unrelated skills.

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.