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.

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 ./packages/java/skills/ax-java-agent-observability/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 concise, API-focused skill body with executable code snippets and clearly signaled external materials. Its main weaknesses are the absence of an explicit step-by-step workflow with validation checkpoints and the inline API-class dump that should live in a separate reference file.

Suggestions

Convert the 'Relevant API Surface' section into a short list of the few classes Claude needs immediately, moving the full class inventory into a separate reference file (e.g., references/api-surface.md) linked with a clear 'See ...' pointer.

Add a short ordered workflow for the core use case (e.g., 1. copy the closest example from examples/, 2. adapt signature and options, 3. verify with a no-key example run, 4. switch to provider credentials only when the user supplies them) with an explicit verification checkpoint.

Extend the usage-observer snippet to show the consumption side (draining the queue and the event fields to read) so the primary example is fully executable end-to-end.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence (e.g., 'The observer is process-wide, best-effort, and fail-open'), with no padding explaining known concepts; the 40+-item comma-separated 'Relevant API Surface' class dump is token-heavy and could be tightened. This sits at anchor 4 rather than 5 because that listing and a few dense bullets could still be trimmed.

4 / 5

Actionability

Executable Java snippets ('AxGlobals.setUsageObserver(usageQueue::add)'), a concrete runnable example path ('src/examples/java/generation/UsageObserverExample.java'), and specific option-map guidance make this mostly copy-paste ready. It falls short of anchor 5 because the observer example shows only registration/clearing, not the event-consumption shape, and imports are omitted.

4 / 5

Workflow Clarity

The body is organized by topic rather than as a sequenced process; the implied order (Core Pattern, observer registration through teardown, guardrails) lacks explicit checkpoints or error-recovery loops for the debugging workflows it covers. This matches anchor 3; it is not 2 because the guardrails and lifecycle guidance do impose a rough order.

3 / 5

Progressive Disclosure

Sections are well organized and external materials are clearly signaled ('Package API docs: `API.md` and `axir-api.json`', 'Runnable examples: `examples/`'), but the long inline 'Relevant API Surface' listing is reference content that belongs in a separate file. This matches anchor 3 rather than 4 because that misplaced inline content is a real organization gap.

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 description with an explicit 'Use when' trigger, a pinned package identity, and a list of concrete capability areas. Its only gaps are minor: capability nouns instead of concrete actions and a few missing natural synonyms.

DimensionReasoningScore

Specificity

It names several concrete capability areas ('agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging'), matching anchor 4's 'several specific actions; minor gaps'. It is not 5 because the items are domain nouns rather than fully concrete actions, leaving minor coverage gaps.

4 / 5

Completeness

It explicitly answers 'when' ('Use when writing Java code with `dev.axllm:ax`') and lists what the package covers (tracing, accounting, logs, diagnostics, replay, debugging), so both are present. It is not 5 because the 'what' is a list of capability areas rather than concrete actions the skill performs, making it slightly less explicit than the anchor-5 example.

4 / 5

Trigger Term Quality

'agent tracing', 'usage accounting', 'runtime diagnostics', 'replay', 'production debugging', and 'Java' are natural phrases a user needing this skill would say, matching anchor 4's good-but-incomplete coverage. It is not 5 because common synonyms like 'telemetry', 'observability', or 'LLM monitoring' are missing.

4 / 5

Distinctiveness Conflict Risk

The exact package coordinate '`dev.axllm:ax`' plus the Java language pin and the observability niche give it a clear, distinct trigger profile with minimal overlap risk, matching anchor 5.

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.