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.

Quality

80%

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

Quality

Content

68%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 well-structured, actionable reference skill with concrete Java examples and clearly signaled external references. Its main gaps are the lack of any explicit workflow sequencing/validation and a long inline API-surface list that partially duplicates the referenced API docs.

Suggestions

Move the long 'Relevant API Surface' class enumeration into the referenced `API.md` (or a dedicated surface file) and keep only the handful of entry points needed for the core patterns inline.

Define the `llm` variable in the Core Pattern snippet (or note where it comes from) so the example is fully copy-paste executable.

For the usage-observer registration flow, add a short explicit sequence (register observer -> enqueue synchronously -> persist out of band -> clear on teardown) with a validation/checkpoint step so the workflow is sequenced rather than only described as bullets.

Dimension	Reasoning	Score
Conciseness	The body is lean — short factual bullets and two tight code examples with no padding or explanation of concepts Claude already knows — but the long inline 'Relevant API Surface' enumeration is a dense token dump that could be referenced rather than inlined, keeping it just below a 5.	4 / 5
Actionability	Concrete, mostly copy-paste-ready code is given (`Ax.agent(...)`, `helper.forward(...)`, `AxGlobals.setUsageObserver(usageQueue::add)`) plus pointers to runnable example files, with only a minor gap such as the undefined `llm` variable in the Core Pattern snippet.	4 / 5
Workflow Clarity	Content is organized clearly by capability rather than as a sequenced process, and the skill is not a destructive/batch workflow so feedback loops are not strictly required, but no explicit sequence or validation checkpoints are present, capping it at the midpoint.	3 / 5
Progressive Disclosure	Structure is good with clearly signaled, one-level-deep references (`API.md`, `axir-api.json`, `axir-capabilities.json`, `examples/`), though the referenced bundle files are not actually present and the inline 'Relevant API Surface' list overlaps content that `API.md` would hold — a minor organization gap.	4 / 5
	Total	15 / 20 Passed

Description

92%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, specific description that names the package, enumerates concrete capabilities, and opens with an explicit 'Use when' trigger. Its only mild weakness is trigger-term breadth — it lacks synonyms or variations of its keywords.

Dimension	Reasoning	Score
Specificity	Names the domain (Java with `dev.axllm:ax`) and lists six concrete actions — 'agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging' — giving comprehensive coverage of specific capabilities.	5 / 5
Completeness	It explicitly answers both 'what' (the enumerated observability capabilities) and 'when' via the literal 'Use when writing Java code with `dev.axllm:ax`' trigger clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural terms like 'Java code', 'agent tracing', 'usage accounting', and 'production debugging' are present and would be said by users, but synonyms and common variations are not exhaustively covered, so it sits above the midpoint but short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	The description is pinned to a specific generated package (`dev.axllm:ax`) and a narrow observability niche, making it clearly distinguishable with minimal risk of triggering for unrelated skills.	5 / 5
	Total	19 / 20 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-observability/SKILL.md
Commit: dec4f9e

Reviewed: 5 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.