Name: ax-go-agent-observability
Rating: 68 (1 reviews)
Author: ax-llm

ax-go-agent-observability

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.

Quality

82%

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

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.

The body is well-structured and actionable with executable Go examples and valuable non-obvious operational guidance, but it inlines reference material that should live in the referenced API files and lacks explicit validation checkpoints in its usage-observer workflow.

Suggestions

Move the 'Relevant API Surface' symbol list into API.md and replace it with a short pointer plus the handful of symbols needed for the shown patterns, improving both conciseness and progressive disclosure.

Render file references as real markdown links (e.g., [API.md](API.md), [examples/](examples/)) so navigation is clearly signaled and one level deep.

Add an explicit validation/verification step to the usage-observer workflow (e.g., confirm events emit for a consumed stream before relying on accounting, and assert the observer is cleared in teardown) to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code and non-obvious operational guidance (e.g., fail-open observer, bounded queue) that earns its place, though the large inline API symbol list and some bullets could be trimmed or deferred.	4 / 5
Actionability	Provides copy-paste-ready Go for the core agent pattern and usage observer plus concrete symbol names, but attaching usageContext and per-call overrides are described rather than shown in code — a minor gap.	4 / 5
Workflow Clarity	There is a rough sequence (register observer → enqueue → persist out of band → clear on shutdown) but no explicit validation checkpoints; for a reference-style skill the steps are present yet lack feedback loops.	3 / 5
Progressive Disclosure	References to API.md, axir-api.json, axir-capabilities.json, and examples/ exist but are bare paths rather than clearly signaled links, and the large inline 'Relevant API Surface' list is reference content that belongs in the referenced API.md; no bundle files are actually present to verify.	3 / 5
	Total	14 / 20 Passed

Description

100%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.

The description is specific, uses a natural 'Use when …' trigger, answers both what and when explicitly, and occupies a clearly distinct niche. It is concise without fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Names the domain (Go code with the ax package) and lists six concrete capabilities — agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging — giving comprehensive coverage.	5 / 5
Completeness	Explicitly states both what the skill does (write Go code with the ax package for the listed observability tasks) and when to use it via the 'Use when …' clause.	5 / 5
Trigger Term Quality	'Use when writing Go code with …' is a natural trigger, and the capability terms (agent tracing, usage accounting, action logs, runtime diagnostics, replay, production debugging) are phrases users would actually say, with strong coverage.	5 / 5
Distinctiveness Conflict Risk	Scoped to Go code using a specific generated package for observability — a clear niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	20 / 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/go/skills/ax-go-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.