Name: ax-agent-observability
Rating: 71.2 (1 reviews)
Author: ax-llm

ax-agent-observability

This skill helps an LLM generate correct AxAgent observability code using @ax-llm/ax. Use when the user asks about axGlobals.onUsage, usageContext, centralized or multi-tenant usage accounting, actorTurnCallback, onContextEvent, agentStatusCallback, onFunctionCall, reportSuccess, reportFailure, getChatLog(), getUsage(), resetUsage(), debug traces, progress updates, or telemetry for AxAgent runs.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

75%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 thorough, highly actionable observability reference with executable TypeScript examples and clear hook-selection guidance. Its main weakness is token efficiency: a verbatim duplicated type block and some repeated field descriptions could be trimmed.

Suggestions

Remove the duplicated actorTurnCallback type block (the 'deprecated alias' is identical to the first); note the alias in one line instead.

Avoid restating every field in prose bullets, the type signature, and the destructured example — let the type signature carry the canonical list and keep prose to non-obvious semantics only.

Consider moving the large type-signature reference (AxChatLogEntry, AxChatLogMessage, agent.* signatures) into a references/ file and linking to it, keeping SKILL.md as the dispatch overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly assumes Claude's competence, but the actorTurnCallback type signature is duplicated verbatim (~30 lines) as a 'deprecated alias', and field lists are restated across the prose bullets, the type block, and the destructured example — content that could be tightened.	3 / 5
Actionability	Every hook ships a complete, import-included, copy-paste TypeScript example plus full type signatures, covering the common cases concretely.	5 / 5
Workflow Clarity	The 'Choose The Smallest Hook' decision list and per-hook 'Use X when…' guidance give a clear selection sequence, reinforced by a 'Do Not Generate' guardrail section; operations are non-destructive so the validation cap does not apply, but there is no explicit end-to-end multi-step workflow.	4 / 5
Progressive Disclosure	No bundle files exist; the skill is a single well-sectioned dispatch surface with clear headers and one-level cross-skill pointer ('also read ax-ai'). The bulk API/type reference is inline rather than split into referenced files, a minor organization gap.	4 / 5
	Total	16 / 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.

A strong, specific description that clearly states what the skill does and when to use it, with a comprehensive list of natural trigger terms tied to concrete APIs. It uses third-person voice and avoids vague fluff.

Dimension	Reasoning	Score
Specificity	Names the domain ('generate correct AxAgent observability code using @ax-llm/ax') and enumerates many concrete APIs (axGlobals.onUsage, actorTurnCallback, onContextEvent, getChatLog(), getUsage(), resetUsage()), giving comprehensive coverage of concrete actions.	5 / 5
Completeness	Explicitly answers both 'what' (helps an LLM generate correct AxAgent observability code) and 'when' (Use when the user asks about [concrete triggers]), with concrete trigger phrases.	5 / 5
Trigger Term Quality	The 'Use when the user asks about…' clause lists the exact API names a developer would naturally say, plus synonyms such as 'debug traces', 'progress updates', and 'telemetry', giving comprehensive natural-term coverage for this domain.	5 / 5
Distinctiveness Conflict Risk	Triggers are tightly niched to AxAgent observability APIs and clearly distinct from sibling skills (ax-agent, ax-agent-rlm, ax-agent-memory-skills), minimizing conflict risk.	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: website/static/typescript/.well-known/agent-skills/ax-agent-observability/SKILL.md
Commit: 1abea97

Reviewed: ~18 hours 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.