CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

67

Quality

84%

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

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 strong, highly actionable API reference with a clear hook-selection guide and guardrails, undermined by token waste: the duplicated actorTurnCallback type block and inline reference-material bulk. Splitting type/event-shape details into a references file and de-duplicating would lift both conciseness and progressive disclosure.

Suggestions

Delete the duplicated actorTurnCallback type block (the second copy marked 'deprecated alias'); if the alias must be documented, one line suffices.

Move the full callback type signatures and event-shape details into a references/ file (e.g., references/types.md), keeping usage examples and selection guidance inline in SKILL.md.

Trim rules that restate the field definitions verbatim (e.g., 'output is not raw stdout' repeats the earlier output definition) and consolidate each hook's 'What it gives you' bullets with its rules list.

DimensionReasoningScore

Conciseness

Dense rules and code with no explanations of known concepts, but the actorTurnCallback type block is duplicated verbatim (~30 lines, second copy labeled 'deprecated alias') and several rules restate earlier bullet definitions. Mostly efficient but noticeably could be tightened — more than minor trimming, less than several padded sections.

3 / 5

Actionability

Every hook has a concrete TypeScript example plus full type signatures (e.g., the axGlobals.onUsage + usageContext forward snippet and the onFunctionCall payload shape). Examples reference undefined context (usageQueue, runtime, llm, auth), making them illustrative rather than fully copy-paste ready — minor gaps.

4 / 5

Workflow Clarity

'Choose The Smallest Hook' gives an unambiguous decision sequence, each section opens with 'Use X when...', and 'Do Not Generate' provides guardrails; no validation steps are needed (no destructive/batch operations). Clear selection workflow, but no explicit error-recovery or end-to-end setup ordering beyond the globals snippet.

4 / 5

Progressive Disclosure

No bundle files exist; a ~400-line SKILL.md inlines bulk type-signature dumps and event-shape reference material (part of it duplicated) that belongs in a references/ file. Headers are clear and the one cross-skill reference ('also read ax-ai') is signaled, but reference content that should be separate is inline.

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.

A model description: concrete 'what', explicit 'Use when' trigger clause with natural keywords and specific API names, third-person voice, and a distinct niche with minimal overlap risk. No changes needed.

DimensionReasoningScore

Specificity

Enumerates ~15 concrete API surfaces (axGlobals.onUsage, usageContext, actorTurnCallback, getChatLog(), getUsage(), resetUsage(), reportSuccess/reportFailure, etc.) alongside a concrete 'what' ('generate correct AxAgent observability code using @ax-llm/ax'), matching the comprehensive-coverage anchor rather than the minor-gaps anchor.

5 / 5

Completeness

Explicitly answers both 'what' (generate correct AxAgent observability code using @ax-llm/ax) and 'when' ('Use when the user asks about...') with concrete trigger phrases, in third-person voice with no fluff.

5 / 5

Trigger Term Quality

Natural user phrasing ('centralized or multi-tenant usage accounting', 'debug traces', 'progress updates', 'telemetry') plus literal API names a user would mention; no common natural variation is missing, matching the comprehensive-synonyms anchor.

5 / 5

Distinctiveness Conflict Risk

Clear niche (AxAgent observability) with distinct symbol-name triggers that would not fire for sibling skills (ax-agent, ax-agent-rlm, ax-agent-memory-skills cover other scopes); minimal conflict risk.

5 / 5

Total

20

/

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.