cx-ai-center

Use this skill for any question or action about the user's AI/GenAI applications or agents — their behavior, prompts/responses, quality, hallucinations, guardrails, security, cost/tokens, errors, evaluations/policies, model pricing, or configuration — including comparing or tracking agents over time. It covers both analyzing AI telemetry (GenAI spans) and managing AI Center config via the `cx ai-center` commands.

Quality

94%

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

92%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.

Well-structured and highly actionable content: executable commands, a guarded write workflow with validation, and clean one-level-deep reference disclosure. The only nit is mild repetition of the config-vs-telemetry framing.

Suggestions

Consolidate the config-vs-telemetry distinction into a single section; it currently appears in the intro, 'Golden rule', and 'Key principles', so trimming two of the three repetitions would tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean — compact command tables, targeted jq snippets, and a single JSON example — but the config-vs-telemetry distinction is restated three times (intro, 'Key principles', 'Golden rule'), which is trimmable padding rather than the lean ideal.	4 / 5
Actionability	Executable, copy-paste-ready guidance throughout: concrete `cx ai-center <subcommand>` commands in tables, a runnable jq pipeline, and a complete model-pricing JSON example covering the common cases.	5 / 5
Workflow Clarity	Destructive writes get an explicit sequenced procedure with a validation checkpoint — 'Describe the exact operation… Wait for the user to confirm… Only then execute with `--yes`' — plus read-only/agent-mode feedback guards, matching the top anchor for risky operations.	5 / 5
Progressive Disclosure	The body is an overview that signals one-level-deep detail via real links to references/ai-center-queries.md (verified present), which itself links the sibling dataprime-reference.md and spans-querying.md; navigation is easy and nesting stays one level deep.	5 / 5
	Total	19 / 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 description: it states the domain, concrete actions, an explicit 'Use when…' trigger, and a distinctive command surface. The only minor gap is a few missing natural synonyms in the trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'analyzing AI telemetry (GenAI spans)', 'managing AI Center config via the `cx ai-center` commands', plus behavior, prompts/responses, quality, hallucinations, guardrails, cost/tokens, errors, evaluations/policies, model pricing — giving comprehensive coverage rather than a single vague verb.	5 / 5
Completeness	Opens with an explicit 'Use this skill for any question or action about…' clause that answers both what (analyze AI telemetry + manage AI Center config) and when (any question/action about AI/GenAI apps) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural terms users would say ('AI/GenAI applications', 'agents', 'prompts/responses', 'hallucinations', 'guardrails', 'cost/tokens', 'model pricing', 'AI Center') are well covered, but a few common synonyms/variants are absent, keeping it just short of the top anchor.	4 / 5
Distinctiveness Conflict Risk	The AI/GenAI-applications niche plus the specific `cx ai-center` command surface carve a clear trigger territory distinct from the generic `cx-telemetry-querying` skill, minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: coralogix/cx-cli
Path: skills/cx-ai-center/SKILL.md
Commit: c071372

Reviewed: 6 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.