cx-telemetry-querying

Use this skill for any question involving telemetry data: "investigate an issue", "debug a problem", "find out why something is slow", "check error rates", "analyze user behavior", "understand a production incident", "query telemetry data", "look at logs", "search logs", "find errors", "find stack traces", "filter by severity", "check traces", "examine spans", "investigate request latency", "debug service-to-service calls", "look up a trace ID", "analyze RUM data", "check frontend performance", "frontend errors", "Core Web Vitals", "JavaScript exceptions", "query metrics", "check CPU usage", "run a PromQL query", "check error rate", "look up a metric", "check memory usage", "how do I write a DataPrime query", "DataPrime syntax", or wants to answer questions using observability data from logs, metrics, traces, RUM, or APM.

Quality

92%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable routing skill with clear workflows and sound progressive disclosure that points to real reference files. The main weakness is redundancy across the routing/CLI sections, which inflates the token budget without adding new guidance.

Suggestions

Consolidate routing guidance: the Quick Routing Guide, Discovery Workflow, and Examples overlap on pillar-selection logic — consider a single decision table plus one worked ambiguous example.

Trim the CLI Commands Reference of commands already demonstrated inline in the Discovery Workflow, or move the full reference table into a dedicated reference file.

Reduce repeated "load references" instructions by relying on the Loading References table once and citing it (e.g., "load per the table above") in subsequent steps.

Dimension	Reasoning	Score
Conciseness	It avoids explaining concepts Claude already knows, but routing guidance is repeated across the Quick Routing Guide, Discovery Workflow, Examples, and Fallback sections, and the CLI Commands Reference duplicates commands already shown in Discovery. It could be tightened.	2 / 3
Actionability	Concrete, copy-paste-ready commands appear throughout, e.g. `cx metrics search --name 'transaction'` and `cx search-fields "transaction amount" --dataset logs`, with specific flags and examples.	3 / 3
Workflow Clarity	The Discovery Workflow is clearly sequenced (Steps 1-4) with per-step decision points, and the Fallback and Pivoting section provides an explicit error-recovery feedback loop ("Try at least two pillars before concluding the data does not exist").	3 / 3
Progressive Disclosure	The SKILL.md is a concise overview that signals one-level-deep references via the Loading References table; all seven referenced files exist in ./references/ and content is appropriately split between routing and query syntax.	3 / 3
	Total	11 / 12 Passed

Description

100%

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, trigger-rich description that clearly states the skill's domain and when to invoke it, anchored by distinctive observability terminology. Its only weakness is verbosity from listing ~30 trigger phrases, though this does not violate any single dimension's anchors.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions such as "run a PromQL query", "filter by severity", "look up a trace ID", "check CPU usage", and "check error rate" rather than vague language.	3 / 3
Completeness	Explicitly answers both what ("answer questions using observability data from logs, metrics, traces, RUM, or APM") and when ("Use this skill for any question involving telemetry data") with an explicit trigger clause.	3 / 3
Trigger Term Quality	Strong coverage of natural phrasings users would actually say, e.g. "find out why something is slow", "look at logs", "Core Web Vitals", and "how do I write a DataPrime query".	3 / 3
Distinctiveness Conflict Risk	Telemetry-specific vocabulary (DataPrime, PromQL, RUM, spans, traces, Core Web Vitals) carves a clear niche that is unlikely to trigger the wrong skill, despite a few generic phrases like "investigate an issue".	3 / 3
	Total	12 / 12 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
Commit: 6574ecc

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.