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

83%

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

86%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 well-structured, highly actionable routing skill with executable commands, a clear discovery workflow, and clean one-level-deep progressive disclosure. The only notable weakness is redundant re-listing of reference file paths across sections.

Suggestions

Reference the Loading References table once and link to it from Discovery Workflow and Examples instead of re-listing the same file paths inline.

Consider adding a brief explicit validation checkpoint (e.g., confirm a discovered metric/field is non-empty before committing to that pillar) to strengthen the workflow gates.

Dimension	Reasoning	Score
Conciseness	The body is largely purposeful and assumes Claude's competence (routing/pointers rather than teaching what telemetry is), but reference file lists are re-stated inline in Discovery Workflow, Examples, and Key Principles, which could be trimmed to tighten token use.	4 / 5
Actionability	It provides fully executable, copy-paste-ready commands with real flags and dataset values (e.g., `cx metrics search --name 'transaction'`, `cx search-fields "payment_failed" -s value --dataset logs`) plus a command reference table covering the common cases.	5 / 5
Workflow Clarity	A clear Discovery Workflow (Steps 1-4), routing table, and an explicit pivot feedback loop ("Do not stop after one failed attempt; try at least two pillars") sequence the process, though checkpoints are soft ("if found, load...") rather than hard validate-then-proceed gates.	4 / 5
Progressive Disclosure	SKILL.md is a clean overview whose references are one level deep, all referenced paths verified to exist, and organized via a pillar-to-files routing table plus inline pointers, making navigation easy with no nested references.	5 / 5
	Total	18 / 20 Passed

Description

81%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 trigger-rich, well-targeted description with explicit use-when guidance and a clear observability niche. The main weakness is that the "what" is conveyed as a long list of example questions rather than a concise capability statement.

Suggestions

Lead with a one-sentence capability statement (e.g., "Routes and runs telemetry queries across logs, metrics, traces, and RUM") before the trigger-phrase list so the 'what' is explicit.

Trim the longest trigger list slightly and group synonyms per pillar to reduce verbosity while preserving coverage.

Dimension	Reasoning	Score
Specificity	The description names the telemetry domain and touches many concrete actions ("check error rates", "run a PromQL query", "examine spans"), but these are framed as user utterances rather than a clean enumerated capability list, so it sits at anchor 3 rather than the comprehensive anchor 5.	3 / 5
Completeness	An explicit "Use this skill for any question involving..." clause answers "when" with concrete trigger phrases, but the "what" is only implied via the example-question list rather than stated as capabilities, keeping it just below anchor 5.	4 / 5
Trigger Term Quality	It packs in comprehensive natural-language triggers across all pillars ("investigate an issue", "find out why something is slow", "Core Web Vitals", "run a PromQL query") including synonyms and technical terms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche (telemetry querying across logs, metrics, traces, RUM, APM) with distinct triggers and minimal risk of firing for unrelated skills.	5 / 5
	Total	17 / 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-telemetry-querying/SKILL.md
Commit: 4aa811a

Reviewed: 2 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.