CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cx-alerts

This skill should be used when the user asks to "manage alerts", "create alert", "list alerts", "delete alert", "check alert status", "enable alert", "disable alert", "investigate firing alerts", "check which alerts are active", "find alerting rules", "set up an alert", "configure alerting", "mute an alert", "silence an alert", "see alert definitions", "check alert priority", or wants to manage Coralogix alert definitions using the cx CLI.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

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 highly actionable, well-structured body with copy-paste commands, complete JSON examples, and exemplary progressive disclosure into a verified five-file reference bundle. The main improvements are removing the duplicated suppression-rules command table and adding an explicit error-recovery step for failed creates.

Suggestions

Drop or compress the Suppression Rules command table (it repeats five rows already present in the CLI Commands table) and keep only the two-ID semantics and request-body shape, which are the non-obvious parts.

Reduce the three full inline JSON examples to one representative example (e.g., Logs Threshold) and point to references/alert-schemas.md for the other types, since that file already contains all wire formats.

Add an error-recovery step to the Create Workflow, e.g., "If create fails on schema validation, fetch an existing alert with `cx alerts get <id> -o json`, diff the structure, and retry" — this closes the feedback loop the rubric expects for destructive/batch operations.

DimensionReasoningScore

Conciseness

The body is dense and operational with no padding or explanations of known concepts, but the Suppression Rules command table ("cx alerts suppression-rules list/get/create/update/delete") duplicates rows already in the CLI Commands table, and three full inline JSON examples is generous given references/alert-schemas.md holds the complete schemas. Minor trimming opportunities keep this below the lean-and-efficient anchor.

4 / 5

Actionability

Everything is copy-paste ready: exact CLI invocations ("echo '<json>' | cx alerts create", "cx alerts list -o json | jq '.[] | select(.status == \"ALERTING\")'"), three complete executable JSON payloads covering the common alert types, a concrete suppression-rule request body, and a documented tip to fetch an existing alert as a template.

5 / 5

Workflow Clarity

The Create Workflow is a clear 6-step sequence with an explicit verification checkpoint ("Verify with `cx alerts list --name`", reinforced by "Verify after create" in Key Principles), but there is no error-recovery loop for when creation fails, fitting "most checkpoints present; minor validation gaps" rather than the feedback-loops anchor.

4 / 5

Progressive Disclosure

Verified against the actual bundle: all five referenced files (alert-schemas.md, dataprime-reference.md, logs-querying.md, promql-guidelines.md, spans-querying.md) exist, are one level deep, and are clearly signaled in Additional Resources with accurate one-line descriptions. The body keeps only quick-reference tables and three examples while bulk schemas and query languages live in the references — a clear overview with well-signaled references.

5 / 5

Total

18

/

20

Passed

Description

96%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 with explicit what/when structure, comprehensive natural trigger phrases including synonyms, and concrete lifecycle actions for a clearly named domain. Its only weakness is that most trigger phrases are generic alert vocabulary, with the Coralogix/cx CLI anchor appearing only at the end.

DimensionReasoningScore

Specificity

The description enumerates concrete actions across the full alert lifecycle — "create alert", "list alerts", "delete alert", "enable alert", "disable alert", "mute an alert", "silence an alert", "check alert status", "check alert priority" — for a clearly named domain ("manage Coralogix alert definitions using the cx CLI"), matching the comprehensive-coverage anchor.

5 / 5

Completeness

Both halves are explicit: "when" via "This skill should be used when the user asks to" followed by concrete trigger phrases, and "what" via "wants to manage Coralogix alert definitions using the cx CLI". This matches the anchor for clearly answering both what AND when with concrete trigger phrases.

5 / 5

Trigger Term Quality

It includes natural user phrases with thorough synonym coverage — "mute an alert"/"silence an alert", "set up an alert"/"configure alerting", "manage alerts"/"create alert", "investigate firing alerts"/"check which alerts are active" — matching the anchor requiring comprehensive natural terms including synonyms.

5 / 5

Distinctiveness Conflict Risk

The niche is clear (Coralogix alert definitions, cx CLI), but most listed triggers ("manage alerts", "check alert status") are generic alert phrases anchored to Coralogix only at the end, leaving minor overlap risk with alert-related requests in other systems — fitting the "mostly distinct; minor overlap risk" anchor rather than the minimal-conflict anchor.

4 / 5

Total

19

/

20

Passed

Validation

100%

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-alerts/SKILL.md

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.