CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cx-rum-setup

Use this skill when the user asks to "add RUM", "set up RUM", "install the RUM SDK", "add Coralogix RUM to my app", "create a RUM API key", "RUM public key", "init Coralogix RUM", "CoralogixRum.init", "add the browser SDK", "real user monitoring", "frontend monitoring", "monitor my web app", "session replay", "track frontend errors", "add RUM to React", "add RUM to Next.js", "add RUM to my mobile app", or wants to instrument a browser or mobile application with Coralogix Real User Monitoring end to end - RUM API key, SDK install, init code, and verifying data arrives.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 body: concrete commands and code at every step, a well-sequenced workflow with validation and error recovery, and disciplined token use. The main improvement opportunities are trimming the Key Principles recap and moving secondary detail (source maps, permission-error matrix) into a reference file.

Suggestions

Trim or fold the "Key Principles" section into the workflow steps - most bullets restate rules already stated (SendRUMData-only, reuse before create, fetch docs), saving ~10 lines.

Move the source-maps guidance and the DATA-INGEST-API-KEYS permission-error matrix into a references/ file (e.g. references/troubleshooting.md) to shorten the main body and improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is dense with operational specifics and explains nothing Claude already knows, but the "Key Principles" section recapitulates rules already stated in the workflow and the CLI table duplicates commands shown in context - anchor 4's "minor instances that could be trimmed" rather than anchor 5's every-token-earns-its-place.

4 / 5

Actionability

Fully executable throughout: exact CLI commands with flags, a copy-paste-ready heredoc JSON for key creation, real CoralogixRum.init TypeScript, and a runnable dataprime verification query. Showing only the browser install inline is explicitly justified ("fetch them instead of guessing"), matching anchor 5.

5 / 5

Workflow Clarity

Six clearly sequenced steps with an ordered stop-at-first-match platform table, an approval gate before the write, explicit permission-denied recovery paths ("Don't retry with other payloads... continue from step 4"), and a verification step with troubleshooting causes - anchor 5's explicit validation and error-recovery feedback loops. No destructive/batch operation applies a cap.

5 / 5

Progressive Disclosure

Well-organized sections with clear headers and cross-links to related skills, but at ~145 lines with no bundle files, detail like the source-maps aside and the permission-error matrix would sit better in a reference file - anchor 4's "good structure, minor organization gaps" rather than anchor 5's appropriately split content.

4 / 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.

An excellent description: concrete end-to-end capability statement, an explicit Use-when clause with a comprehensive set of natural trigger phrases, and a clearly branded Coralogix RUM niche. The only weakness is a handful of generic monitoring phrases that slightly raise overlap risk with neighboring observability skills.

DimensionReasoningScore

Specificity

"instrument a browser or mobile application with Coralogix Real User Monitoring end to end - RUM API key, SDK install, init code, and verifying data arrives" lists multiple concrete actions comprehensively covering the whole setup flow, matching the anchor-5 example's coverage rather than the minor-gaps anchor 4.

5 / 5

Completeness

It explicitly answers "when" ("Use this skill when the user asks to..." with concrete trigger phrases) and "what" (key, SDK install, init code, verifying data arrives), matching the anchor-5 pattern exactly.

5 / 5

Trigger Term Quality

Natural phrases users would actually say are covered exhaustively - "add RUM", "set up RUM", "real user monitoring", "session replay", "track frontend errors", plus platform variants like "add RUM to React" / "add RUM to Next.js" - going beyond anchor 4's "a few natural terms missing".

5 / 5

Distinctiveness Conflict Risk

The Coralogix RUM niche is unmistakable ("CoralogixRum.init", "RUM public key"), but broader triggers like "monitor my web app", "frontend monitoring", and "track frontend errors" could overlap with general monitoring or error-tracking skills, fitting anchor 4 (minor overlap risk) rather than anchor 5's minimal conflict risk.

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-rum-setup/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.