implementing-real-user-monitoring

Implement Real User Monitoring (RUM) to capture actual user performance data including Core Web Vitals and page load times. Use when setting up user experience monitoring or tracking custom performance events. Trigger with phrases like "setup RUM", "track Core Web Vitals", or "monitor real user performance".

Quality

50%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/performance/real-user-monitoring/skills/implementing-real-user-monitoring/SKILL.md

Quality

Discovery

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.

This is a strong skill description that clearly defines its scope around Real User Monitoring, lists specific capabilities, and provides explicit trigger guidance with natural user phrases. It uses proper third-person voice and covers both the 'what' and 'when' dimensions effectively. The description is concise yet comprehensive, making it easy for Claude to distinguish this skill from others.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'capture actual user performance data', 'Core Web Vitals', 'page load times', 'tracking custom performance events'. These are concrete, domain-specific capabilities.	3 / 3
Completeness	Clearly answers both 'what' (implement RUM to capture user performance data including Core Web Vitals and page load times) and 'when' (explicit 'Use when' clause plus 'Trigger with phrases like' providing concrete trigger examples).	3 / 3
Trigger Term Quality	Includes strong natural trigger terms: 'RUM', 'Core Web Vitals', 'page load times', 'user experience monitoring', 'custom performance events', 'setup RUM', 'track Core Web Vitals', 'monitor real user performance'. Good coverage of terms users would naturally use.	3 / 3
Distinctiveness Conflict Risk	Clearly occupies a distinct niche around Real User Monitoring specifically. The terms 'RUM', 'Core Web Vitals', and 'real user performance' are highly specific and unlikely to conflict with general monitoring or other performance-related skills.	3 / 3
	Total	12 / 12 Passed

Implementation

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

This skill reads like a product description or README rather than actionable instructions for Claude. It is almost entirely meta-commentary about what the skill does rather than providing concrete, executable guidance. There are no code examples, no specific platform implementation details, and no validation steps despite the task involving JavaScript integration and third-party platform configuration.

Suggestions

Replace the abstract 'Instructions' section with concrete, executable code examples for at least one RUM platform (e.g., a complete web-vitals + Google Analytics snippet that can be copy-pasted).

Remove the 'Overview', 'How It Works', 'When to Use This Skill', and 'Integration' sections entirely—they are meta-descriptions that waste tokens and provide no actionable value.

Add explicit validation steps to the workflow, such as verifying metrics appear in the platform dashboard, checking browser console for errors, and testing with Lighthouse.

Create separate reference files for each platform (e.g., DATADOG_RUM.md, GA_RUM.md, NEWRELIC_RUM.md) with platform-specific implementation code and link to them from the main skill.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive sections explaining what the skill does, when to use it, how it works, and integration notes—all meta-information Claude doesn't need. The 'Overview' and 'How It Works' sections restate the same information. Concepts like Core Web Vitals abbreviations and RUM platforms are explained at a level Claude already understands.	1 / 3
Actionability	Despite promising code snippets in the examples section, no actual executable code is provided anywhere. The instructions are entirely abstract ('Implement tracking code in application frontend', 'Select appropriate RUM platform') with no concrete commands, code examples, or copy-paste ready snippets for any of the three mentioned platforms.	1 / 3
Workflow Clarity	The 'Instructions' section lists 6 high-level steps but they are vague directives without any specifics, validation checkpoints, or feedback loops. For an implementation task involving JavaScript integration and platform configuration, there are no concrete validation steps or error recovery sequences.	1 / 3
Progressive Disclosure	The content is a monolithic wall of text with no references to external files, no bundle files to support it, and no structured navigation. The 'Resources' section lists generic topic names without actual links or file references. Content that could be split (platform-specific implementations, examples) is neither inline nor referenced.	1 / 3
	Total	4 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 69c73e9

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.