web-monitor

Use this skill when the user wants to watch a webpage for changes, monitor a URL, detect content updates, or get notified when a site changes.

Quality

86%

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

87%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 concise, highly actionable single-purpose skill with excellent code coverage and clean structure. Its main weakness is the monitoring loop, which lacks explicit validation and error-recovery checkpoints for a continuous batch operation.

Suggestions

Add a validation/verification checkpoint in run_monitor: confirm notification POSTs succeeded (check response status) before considering an alert sent, and surface failures rather than swallowing them in a bare 'except Exception'.

Introduce a validate→fix→retry feedback loop for transient fetch failures (e.g., retry with backoff on timeouts) so the monitoring workflow degrades gracefully instead of silently skipping URLs.

Note an explicit guardrail for the monitoring loop (e.g., rate-limit/robots.txt check before fetching) as a stated step rather than only mentioning 'Respect robots.txt' in passing in the Quick Reference table.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout — each section is a one-line header followed by executable code, assuming Claude's competence with no padded explanations of hashing, CSS selectors, or notification libraries.	5 / 5
Actionability	Fully executable, copy-paste-ready code covering the common cases (whole-page hashing, CSS-element targeting, diffing, Discord/Telegram/generic webhooks, Playwright rendering) plus a concrete tool-mapping Quick Reference table.	5 / 5
Workflow Clarity	The Full Monitor Loop gives a rough sequence, but it lacks validation checkpoints — a broad 'except Exception' swallows errors, notifications are fire-and-forget with no success verification, and there is no validate→fix→retry feedback loop, which caps batch/continuous-operation workflow clarity at 3.	3 / 5
Progressive Disclosure	No bundle files are present and the body is a single-purpose, well-organized set of single-level sections; per the simple-skill guidance, well-organized structure without nested references earns the top score.	5 / 5
	Total	18 / 20 Passed

Description

86%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, trigger-rich description that clearly signals when to use the skill and uses natural user language. It would reach the top tier by stating the capability ('what') explicitly alongside the 'when' trigger clause.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('watch a webpage for changes, monitor a URL, detect content updates, get notified when a site changes'), but stops short of the comprehensive coverage seen in a 5 since it never surfaces the alert channels (webhook/Discord/Telegram/email) the skill actually supports.	4 / 5
Completeness	It has an explicit 'when' ('Use this skill when the user wants to...'), but the 'what' is only implied by the trigger phrasing rather than stated as a concrete capability (e.g., 'Monitors URLs for content changes and sends alerts'), so it falls just below the explicit both-what-and-when anchor.	4 / 5
Trigger Term Quality	Comprehensive natural phrasing a user would actually say — 'watch a webpage for changes', 'monitor a URL', 'detect content updates', 'notified when a site changes' — covering the core synonyms and intents without relying on jargon.	5 / 5
Distinctiveness Conflict Risk	The description carves out a clear niche (webpage/URL change monitoring and notification) with distinct triggers and minimal overlap with other skill categories.	5 / 5
	Total	18 / 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: ProwlrBot/prowlr-marketplace
Path: skills/web-monitor/SKILL.md
Commit: 32f0050

Reviewed: 3 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.