wigolo-watch

Monitor a page for changes over time. Create lazy watch jobs on one or many URLs, list them, and check for changes on demand — with optional SSRF-guarded webhook delivery when a change is detected. Use when the user says "monitor this page", "watch this URL for changes", "tell me when this updates", "track this changelog", "notify me if this changes", or wants recurring change detection on web content.

Quality

94%

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 tight, highly actionable SKILL.md: executable examples for every action, a parameters table, explicit anti-patterns and scoping guidance ('When NOT to use'), with zero token waste. The one weakness is the absence of validation/verification steps around its batch-create and delete operations, which caps workflow clarity.

Suggestions

Add a verification step after batch create — e.g. 'After a batch create, run { "action": "list" } and confirm each URL has a job_id before relying on it' — to close the feedback loop for the batch operation.

Document what a check response looks like (changed/unchanged fields, how a webhook failure is reported) so a failed delivery can be detected and retried rather than silently assumed.

Add a brief note on delete semantics (irreversible? does it drop the snapshot?) so the destructive action is used with an explicit checkpoint.

Dimension	Reasoning	Score
Conciseness	The body teaches only skill-specific behavior ('Lazy execution model — there is no background daemon', the 60-second minimum, SSRF guard, url/urls exclusivity) and never explains concepts Claude already knows. Every section and example earns its tokens. Not a 4 because there is no over-explanation to trim.	5 / 5
Actionability	The Quick Reference gives eight complete, copy-paste-ready JSON payloads covering every action (single and batch create, selector scoping, webhook, list, check, pause/resume/delete), backed by a parameter table with defaults and mutual-exclusion notes. Not a 4 because the examples cover the common cases fully and are executable as written.	5 / 5
Workflow Clarity	'How It Works' sequences create→check→deliver clearly and Anti-Patterns cover pre-flight error modes (interval below 60, expecting autonomous checks, url/urls exclusivity). However, the skill involves batch operations ('Batch create across several URLs') and a destructive 'delete' action with no validation/verification steps — e.g. confirming created jobs via 'list', or handling partial batch failures — which per the rubric caps this dimension at 3. Not a 2 because the sequence itself is coherent and error-avoidance guidance is present; not a 4 because the batch/destructive cap takes precedence.	3 / 5
Progressive Disclosure	A single-file bundle (no references/, scripts/, or assets/ exist) of roughly 72 lean lines, organized into clean, navigable sections (Quick Reference, Parameters, How It Works, Anti-Patterns, When NOT to use, See Also). The See Also links to sibling skills are one level deep and clearly signaled, and nothing is bloated enough to warrant splitting. Not a 4 because there are no organization gaps or buried references.	5 / 5
	Total	18 / 20 Passed

Description

100%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 exemplary description: third-person voice, concrete actions covering the full lifecycle, an explicit 'Use when…' clause with five natural trigger phrases, and a well-delineated niche. It follows every guideline — concise, no fluff, no over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create lazy watch jobs on one or many URLs', 'list them', 'check for changes on demand', 'optional SSRF-guarded webhook delivery' — comprehensively covering the skill's lifecycle. This matches the anchor-5 example's breadth; it is not a 4 because the action coverage is comprehensive rather than having minor gaps.	5 / 5
Completeness	Explicitly answers 'what' (monitor pages, create/list/check lazy watch jobs, webhook delivery) and 'when' via a concrete 'Use when the user says…' clause with trigger phrases — the anchor-5 pattern. Not a 4 because the 'when' guidance is maximally explicit.	5 / 5
Trigger Term Quality	Quotes 'monitor this page', 'watch this URL for changes', 'tell me when this updates', 'track this changelog', 'notify me if this changes' — comprehensive natural phrasings with synonyms users would actually say. Not a 4 because no common variant of the request is obviously missing.	5 / 5
Distinctiveness Conflict Risk	Recurring page-change monitoring with lazy checks and webhook delivery is a clear niche with distinct triggers ('tell me when this updates', recurring change detection) that would not pull one-shot diff or plain fetch skills. Not a 4 because conflict risk is minimal.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: KnockOutEZ/wigolo
Path: skills/wigolo-watch/SKILL.md
Commit: da59eee

Reviewed: 9 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.