localhost-screenshots

Capture and compare localhost pages across viewports for visual regression. Use when asked to "screenshot my site", "capture pages", "visual diff", "compare screenshots", "responsive screenshots", "check breakpoints", "visual regression", or when capturing programmatic screenshots of a local dev server across viewport breakpoints.

Quality

83%

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

71%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.

The body is well-structured with strong progressive disclosure and actionable, sequenced workflows including validation checkpoints. Its main weakness is conciseness: several explanatory prose passages could be trimmed. Tightening the Chrome MCP capability-binding paragraphs would lift the score.

Suggestions

Condense the Playwright 1.62 entry-points paragraph and the Chrome MCP "Host tab-tool schema" / "Missing resize capability" prose into bullet rules; keep the executable guidance, drop the rationale paragraphs.

Inline or briefly preview the canonical 8-breakpoint capture script (or a minimal variant) so the main action path is executable from SKILL.md alone, pushing actionability toward 5.

Mirror the Chrome MCP flow's explicit verify/restore checkpoints into the Playwright quick workflow steps so both paths show the same validation rigor.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational guidance Claude would not already know, but several prose-heavy passages (the Playwright 1.62 entry-points paragraph, the Chrome MCP capability-binding and host-tab-schema paragraphs) could be tightened without losing clarity, fitting the "mostly efficient but could be tightened" anchor.	3 / 5
Actionability	Copy-paste setup commands (playwright@1.62.0, playwright install chromium, npx serve ... --no-clipboard) and executable one-line JS snippets give mostly executable guidance; the canonical capture script is deferred to a reference file rather than inlined, a minor gap.	4 / 5
Workflow Clarity	The Chrome MCP quick-screenshot flow is a clear 5-step sequence with explicit verification (verify viewport before navigation, check final URL stays local, report artifact only after capture, restore overrides) and fallback paths; the Playwright quick workflow is briefer and defers detail to references, leaving a minor gap versus the explicit-checkpoint anchor.	4 / 5
Progressive Disclosure	A clear overview with a well-signaled one-level-deep Reference Files table mapping each bundled file to a "Load when" condition; all referenced paths (5 reference md files, 3 scripts, evals/scenarios.json) exist as real files, matching the clear-overview anchor.	5 / 5
	Total	16 / 20 Passed

Description

95%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.

The description is strong: it concisely states the skill's purpose and provides abundant natural trigger phrases. It clearly answers both what and when with low conflict risk. Minor expansion of the concrete action list could push specificity to a 5.

Dimension	Reasoning	Score
Specificity	"Capture and compare localhost pages across viewports for visual regression" names the domain and several concrete actions (capture, compare, viewport sweeps, visual regression); not a 5 because the action list is compact rather than comprehensive.	4 / 5
Completeness	Explicitly answers what (capture/compare localhost pages across viewports for visual regression) and when ("Use when asked to..." with concrete trigger phrases), matching the both-what-and-when anchor.	5 / 5
Trigger Term Quality	Quotes many natural user phrases — "screenshot my site", "visual diff", "compare screenshots", "responsive screenshots", "check breakpoints", "visual regression" — with strong synonym coverage, matching the comprehensive anchor.	5 / 5
Distinctiveness Conflict Risk	A clear niche (localhost dev-server captures across breakpoints for visual regression) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 7 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: t4sh/skills4sh
Path: skills/localhost-screenshots/SKILL.md
Commit: fe99a33

Reviewed: 1 day 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.