Name: visual-testing
Rating: 61.6 (1 reviews)
Author: fernandezbaptiste

visual-testing

Visual regression testing with Chromatic, Lost Pixel, and Playwright snapshots. Use when detecting UI changes, maintaining visual consistency, reviewing design changes, or setting up screenshot comparison in CI/CD.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/visual-testing/SKILL.md

The canonical home for this skill is visual-testing in fernandezbaptiste/Skrillz

Quality

Content

61%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.

Highly actionable with executable examples across all three tools, but weakened by broken reference paths, heavy inlining of detail that belongs in the existing reference files, and missing validation feedback loops around destructive baseline updates.

Suggestions

Fix the References section to match the actual bundle: `references/lost-pixel-setup.md` and create or remove `references/playwright-snapshots.md`.

Move detailed config blocks, CI YAML, and the comparison matrix into the reference files, keeping SKILL.md as a concise overview that points to them.

Add an explicit validate-before-accept checkpoint to baseline management (e.g., review the diff and confirm intent before running `--update-snapshots` or `--auto-accept-changes`).

Dimension	Reasoning	Score
Conciseness	Mostly practical with lean code blocks, but includes some padding (ASCII workflow diagram, feature/comparison tables) and pins time-sensitive version numbers ('playwright:v1.40.0-focal') outside any deprecated section, which the guideline penalizes.	3 / 5
Actionability	Copy-paste ready throughout: install commands, playwright/lostpixel configs, executable test specs, GitHub Actions YAML, and Dockerfile, covering the common cases for all three approaches.	5 / 5
Workflow Clarity	Quick Start and PR workflow are sequenced with a review/approve checkpoint, but baseline updates (`--update-snapshots`, `--auto-accept-changes`) are destructive/batch operations without an explicit validate-before-overwrite feedback loop, capping the score per the rubric guidance.	3 / 5
Progressive Disclosure	The References section signals one-level-deep files, but two of three referenced paths are wrong — `lost-pixel-self-hosted.md` (actual: `lost-pixel-setup.md`) and `playwright-snapshots.md` (does not exist) — and large config/example content that belongs in those reference files is inlined in SKILL.md, breaking navigation.	2 / 5
	Total	13 / 20 Passed

Description

83%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, third-person description that clearly states capability and trigger conditions with concrete, natural-language triggers. Minor room to tighten 'maintaining visual consistency' and reduce Playwright overlap.

Dimension	Reasoning	Score
Specificity	Names the domain ('visual regression testing') plus several concrete actions — 'detecting UI changes, maintaining visual consistency, reviewing design changes, or setting up screenshot comparison in CI/CD' — but 'maintaining visual consistency' is slightly abstract, leaving minor gaps versus comprehensive coverage.	4 / 5
Completeness	Explicitly states both what ('Visual regression testing with Chromatic, Lost Pixel, and Playwright snapshots') and when ('Use when detecting UI changes...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('UI changes', 'design changes', 'screenshot comparison', 'CI/CD') alongside named tools, but misses a few common synonyms/extensions like 'visual diffs' or 'snapshot testing'.	4 / 5
Distinctiveness Conflict Risk	The 'visual regression / screenshot comparison' niche is clear and tool-scoped, but naming Playwright creates minor overlap risk with a general Playwright testing skill.	4 / 5
	Total	17 / 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
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: .claude/skills/visual-testing/SKILL.md
Commit: 93ed392

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.