visual-regression
Visual Regression Test Agent. Storybook + Chromatic/Percy를 사용한 Visual Regression 테스트를 담당합니다. UI 변경 감지 및 시각적 일관성을 검증합니다.
Install with Tessl CLI
npx tessl i github:shaul1991/shaul-agents-plugin --skill visual-regression63
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
40%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 identifies a clear technical niche with specific tooling (Storybook, Chromatic/Percy) which helps with distinctiveness. However, it lacks explicit trigger guidance ('Use when...') and could benefit from more concrete action verbs and natural user language variations. The Korean language mixed with English tool names may also limit discoverability for some users.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios like 'Use when the user mentions visual testing, screenshot comparison, UI regression, or asks about Storybook/Chromatic/Percy integration'
Include more concrete actions such as 'capture component screenshots', 'compare visual baselines', 'review and approve visual changes', 'configure visual test thresholds'
Add natural language trigger terms users might say: 'screenshot testing', 'visual diff', 'UI snapshots', 'component visual testing'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Visual Regression Testing) and tools (Storybook, Chromatic/Percy), mentions UI change detection and visual consistency verification, but doesn't list comprehensive concrete actions like 'capture screenshots', 'compare baselines', or 'approve/reject changes'. | 2 / 3 |
Completeness | Describes what it does (visual regression testing with specific tools) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes relevant technical terms like 'Visual Regression', 'Storybook', 'Chromatic', 'Percy', and 'UI', but missing common user phrases like 'screenshot testing', 'visual diff', 'component testing', or 'UI snapshots' that users might naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | The specific tool names (Storybook, Chromatic, Percy) and the narrow focus on visual regression testing create a clear niche that is unlikely to conflict with other testing or UI-related skills. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides comprehensive, actionable guidance for visual regression testing with Storybook and Chromatic/Percy, featuring excellent executable code examples. However, it's verbose with unnecessary conceptual explanations, lacks explicit validation checkpoints in workflows, and could benefit from better progressive disclosure by splitting detailed configurations into separate files.
Suggestions
Remove the 'Visual Regression 테스트란?' diagram section - Claude already understands this concept
Add explicit validation steps between workflow stages, such as 'Verify Storybook builds successfully before running Chromatic'
Split CI configuration examples (GitHub Actions YAML) into separate reference files and link to them from the main skill
Add error recovery guidance for common failure scenarios (e.g., what to do when diff threshold is exceeded unexpectedly)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanations like the visual diagram explaining what visual regression testing is (Claude knows this), but the code examples are reasonably efficient. The Korean explanations add some verbosity. | 2 / 3 |
Actionability | Provides fully executable code examples for Storybook setup, story writing, Chromatic/Percy CI integration, and configuration files. All commands and code snippets are copy-paste ready. | 3 / 3 |
Workflow Clarity | The review process and checklists provide some workflow guidance, but lacks explicit validation checkpoints between steps. The flow diagram is conceptual rather than actionable, and there's no error recovery guidance for when visual tests fail. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but it's a monolithic document that could benefit from splitting detailed configurations (CI workflows, Percy setup) into separate reference files. No external file references are provided. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Reviewed
Table of Contents
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.