CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/chromatic-visual-regression-testing

Authors and runs Chromatic visual tests on Storybook, Playwright, or Cypress projects via the `chromatic` CLI; configures baselines, TurboSnap, UI Review, and CI gating; reads exit codes for change-vs-error classification. Use when the project ships visual regression coverage to Chromatic Cloud.

77

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A high-quality, actionable reference: executable commands, dense tables, and well-sourced external citations with no padding. The main weakness is progressive disclosure — a long single-file skill carrying full reference tables inline instead of offloading them to a bundle file.

Suggestions

Move the full CLI flag table and the exit-code table into a references file (e.g. references/cli-reference.md) and summarize only the most common flags inline, keeping SKILL.md as an overview.

Add a one-line pointer near the top of the flag/exit-code sections (e.g. "See references/cli-reference.md for the complete table") so the offloaded detail is clearly signaled.

Consider extracting the TurboSnap bundler-requirements and full-rebuild-triggers detail into the same reference file to shorten the body further.

DimensionReasoningScore

Conciseness

Lean and information-dense — it cites external docs via reference links instead of reproducing them and does not re-explain concepts Claude already knows (Storybook, git, PRs); every section earns its place.

3 / 3

Actionability

Provides copy-paste-ready, executable guidance: install command, `npx chromatic --project-token`, a full CI workflow YAML, a `chromatic.config.json` with schema URL, and concrete flag/exit-code tables.

3 / 3

Workflow Clarity

A clear install→connect→author→run→CI sequence with an explicit validation checkpoint (exit-code classification and CI gate logic); operations are non-destructive, so the missing retry loop does not cap the score at 2.

3 / 3

Progressive Disclosure

Sections are well-organized and external-doc references are clearly signaled (reference-style links plus a References section), but substantial reference material — the full flag table and full exit-code table — is kept inline in a ~220-line single file with no bundle files, rather than split into a one-level-deep reference file.

2 / 3

Total

11

/

12

Passed

Description

100%

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 description: concrete capabilities, natural trigger terms, an explicit 'Use when' clause, and a distinctive niche. It mirrors the rubric's good examples (actions + trigger) with no padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Authors and runs Chromatic visual tests", "configures baselines, TurboSnap, UI Review, and CI gating", "reads exit codes for change-vs-error classification" — matching the multi-action anchor rather than the single-domain score 2.

3 / 3

Completeness

Explicitly answers both what (author/run/configure/read exit codes) and when via the "Use when the project ships visual regression coverage to Chromatic Cloud" clause; not the score-2 case where 'when' is only implied.

3 / 3

Trigger Term Quality

Covers natural terms a user would say ("Chromatic visual tests", "Storybook, Playwright, or Cypress", "visual regression coverage", "Chromatic Cloud", "TurboSnap") with common framework variations, not just jargon.

3 / 3

Distinctiveness Conflict Risk

A clear niche (Chromatic visual regression on Storybook/Playwright/Cypress) with distinct triggers unlikely to fire for unrelated skills; uses correct third-person voice with no first/second-person penalty.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents