CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/responsive-breakpoint-runner

Produces a single breakpoint-matrix report (rows = pages/stories, columns = viewports) across Percy, Chromatic, Playwright snapshots, or Storybook test-runner. Routes per-engine viewport syntax, runs each, and aggregates the results into one cross-breakpoint view. Use when the team needs one unified pass/fail view across three or more viewport widths instead of separate per-engine or per-breakpoint reports. The matrix-view output is the distinguishing trait: it dispatches to playwright-snapshots (and the other engines) rather than replacing any single-engine skill.

75

Quality

94%

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

85%

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 and actionable with a clear sequenced workflow, explicit validation gate, and clean one-level-deep progressive disclosure to a real reference file. Its only weakness is repetition — the matrix table, $GITHUB_STEP_SUMMARY piping, and visual-baseline-gate handoff each appear multiple times and could be consolidated.

Suggestions

Render the markdown matrix table once (in 'Producing the unified report') and reference it from the worked example and 'How to use' steps rather than duplicating it.

State the $GITHUB_STEP_SUMMARY / visual-baseline-gate handoff once in 'Producing the unified report' and link back to it instead of repeating the instruction in the worked example and 'How to use'.

Collapse the repeated 'visual-baseline-gate consumes the row shape' mentions into a single sentence in the unified-report section.

DimensionReasoningScore

Conciseness

Mostly efficient and free of concept-explaining padding, but the markdown matrix table is rendered twice (worked example and 'Producing the unified report'), the $GITHUB_STEP_SUMMARY piping instruction is repeated three times, and the visual-baseline-gate handoff is restated repeatedly, so it could be tightened.

2 / 3

Actionability

Provides concrete, copy-paste-ready artifacts — the row-shape JSON, the markdown matrix table, and the CI artifact-upload YAML — with engine-specific executable syntax one reference hop away, which is appropriate for a dispatcher skill.

3 / 3

Workflow Clarity

A clear 7-step 'How to use' sequence reinforced by a worked example, with an explicit validation gate (step 7 feeds rows to visual-baseline-gate) and CI artifact upload; the red-cell matrix pinpoints which breakpoint regressed for recovery.

3 / 3

Progressive Disclosure

The body is an overview that delegates per-engine viewport syntax to the verified references/engine-viewport-syntax.md file via clearly signaled, one-level-deep links, keeping dispatch logic and the unified row shape inline.

3 / 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.

The description is strong across all dimensions: it states concrete actions, gives an explicit 'Use when' trigger with natural keywords, and clearly distinguishes itself as a dispatcher that composes rather than replaces per-engine skills. Voice is correctly third person throughout.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'Produces a single breakpoint-matrix report', 'Routes per-engine viewport syntax', 'runs each', 'aggregates the results into one cross-breakpoint view' — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers both what ('Produces a single breakpoint-matrix report... aggregates the results') and when ('Use when the team needs one unified pass/fail view across three or more viewport widths').

3 / 3

Trigger Term Quality

Covers natural terms a user would say — 'breakpoint', 'viewport widths', 'pass/fail view across three or more viewport widths' — plus the named engines (Percy, Chromatic, Playwright, Storybook test-runner).

3 / 3

Distinctiveness Conflict Risk

Explicitly stakes a clear niche — 'The matrix-view output is the distinguishing trait: it dispatches to playwright-snapshots (and the other engines) rather than replacing any single-engine skill' — unlikely to trigger for a per-engine skill.

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