e2e-cucumber-playwright

Use when writing, changing, or reviewing Cucumber and Playwright tests under `e2e/`, including feature files, step definitions, support code, scenario tags, locators, and assertions. Do not use for Vitest, React Testing Library, backend tests, or generic browser automation outside the E2E suite.

Quality

89%

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

Quality

Content

86%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.

A well-structured, lean skill body that routes to real bundled references and lays out a concrete workflow with a validation step. It would reach the top tier with an explicit validate-then-retry feedback loop and one or two inline executable commands.

Suggestions

Add an explicit feedback loop in the workflow (e.g., "if the tagged scenario fails, fix and re-run only that scenario before broadening") to lift workflow clarity.

Inline one concrete command for running a tagged scenario (or a one-line pointer to the exact command shape) so the guidance is directly executable rather than deferred to e2e/AGENTS.md.

Dimension	Reasoning	Score
Conciseness	The body is lean, states project-specific ownership boundaries rather than explaining what Cucumber/Playwright are, and every line earns its place (e.g., the timeout-domain separation caution), matching the lean/efficient level-5 anchor.	5 / 5
Actionability	Provides concrete routing rules mapping decision types to specific reference files and a 6-step numbered workflow, but defers actual executable commands to e2e/AGENTS.md rather than giving copy-paste code, fitting the mostly-executable level-4 anchor.	4 / 5
Workflow Clarity	A clear 6-step sequence with a validation checkpoint in step 6 ("run the narrowest tagged scenario and package checks"), but no explicit error-recovery feedback loop, matching the clear-sequence-with-minor-validation-gaps level-4 anchor rather than level 5.	4 / 5
Progressive Disclosure	Clear overview with two real one-level-deep bundled references, each well-signaled via a routing bullet and markdown link definitions, matching the clear-overview-with-well-signaled-references level-5 anchor.	5 / 5
	Total	18 / 20 Passed

Description

92%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, specific description with explicit trigger guidance and helpful negative boundaries that sharply scope the skill. The only gap is the absence of file-extension synonyms (e.g., .feature) that would round out trigger-term coverage.

Suggestions

Add the .feature file extension and a synonym like "end-to-end tests" to broaden natural trigger terms toward full coverage.

Optionally name a concrete command or artifact type users say out loud (e.g., "run the tagged scenario") to make the trigger phrasing even more natural.

Dimension	Reasoning	Score
Specificity	Lists concrete actions ("writing, changing, or reviewing") plus a comprehensive surface of artifacts ("feature files, step definitions, support code, scenario tags, locators, and assertions"), matching the comprehensive-coverage anchor rather than the minor-gaps anchor at 4.	5 / 5
Completeness	Explicitly answers both what (writing/changing/reviewing Cucumber+Playwright tests and the listed artifacts) and when ("Use when writing, changing, or reviewing...") with concrete triggers plus negative boundaries, matching the level-5 anchor.	5 / 5
Trigger Term Quality	Good natural keyword coverage ("Cucumber and Playwright tests", "feature files", "step definitions", "scenario tags", "E2E suite"), but lacks synonyms and file extensions like ".feature" that the level-5 anchor expects.	4 / 5
Distinctiveness Conflict Risk	Clear niche (Cucumber + Playwright under e2e/) with an explicit "Do not use for Vitest, React Testing Library, backend tests, or generic browser automation" boundary list, giving minimal conflict risk per the level-5 anchor.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: langgenius/dify
Path: .agents/skills/e2e-cucumber-playwright/SKILL.md
Commit: 79effdd

Reviewed: 2 days 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.