Writes Cypress E2E/component tests, configures `cy.intercept()` and `cy.session()`, authors custom commands, and wires CI artifacts. Use when creating E2E specs, component tests, or CI test pipelines. Trigger terms: cypress, e2e, component test, cy.intercept, cy.session
100
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Quality
Discovery
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.
This is an excellent skill description that clearly articulates specific Cypress-related capabilities, provides explicit trigger guidance with a 'Use when' clause and enumerated trigger terms, and is highly distinctive. It uses proper third-person voice and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: writing Cypress E2E/component tests, configuring cy.intercept() and cy.session(), authoring custom commands, and wiring CI artifacts. These are precise, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (writes Cypress tests, configures intercept/session, authors custom commands, wires CI artifacts) and 'when' (explicit 'Use when' clause plus listed trigger terms). | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger terms users would say: 'cypress', 'e2e', 'component test', 'cy.intercept', 'cy.session'. Also includes 'CI test pipelines', 'E2E specs', and 'custom commands' in the body, covering common variations well. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to Cypress testing framework with distinct triggers like 'cy.intercept', 'cy.session', and 'cypress'. Unlikely to conflict with other testing skills (e.g., Jest, Playwright) due to framework-specific terminology. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that efficiently covers Cypress testing patterns with executable examples, a clear workflow with validation steps, and appropriate progressive disclosure. It respects Claude's intelligence by focusing on Cypress-specific patterns and non-obvious best practices rather than explaining basic testing concepts. The only minor issue is the duplicate reference to REFERENCE.md at the end (two consecutive lines pointing to the same file for slightly different reasons), but this is negligible.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what Cypress is or how E2E testing works conceptually. Every section delivers actionable information without padding. The best practices section specifically notes 'Cypress-specific and non-obvious' which shows intentional filtering. | 3 / 3 |
Actionability | Provides fully executable TypeScript code examples for E2E tests and custom commands, concrete bash commands for installation and running, and specific file paths. The examples are copy-paste ready with realistic selectors and assertions. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (install → add data-testid → write → run → CI) with explicit validation checkpoints: 'npx cypress verify' after install, running a single spec as a smoke check after authoring, and inspecting screenshots/videos on failure. The feedback loop for failures is present. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to testing-config.md and REFERENCE.md for CI pipeline examples, advanced configuration, and selector consistency rules. Content is appropriately split between the main skill and reference files. | 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
f5c8508
Table of Contents
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.