CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/cypress-testing

Authors and improves Cypress E2E tests - installs Cypress, configures `cypress.config.ts`, authors `cy.*` command chains, refactors existing specs (`cy.wait(ms)` sleeps into assertions, repeated flows into `cy.session` custom commands), and debugs with the time-travel GUI; Cypress Cloud for parallel runs and recording. Use for both greenfield test authoring and improving hand-written specs already in the codebase. For automated refactor of raw Cypress Studio recordings specifically, use a dedicated codegen-review pass.

88

Quality

88%

Does it follow best practices?

Impact

Average score across 10 eval scenarios

SecuritybySnyk

High

Do not use without reviewing

Overview
Quality
Evals
Security
Files

Quality

Content

78%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, highly actionable skill body with good progressive disclosure via a single real reference file. The main weakness is marketing-quote padding in the Overview and a missing explicit validation checkpoint in the run workflow.

Suggestions

Trim the Overview blockquotes of Cypress marketing language ('next generation front end testing tool', the time-travel/auto-wait/reliability blurbs) to just the differentiators Claude can't infer, or fold them into the relevant step.

Add an explicit verify/validate checkpoint in the run step (e.g. 'After `npx cypress run`, confirm all specs pass before recording to Cypress Cloud; on failure, replay in `cypress open` and fix the failing assertion').

Consolidate the Step 7 time-travel explanation with the earlier automatic-waiting note to avoid re-explaining the same feature.

DimensionReasoningScore

Conciseness

Mostly efficient with executable code, but the Overview blockquotes Cypress marketing copy ('next generation front end testing tool', time-travel/auto-wait blurbs) and Step 7 re-explains the time-travel feature, padding that Claude could infer.

3 / 5

Actionability

Copy-paste ready throughout: install commands, a full cypress.config.ts, a complete checkout spec, a cy.session custom command, and CLI run flags cover the common cases.

5 / 5

Workflow Clarity

A clear 7-item sequence expanded into Steps 1-8 with executable commands and a verify-green worked example, but the run step (Step 6) lacks an explicit validate/checkpoint gate.

4 / 5

Progressive Disclosure

SKILL.md is an overview with CI/Cloud operational detail split into references/ci-and-cloud.md, referenced clearly twice and confirmed to exist as a real one-level-deep file.

5 / 5

Total

17

/

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 highly specific, well-triggered description that covers what it does, when to use it, and where it does NOT apply. Trigger-term coverage is strong but stops just short of comprehensive synonyms.

DimensionReasoningScore

Specificity

Lists seven-plus concrete actions with named APIs ('installs Cypress, configures `cypress.config.ts`, authors `cy.*` command chains, refactors ... `cy.wait(ms)` sleeps into assertions, repeated flows into `cy.session` custom commands'), matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly answers both what ('Authors and improves Cypress E2E tests') and when ('Use for both greenfield test authoring and improving hand-written specs'), with concrete trigger phrases and boundary steering.

5 / 5

Trigger Term Quality

Includes natural terms users would say ('Cypress E2E tests', 'Cypress', 'specs', 'cy.*') plus the product name, but lacks broader synonyms/file extensions needed for a 5.

4 / 5

Distinctiveness Conflict Risk

Niched to a named tool with explicit boundary guidance ('For automated refactor of raw Cypress Studio recordings specifically, use a dedicated codegen-review pass'), minimizing overlap with sibling E2E skills.

5 / 5

Total

19

/

20

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