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.

70

Quality

88%

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

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 highly actionable, well-structured skill whose eight-step sequence, complete code samples, and correctly split-out CI/Cloud reference make it immediately usable. Its main cost is token redundancy: the marketing-quote Overview and four-fold repetition of the no-`cy.wait(ms)` guidance could be cut roughly in half with no loss.

Suggestions

Cut the Overview's marketing quotes and differentiator bullets - the auto-waiting and time-travel points are already made concretely in Step 3 and Step 7, so the quotes only burn tokens restating what the steps show.

State the no-`cy.wait(ms)` guidance once (in the anti-patterns table) instead of four times across the Overview, Step 3, the table, and the worked example.

Add an explicit validation checkpoint to the "How to use" sequence, e.g. "run `npx cypress run --spec ...` and confirm green locally before wiring Cypress Cloud recording and the CI job", making the feedback loop explicit rather than implicit.

DimensionReasoningScore

Conciseness

The Overview re-quotes Cypress marketing copy ("a next generation front end testing tool built for the modern web" plus three differentiator bullets) that restates auto-waiting and time-travel - concepts Claude already knows and that are repeated in Step 3, Step 7 ("This is Cypress's killer feature"), the anti-patterns table, and the worked example. Mostly efficient but includes unnecessary explanation and could be tightened by collapsing the redundancy.

3 / 5

Actionability

Fully executable throughout: install commands, a complete `cypress.config.ts`, a full `checkout.cy.ts` spec including secret handling via `cy.env()`, typed custom-command scaffolding, run commands with `--spec`/`--browser` flags, and a concrete before/after refactor in the worked example. Copy-paste ready and covers the common cases.

5 / 5

Workflow Clarity

Steps 1-8 are clearly sequenced, and the worked example validates the outcome ("green 20/20 locally" before wiring CI) with a debug feedback path (replay failures in the time-travel GUI). Not 5 because validation checkpoints are implicit rather than explicit - the main "How to use" sequence lacks a called-out "confirm the spec is green before recording to Cloud" step.

4 / 5

Progressive Disclosure

The single bundle file, `references/ci-and-cloud.md`, is real, matches its described contents (Cloud commands + GitHub Actions workflow YAML), is linked with markdown paths in two places, and sits exactly one level deep with CI/Cloud detail appropriately split out of the main file. The body is well-sectioned (numbered steps, worked example, anti-patterns, limitations) and easy to navigate.

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 strong description: third-person, concrete, and comprehensive across install, configure, author, refactor, debug, and CI scale-out, with an explicit use-when clause and boundary guidance for the Cypress Studio edge case. The only weakness is missing a few natural synonyms ("end-to-end", "flaky") and the .cy.ts extension in its trigger vocabulary.

DimensionReasoningScore

Specificity

Lists multiple concrete actions covering the full lifecycle - "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" - with no vague language or gaps in coverage.

5 / 5

Completeness

Explicitly answers both what (the concrete action list) and when ("Use for both greenfield test authoring and improving hand-written specs already in the codebase"), plus boundary guidance ("For automated refactor of raw Cypress Studio recordings specifically, use a dedicated codegen-review pass"). Matches the anchor-5 example pattern exactly.

5 / 5

Trigger Term Quality

Good natural keyword coverage - "Cypress", "E2E tests", "specs", "test authoring", "hand-written specs", "Cypress Cloud", "greenfield" - but a few natural terms users would say are missing: "end-to-end" spelled out, "flaky"/"flake", and the `.cy.ts` file extension. Falls between anchor 4 (good coverage, a few natural terms missing) and 5.

4 / 5

Distinctiveness Conflict Risk

Clear Cypress niche with a distinctive named trigger, and it actively routes the one confusing edge case ("raw Cypress Studio recordings") away to "a dedicated codegen-review pass", minimizing wrong-skill triggering. Only negligible residual overlap with framework-agnostic 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents