CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/selenium-testing

Authors Selenium WebDriver tests in any of its 6+ supported languages (Java, Python, JavaScript, C#, Ruby, Kotlin, PHP) - picks the appropriate language binding, configures WebDriver per browser, uses `By.*` locators with the team's accessibility-first preference where supported, runs locally + via Selenium Grid for distributed execution, parses results to JUnit XML. Use for legacy Selenium-locked stacks; new projects pick Playwright or Cypress.

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

High

Do not use without reviewing

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.

A well-structured, highly actionable Selenium skill with executable code, explicit verification checkpoints, and a clean one-level reference split. The main weakness is time-sensitive pinned versions and a dated '2026+' clause not isolated in a deprecated section, which costs conciseness.

Suggestions

Move pinned dependency versions (selenium-java 4.27.0, webdrivermanager 5.9.2) into a dedicated, clearly labeled versions block or note them as examples-of-the-moment so they don't silently rot the install step.

Reframe 'For new projects in 2026+' as an evergreen recommendation (e.g. 'for new projects, prefer Playwright or Cypress') to avoid the date becoming stale guidance.

Consider moving the locator-strategy table or the Grid/CI YAML into the existing references/ file to keep SKILL.md's overview even leaner now that the one-level reference pattern is established.

DimensionReasoningScore

Conciseness

Mostly lean and assumes Claude's competence (no 'what is Selenium' filler, tight steps), but pinned versions (selenium-java 4.27.0, webdrivermanager 5.9.2) and the 'For new projects in 2026+' date are time-sensitive and not isolated in a deprecated section, which the guidelines penalize. Not a 3 because of that explicit time-sensitivity demerit; not a 1 because the body is efficient rather than padded.

2 / 3

Actionability

Fully executable, copy-paste-ready artifacts: pom.xml dependencies, a complete Java JUnit test class, a docker-compose grid file, GitHub Actions YAML, and a concrete locator-strategy table. Not a 2 — nothing here is pseudocode or missing key details.

3 / 3

Workflow Clarity

Steps 1-7 are clearly sequenced and include explicit validation checkpoints with error recovery: 'Verify: `curl http://localhost:4444/status` reports ready:true ... if not, the hub or nodes haven't registered' and the surefire-reports empty-directory diagnostic. Not a 2 because validation is explicit, not implicit.

3 / 3

Progressive Disclosure

SKILL.md is an overview; the only bundle file, references/language-bindings.md, is referenced once via a clearly signaled one-level-deep link ('[references/language-bindings.md](references/language-bindings.md)') and verified to contain the Python/C# examples. Content is appropriately split and navigable. Not a 2 — the reference is real, shallow, and well signaled.

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.

A dense, specific description that names concrete capabilities, an explicit use-when trigger, and a clear niche with routing guidance to avoid conflicts. Voice is third-person ('Authors ...') with no first/second-person slippage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'picks the appropriate language binding, configures WebDriver per browser, uses `By.*` locators ... runs locally + via Selenium Grid ... parses results to JUnit XML' — matching the score-3 anchor of multiple specific concrete actions.

3 / 3

Completeness

Clearly answers what (authors/tests across 6+ bindings, locators, grid, JUnit XML) and when via the explicit trigger 'Use for legacy Selenium-locked stacks; new projects pick Playwright or Cypress.'

3 / 3

Trigger Term Quality

Natural Selenium triggers a user would say are well covered: 'Selenium WebDriver tests', 'Selenium Grid', 'legacy Selenium-locked stacks', plus contrast terms 'Playwright or Cypress'. Not a 2 because coverage goes beyond a single label to the workflow vocabulary users actually invoke.

3 / 3

Distinctiveness Conflict Risk

Clear niche (Selenium WebDriver) with a distinct trigger scoping it to legacy/locked stacks and explicitly routing new projects to Playwright/Cypress, making misfires unlikely.

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