mcpField
U
ui-test-selenium

ui-test-selenium

github.com/naodengTesting & quality28541 installsUpdated today
Repository

About ui-test-selenium

A prompt-based skill for planning and reviewing Selenium UI tests. It guides users to account for browser and driver compatibility, observable waits, rerender handling, and cleanup while marking assumptions and missing context.

Key features

  1. 01Selenium test planning
  2. 02Version and configuration checks
  3. 03Observable-condition waits
  4. 04Rerender and stale-element handling
  5. 05Session isolation and cleanup

Use cases

  1. 01Drafting a Selenium UI test plan
  2. 02Diagnosing browser and driver conflicts
  3. 03Reviewing parallel test isolation
  4. 04Checking failure and cleanup behavior

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/naodeng/awesome-qa-skills --skill ui-test-selenium

After installing, type/ui-test-seleniumin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

README.md
agents/
openai.yaml
evals/
eval.yaml
evals/cases/
basic-success.yaml
domain-method-regression.yaml
edge-incomplete-input.yaml
edge-scope-boundary.yaml
evals/fixtures/
check_domain_decisions.py
check-domain-decisions.sh
domain-oracle.json
evals/fixtures/checkout-app/
checkout.py
index.html
README.md
receipt.html
server.mjs
examples/
sample-context.md
output-templates/
template-markdown.md
prompts/
ui-test-selenium.md
references/
domain-decision-example.md
framework-spec.md
setup-and-ci.md
scripts/
run-tests.sh

Details

From the project README

Selenium UI Testing (EN)

Chinese version： See the corresponding Chinese skill.

When to Use

  • Need outputs that should land in a Selenium UI testing workflow.
  • The project already uses Selenium or wants Selenium-ready planning.

Output Format Options

Markdown by default unless the request explicitly asks for another format.

How to Use

  1. Open prompts/ui-test-selenium.md and use it as the main prompt.
  2. Add the real project context: scope, environment, constraints, risks, dependencies, and expected deliverable.
  3. If the input is incomplete, return a usable first version and mark missing information and assumptions.

Reference Files

  • When calibrating domain outcomes, valid controls, or evidence gaps, read references/domain-decision-example.md for sanitized input, per-item oracles, and reproducible calculations.

  • prompts/ui-test-selenium.md: main prompt for this skill.

  • references/framework-spec.md: tool-specific structure and coverage notes.

  • references/setup-and-ci.md: setup, execution, and CI notes.

  • examples/sample-context.md: sample request context.

  • scripts/run-tests.sh: lightweight local execution entry point.

Domain Execution Essentials

  1. Fix Selenium/binding/browser/driver/Grid versions, capabilities, and runner. Produce compatible config/POM; do not invent Grid topology and diagnose version conflicts first.
  2. Explicitly wait on observable interactability, business state, window, or URL conditions. Presence/visibility is not business readiness; avoid mixed implicit/explicit waits and universal fixed sleeps.
  3. After rerender/stale references re-find by stable locator and wait for fresh state. Bounded retries follow supplied policy; blind payment replay can duplicate effects.
  4. Isolate accounts/business keys per parallel session. Use try/finally driver.quit with screenshots/logs/session/original failures. Rerender, business-failure, and exception controls verify cleanup and nonzero propagation.

Common Pitfalls

  • Do not use it with vague scope and no context.
  • Do not treat every area as equally important.
  • Do not skip assumptions and missing information.

Best Practices

  • Start from the prompt file, then add only the context that matters.

  • Keep the output risk-driven and executable.

  • If the request is incomplete, return a usable first version and mark gaps.

  • To verify generated business assertions, failure propagation or isolation, read evals/fixtures/checkout-app/README.md and its local good/bug/timeout controls; execute only when a run is requested.

Comments

Markdown supported