CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/saucelabs-automate

Author and run E2E tests on Sauce Labs - cloud grid for cross-browser + real-device testing with W3C WebDriver, Cypress, Playwright, and Appium support. Covers SAUCE_USERNAME + SAUCE_ACCESS_KEY auth, regional hub URLs (us-west-1 / us-east-4 / eu-central-1), W3C capabilities, sauce:options dict (build, name, screenResolution, tunnelName), Sauce Connect Proxy for internal-environment testing. Use for cross-browser regression with Sauce Labs as the cloud grid; complements BrowserStack + LambdaTest as alternative providers.

76

Quality

95%

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

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, highly actionable reference skill with executable code throughout and clean one-level external references; the main gap is that the Sauce Connect workflow presents the wait-for-ready step abstractly rather than with a concrete bounded-wait validation checkpoint.

Suggestions

Add a concrete bounded-wait step for tunnel readiness in the Sauce Connect workflow (e.g. a poll loop with a timeout that fails the suite), instead of the abstract 'wait-for-ready' arrow.

Show an explicit validate-before-quit checkpoint in the session-status workflow so the 'always update status before quit' rule is demonstrated as a feedback loop, not just stated.

Consider an explicit timeout/abort step for the ephemeral CI tunnel lifecycle (spawn -> bounded-wait -> run -> terminate) so the failure path is as concrete as the happy path.

DimensionReasoningScore

Conciseness

The body is dense technical reference - executable bash/JSON/Python/YAML, a capabilities table, and an anti-patterns table - with no exposition of concepts Claude already knows (e.g. no 'what is W3C WebDriver'); the two-sentence overview is appropriately scoped rather than padded.

3 / 3

Actionability

Provides copy-paste-ready executable artifacts throughout - export auth env vars, regional hub URLs, a full W3C capabilities JSON, a working Python Remote() example, the `sc` tunnel command with flags, a curl REST call, and a GitHub Actions matrix YAML.

3 / 3

Workflow Clarity

Sections are sequenced (auth -> hub URLs -> capabilities -> running -> tunnel -> parallel limits) but the fragile tunnel operation is only gestured as 'spawn -> wait-for-ready -> run tests -> terminate' with no concrete bounded-wait validation checkpoint shown in the workflow, even though the anti-patterns table calls out the missing-timeout risk; per the rubric, missing validation in a fragile op caps this at 2.

2 / 3

Progressive Disclosure

Single self-contained file with clear section organization and a dedicated References block pointing to one-level-deep external docs (Sauce config options, Sauce Connect 5, Selenium options) - no nested references and easy navigation.

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 strong, concrete description that names specific capabilities, lists natural trigger terms, and gives an explicit 'Use for' clause while clearly distinguishing Sauce Labs from sibling provider skills.

DimensionReasoningScore

Specificity

Quotes multiple concrete actions - 'Author and run E2E tests', 'cross-browser + real-device testing', 'Sauce Connect Proxy for internal-environment testing' - matching the score-3 anchor that lists several specific actions.

3 / 3

Completeness

Explicitly states what it does ('Author and run E2E tests on Sauce Labs...') and when to use it via an explicit 'Use for cross-browser regression with Sauce Labs as the cloud grid' trigger, satisfying both what AND when.

3 / 3

Trigger Term Quality

Natural user-facing terms are well covered - 'E2E tests', 'cross-browser regression', 'real-device testing', 'Sauce Labs', 'Sauce Connect Proxy' - phrases a user would actually say when needing this skill.

3 / 3

Distinctiveness Conflict Risk

The niche is sharply scoped to Sauce Labs and it explicitly distinguishes siblings ('complements BrowserStack + LambdaTest as alternative providers'), so it is unlikely to trigger for the wrong skill.

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