CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/cloud-grid-e2e

Author and run E2E tests on a cloud browser grid - BrowserStack Automate, Sauce Labs, or LambdaTest. All three follow one pattern: username + access-key env vars, a W3C WebDriver hub URL, a vendor options dict inside the capabilities (bstack:options / sauce:options / LT:Options), a local tunnel binary for internal apps, session pass/fail reporting, and a CI matrix throttled to the plan's parallel-session limit. Worked example uses BrowserStack; per-vendor deltas live in references/. Use for cross-browser regression on real devices + browsers beyond the engines bundled on the local machine - distinct from a local matrix runner and from self-hosted Selenium Grid.

72

Quality

90%

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

86%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 executable examples and good progressive disclosure into verified reference files. The main gap is the absence of explicit numbered validation/feedback-loop checkpoints in the batch CI and tunnel workflows.

Suggestions

Add an explicit numbered 'validate → fix → retry' feedback loop to the CI wiring and tunnel sections (e.g., wait-for-ready with bounded timeout, assert tunnel is up, fail fast on session-status=failed) to strengthen workflow clarity for this batch operation.

Tighten the vendor-selection paragraph and a few anti-pattern rows that restate guidance already given in 'How to use' to reclaim tokens.

Surface the per-vendor status-reporting incantations (sauce:job-result, lambda-status) as a small inline table in the worked example so the cross-vendor delta is visible without leaving SKILL.md.

DimensionReasoningScore

Conciseness

Largely lean and assumes Claude's competence (no padding about what Selenium/WebDriver is); the isomorphic-vendor overview and comparison table earn their place, though a few prose passages (e.g. the vendor-selection paragraph and some anti-pattern elaboration) could be trimmed.

4 / 5

Actionability

Provides complete, copy-paste-ready executable code: a full Python Selenium+BrowserStack driver setup, bash tunnel daemon commands, and a GitHub Actions matrix YAML, plus concrete status-reporting one-liners for each vendor.

5 / 5

Workflow Clarity

The 'How to use' section gives a clear 6-step sequenced pattern and the anti-patterns table supplies the key validation checkpoints (bounded wait, report status before quit, match worker pool to plan). However the CI/tunnel flows lack an explicit numbered 'validate → fix → retry' feedback loop, leaving a minor checkpoint gap for a batch operation.

4 / 5

Progressive Disclosure

The body is a concise overview with per-vendor deltas correctly pushed to three one-level-deep reference files (all verified present and linked twice — in Overview and References), plus clearly signaled sibling-skill composition.

5 / 5

Total

18

/

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, specific description that answers what and when clearly and carves out a distinct niche from sibling skills. Trigger-term coverage is very good but slightly short of fully comprehensive natural-language phrasings.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and components — 'Author and run E2E tests', 'username + access-key env vars', 'W3C WebDriver hub URL', 'vendor options dict inside the capabilities', 'local tunnel binary', 'session pass/fail reporting', 'CI matrix throttled to the plan's parallel-session limit' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (author and run E2E tests on a cloud browser grid with the enumerated pattern) and 'when' ('Use for cross-browser regression on real devices + browsers beyond the engines bundled on the local machine') with concrete trigger phrasing.

5 / 5

Trigger Term Quality

Includes natural terms a user would say — 'E2E tests', 'cross-browser regression', 'real devices', vendor names BrowserStack/Sauce Labs/LambdaTest — but is missing a few common natural phrasings like 'automated browser testing' or 'run tests on <vendor>'.

4 / 5

Distinctiveness Conflict Risk

Names three specific vendors and explicitly carves out its niche as 'distinct from a local matrix runner and from self-hosted Selenium Grid', giving a clear niche with minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Reviewed

Table of Contents