CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/playwright-testing

Authors and remediates Playwright E2E tests across Chromium, Firefox, WebKit - `npm init playwright@latest` scaffolding, `playwright.config.ts` browser projects, accessibility-first locators (`getByRole`/`getByLabelText`) to replace brittle CSS selectors, web-first assertions to eliminate `waitForTimeout` flakiness, Page Object pattern, trace viewer debugging, sharded parallel execution with merged HTML reporting, and GitHub Actions CI integration. Use for new test authoring, flakiness remediation, and CI setup; for reviewing codegen output specifically, use a dedicated codegen-review pass.

73

Quality

92%

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

80%

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

A tight, highly actionable Playwright skill: executable code and commands at every step with no padding. The only gap is the absence of explicit validation/retry feedback loops for the sharded CI and browser-install steps, which caps workflow clarity.

Suggestions

Add an explicit validate->fix->retry loop after `npx playwright test` in CI (e.g., re-run only failures, or check the report and re-run before failing the job) to satisfy the batch-operation feedback-loop guideline.

Include a quick verification step after `npx playwright install --with-deps` (e.g., confirm browsers cached via `npx playwright --version` / a smoke `--list`) so a missing-deps failure is caught early.

For sharded execution, note how to confirm all shards merged into the final HTML report before declaring success, closing the batch-operation checkpoint gap.

DimensionReasoningScore

Conciseness

Lean and action-oriented throughout — no beginner explanations of what Playwright or browsers are; each section is commands or code with brief, purpose-justifying notes. Every token earns its place.

3 / 3

Actionability

Every step ships executable, copy-paste-ready commands and complete TypeScript/YAML configs (scaffold, locators, Page Object, playwright.config, sharding, CI workflow), not pseudocode.

3 / 3

Workflow Clarity

The 9-step sequence is clear and well-ordered, but operations with failure-prone or batch character (sharded CI runs, browser install, trace debugging) lack explicit validate->fix->retry checkpoints; guidelines state missing validation in batch/destructive operations caps this at 2.

2 / 3

Progressive Disclosure

No bundle files exist, so the body relies on well-organized sections plus a one-level-deep external link (pw-intro) and clearly-labeled cross-skill references in Limitations/References; for a self-contained skill this is well-structured and easy to navigate.

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.

The description is specific, trigger-rich, complete (what + when), and clearly distinct from sibling skills with explicit handoff guidance for codegen review. It is on the longer side but the density of concrete terms earns their place rather than reading as padding.

DimensionReasoningScore

Specificity

Lists many concrete actions — scaffolding, browser project config, accessibility-first locators, web-first assertions, Page Objects, trace viewer, sharded execution, and CI integration — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what (the enumerated authoring/remediation/CI capabilities) and when ('Use for new test authoring, flakiness remediation, and CI setup; for reviewing codegen output specifically, use a dedicated codegen-review pass').

3 / 3

Trigger Term Quality

Natural terms users would say are well covered: 'new test authoring', 'flakiness remediation', 'CI setup', 'E2E tests', plus concrete tool names like Playwright, Chromium/Firefox/WebKit.

3 / 3

Distinctiveness Conflict Risk

Clearly scoped to Playwright E2E with distinct triggers, and explicitly routes codegen review elsewhere, reducing overlap with sibling skills.

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