CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

playwright-testing

Comprehensive Playwright E2E testing framework for browser automation. Use when setting up tests, writing E2E scenarios, debugging test failures, configuring CI/CD pipelines, or running browser automation on WSL2.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/playwright-testing/SKILL.md

The canonical home for this skill is playwright-testing in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

63%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, largely executable reference whose main value is the project-specific material (WSL2 wiring, full config, CI workflow). It is dragged down by sections restating well-known Playwright basics, an incomplete WSL2 Chrome wiring story, and half of its referenced bundle files being missing, which breaks the progressive-disclosure navigation it advertises.

Suggestions

Remove or move to references/best-practices.md the sections that restate Playwright basics Claude already knows (the Overview "Key Advantages" list, the locator-priority ladder, the auto-wait BAD/GOOD explainer), keeping only the project-specific config and WSL2 material inline.

Create the missing referenced files (references/setup-guide.md, references/ci-cd-integration.md, scripts/generate-test.ts) or delete the dangling references — half the advertised navigation targets currently do not exist.

Complete the WSL2 Option 1 wiring: CHROME_BIN is exported but never used, so show the playwright.config.ts executablePath/channel setting (or a launch script) that actually makes Playwright launch Windows Chrome.

DimensionReasoningScore

Conciseness

The bulk is dense, runnable code, but several sections re-teach Playwright basics Claude already knows: the Overview's marketing claims ("state-of-the-art browser automation framework for 2025", "35-45% faster parallel execution"), the locator-priority ladder, the auto-wait BAD/GOOD explainer, and the VS Code extension bullet list — plus a time-sensitive "recommended testing framework for 2025" closer. Mostly efficient with some unnecessary explanation, rather than several padded sections.

3 / 5

Actionability

Nearly all guidance is copy-paste ready: init commands, a full playwright.config.ts, page objects, the WSL2 wrapper script, a GitHub Actions workflow, and a commands table. Falls short of fully executable because the chromium.connectOverCDP snippet is shown at top level outside any async context, and CHROME_BIN is exported but never wired into a Playwright config, leaving the recommended WSL2 option incomplete.

4 / 5

Workflow Clarity

Two clear sequences are present (numbered Quick Start and the four-step "Creating E2E Tests" workflow) with concrete run/debug commands at each stage. Not 5 because there are no explicit validation checkpoints (e.g., verify the install or confirm the browser launches) and error recovery is only implicitly covered by the debugging section; no destructive/batch cap applies.

4 / 5

Progressive Disclosure

Sections are well organized with clearly signaled one-level-deep references, but scored against the actual bundle, 3 of the 6 referenced files (references/setup-guide.md, references/ci-cd-integration.md, scripts/generate-test.ts) do not exist, so half the navigation paths are broken. Broken reference targets are a structural gap beyond the "minor organization gaps" of the next anchor.

3 / 5

Total

14

/

20

Passed

Description

70%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 solid description with an explicit and multi-trigger "Use when" clause built around natural user phrases. Its main weakness is that the capability statement is a padded label ("Comprehensive... framework") rather than concrete actions, which keeps specificity and completeness just below the top anchors.

DimensionReasoningScore

Specificity

The capability statement is only a domain label — "Comprehensive Playwright E2E testing framework for browser automation" — where "Comprehensive" is fluff; concrete activities like "setting up tests", "debugging test failures", and "running browser automation on WSL2" appear solely as trigger conditions rather than stated capabilities, matching the anchor for domain plus some concrete actions but not comprehensive.

3 / 5

Completeness

Both parts are present: a "what" ("Playwright E2E testing framework for browser automation") and an explicit "Use when..." clause with five concrete triggers. Not 5 because the "what" is a vague label ("Comprehensive... framework") rather than a list of concrete capabilities.

4 / 5

Trigger Term Quality

Natural phrases users would actually say are well covered ("setting up tests", "E2E scenarios", "debugging test failures", "CI/CD pipelines", "browser automation", "WSL2"), but common variations such as "end-to-end tests", "browser testing", or "flaky tests" are missing, so it falls short of comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Playwright is a named, specific tool with a clear niche, so conflict risk is low; however "configuring CI/CD pipelines" is an unscoped trigger that could overlap with generic CI/deployment skills, leaving minor overlap risk with closely related skills.

4 / 5

Total

15

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

15

/

16

Passed

Repository

fernandezbaptiste/Skrillz

Path

.claude/skills/playwright-testing/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.