CtrlK
BlogDocsLog inGet started
Tessl Logo

playwright-cli

Automate browser interactions, test web pages and work with Playwright tests.

54

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./node_modules/.pnpm/playwright-core@1.59.1/node_modules/playwright-core/lib/tools/cli-client/skill/SKILL.md

The canonical home for this skill is playwright-cli in microsoft/playwright-cli

SKILL.md
Quality
Evals
Security

Quality

Content

87%Scale 1-3

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

This is a well-crafted skill that serves as an excellent CLI reference. It's highly concise, fully actionable with copy-paste ready commands, and has excellent progressive disclosure with clear references to detailed guides. The main weakness is the lack of explicit validation/verification steps in workflows—snapshots are taken but there's no guidance on checking results or handling errors.

Suggestions

Add brief validation guidance to workflow examples, e.g., 'After clicking submit, take a snapshot and verify the expected page/element appears before proceeding'

Consider adding a short troubleshooting or error-handling note (e.g., what to do if a ref is stale or an element isn't found)

DimensionReasoningScore

Conciseness

The content is lean and efficient throughout. It avoids explaining what Playwright is, what browsers are, or how web automation works. Every section is command-focused with no unnecessary prose. The examples are minimal but complete.

3 / 3

Actionability

Every command is concrete, copy-paste ready, and uses real CLI syntax with realistic arguments. The examples section shows complete workflows with actual commands rather than pseudocode or abstract descriptions.

3 / 3

Workflow Clarity

The examples show clear sequences of steps (e.g., form submission: open → snapshot → fill → click → snapshot → close), but there are no explicit validation checkpoints or error recovery steps. For browser automation involving potentially destructive or stateful operations, the lack of 'verify the page loaded' or 'check for errors' steps is a gap.

2 / 3

Progressive Disclosure

Excellent structure with a quick start overview, organized command categories, and a well-signaled 'Specific tasks' section at the bottom linking to 9 reference files for deeper topics. All references are one level deep and clearly labeled.

3 / 3

Total

11

/

12

Passed

Description

32%Scale 1-3

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 identifies the core domain (Playwright browser automation and testing) but lacks specificity in concrete actions and is missing an explicit 'Use when...' clause. It would benefit from more specific capability listing and natural trigger terms that users commonly use when requesting browser automation or end-to-end testing help.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about browser automation, end-to-end testing, Playwright scripts, or web page interaction testing.'

Include more natural trigger term variations such as 'e2e tests', 'end-to-end testing', 'headless browser', 'UI testing', '.spec.ts files', and 'browser scripting'.

List more specific concrete actions like 'navigate pages, click elements, fill forms, capture screenshots, write and debug Playwright test scripts, handle selectors and assertions'.

DimensionReasoningScore

Specificity

Names the domain (browser automation, web testing, Playwright) and some actions ('automate browser interactions', 'test web pages', 'work with Playwright tests'), but the actions are somewhat general rather than listing multiple specific concrete operations like 'click elements, fill forms, take screenshots, assert page content'.

2 / 3

Completeness

Describes what the skill does (automate browser interactions, test web pages, work with Playwright tests) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric should cap completeness at 2, and the 'what' portion is also fairly thin, placing this closer to a 1.

1 / 3

Trigger Term Quality

Includes 'Playwright', 'browser', 'web pages', and 'tests' which are relevant keywords, but misses common variations users might say like 'e2e tests', 'end-to-end testing', 'browser automation', 'web scraping', 'headless browser', '.spec.ts', or 'UI testing'.

2 / 3

Distinctiveness Conflict Risk

Mentioning 'Playwright' specifically helps distinguish it from generic testing or browser skills, but 'automate browser interactions' and 'test web pages' are broad enough to potentially overlap with Selenium, Cypress, or general web testing skills.

2 / 3

Total

7

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
stevenknowswhy/ForhemitComing
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.