Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Playwright Cli Pointer

ASecurity

Point to Microsoft's playwright-cli and its skill, and explain when to use it. Use when asked how to install playwright-cli, how to verify a page in a real browser at mobile and desktop widths, or what handles the verification stage of the design pipeline. Produces the install commands, the Node prerequisite, a screenshot routine for both widths, an optional interface guidelines audit step, and credit to the author with a link. Contains no upstream skill content.

1,417 stars
0 votes
0 copies
0 views
Added 10/1/2026
ai-agentsbashnodegit

Works with

cli

Security Analysis

A96/100
mediumInstalls packages at runtime which could introduce malicious dependencies

Pro shows the line behind each finding and how to fix it

Scanned 10/1/2026

$npx -y skills add mohitagw15856/pm-claude-skills --skill playwright-cli-pointer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Playwright Cli Pointer?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Playwright Cli Pointer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mohitagw15856-playwright-cli-pointer-pm-claude-skills/badge)](https://www.skillsdirectory.com/skills/mohitagw15856-playwright-cli-pointer-pm-claude-skills)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: playwright-cli-pointer
description: "Point to Microsoft's playwright-cli and its skill, and explain when to use it. Use when asked how to install playwright-cli, how to verify a page in a real browser at mobile and desktop widths, or what handles the verification stage of the design pipeline. Produces the install commands, the Node prerequisite, a screenshot routine for both widths, an optional interface guidelines audit step, and credit to the author with a link. Contains no upstream skill content."
version: 1.0.0
---

# Playwright CLI (pointer)

This is a pointer, not a copy. It tells you when Microsoft's `playwright-cli` is the right tool, how to install it from the source, and who to credit. The tool and its skill live upstream and are not reproduced here.

## What This Skill Produces

- **A recommendation**: whether the upstream tool fits the task in front of you
- **The install commands** and the prerequisite
- **A verification routine**: mobile and desktop widths, a screenshot per step, fix and re-check
- **An optional audit step** using Vercel's web-design-guidelines skill
- **Attribution**: author, licence and link

## Required Inputs

Ask for these if not provided:
- **The address of the page**, usually a local dev server
- **The main flow to walk through**, step by step
- **Where screenshots should be saved**

## Framework: When to Use It

Use it when:
- A page has been built and critiqued and now needs to be seen rendered
- You need screenshots at more than one width as evidence
- You want the assistant to drive a real browser from the command line

Look elsewhere when:
- Nothing is built yet. Start at stage 1 of the pipeline.
- You want a design opinion and not a rendering check. Use `impeccable-pointer`.
- You already have a working browser tool in the session. Use that, and keep the routine below.

## Install

Prerequisite: Node.js 18 or newer.

```bash
npm install -g @playwright/cli@latest
playwright-cli install --skills
```

Confirm the install:

```bash
playwright-cli --help
```

## Verification Routine

1. Open the page at a mobile width, 390 by 844. Take a screenshot.
2. Walk the main flow. Take a screenshot at each step.
3. Resize to a desktop width, 1440 by 900. Repeat steps 1 and 2.
4. Read the screenshots. List what is wrong: overflow, wrapping, cramped tap targets, broken hierarchy.
5. Fix, then take every screenshot again. Stop when a full pass finds nothing.

Name files so passes can be compared, for example `pricing-mobile-step2-pass1.png`. The upstream README documents the `open`, `resize` and `screenshot` commands used here.

## Optional: Interface Guidelines Audit

After the screenshots pass, you can run Vercel's `web-design-guidelines` skill as a final audit of the code against interface best practice, covering areas such as accessibility, focus states and forms.

```bash
npx skills add vercel-labs/agent-skills --skill web-design-guidelines
```

It is optional and it comes last. It reviews code, so it complements the browser check and does not replace it.

## Output Format

### Pointer: playwright-cli
1. **Fit**: use it or not, in one sentence, with the reason
2. **Prerequisite**: Node version present
3. **Install**: the two commands
4. **Routine**: widths, steps, file naming
5. **Optional audit**: offered, accepted or declined
6. **Credit**: author, licence, link

## Credit

- **Project**: playwright-cli
- **Author**: Microsoft
- **Licence**: Apache 2.0
- **Link**: https://github.com/microsoft/playwright-cli
- **Optional audit**: web-design-guidelines by Vercel, https://github.com/vercel-labs/agent-skills. The README states MIT; the repository has no separate licence file, so check before redistributing.
- **Checked**: 2026-09-28

## Quality Checks
- [ ] Both install commands were given exactly as written above
- [ ] Screenshots were taken at both a mobile and a desktop width
- [ ] Screenshots were taken again after every fix
- [ ] The authors were credited with links
- [ ] No upstream skill text was reproduced
- [ ] The audit step was presented as optional

## Anti-Patterns
- **Checking one width only.** Most layout failures appear at the width you did not open.
- **Fixing without re-checking.** A fix at desktop width often breaks mobile.
- **Reporting "verified" from the code alone.** No screenshot, no verification.
- **Running the audit in place of the browser check.** They test different things.

## Example Trigger Phrases
- "How do I install playwright-cli with its skill?"
- "Check this page in a real browser at mobile and desktop widths."
- "What handles the verification stage of the design pipeline?"
- "Screenshot every step of the signup flow and fix what is broken."

---

Part of the pm-design-taste bundle in the library at https://github.com/mohitagw15856/pm-claude-skills.

Attribution

mohitagw15856mohitagw15856
View sourceSee grades on GitHubMore from mohitagw15856 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →