playwright
/playwright
Capture a screenshot of a URL or local page and load it into context for a visual check. Use when asked to check visually, use playwright, screenshot a page, see or look at the design yourself, or verify a layout on desktop and mobile widths.
- Author
- kovrichard ↗
- Repository
- portable-agent-layer ↗
- Licence
- MIT
- Last repository change
- 23.10.2026
Assessment and security
- Files in this package
- 3
- Scripts
- 2
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 23.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
- 2 scripts in this package. Review them before installing, as Claude may execute them.
Scripts: tools/shot-lib.ts, tools/shot.ts
What it does and when to use it
Capture a screenshot of a URL or local page and load it into context for a visual check. Use when asked to check visually, use playwright, screenshot a page, see or look at the design yourself, or verify a layout on desktop and mobile widths.
Arguments
/playwright <url> [--viewport WxH] [--full-page] [--selector <css>]
Original author description
Capture a screenshot of a URL or local page and load it into context for a visual check. Use when asked to check visually, use playwright, screenshot a page, see or look at the design yourself, or verify a layout on desktop and mobile widths.
How it works
- Overview
- Engine selection (handled by the tool)
- Workflow
- Output format
- When to use
- Do NOT use
SKILL.md preview
---
name: playwright
license: MIT
description: "Capture a screenshot of a URL or local page and load it into context for a visual check. Use when asked to check visually, use playwright, screenshot a page, see or look at the design yourself, or verify a layout on desktop and mobile widths."
argument-hint: <url> [--viewport WxH] [--full-page] [--selector <css>]
metadata:
source: portable-agent-layer
triggers:
- "playwright"
- "screenshot"
- "check visually"
- "look at the design"
- "look at this"
- "check yourself"
- "verify the layout"
- "responsive"
- "browser check"
---
## Overview
Take a screenshot of a running page and `Read` it into context so you can see the rendered result yourself — for design review, responsive checks (desktop + mobile widths), and confirming a layout fix actually looks right. This skill returns an **image**, not page data.
## Engine selection (handled by the tool)
The bundled tool picks the best available local engine automatically:
1. **System `playwright-cli`** (Microsoft's stateful agent CLI) — used when it is on `PATH` and no exact viewport/full-page is requested (its `screenshot` command can't set those).
2. **PAL-installed Playwright, launched in-process** — the precise path. Honors `--viewport`, `--full-page`, and `--selector` precisely.
If neither engine is usable, the tool prints `NO_PLAYWRIGHT_CLI` and exits non-zero — only then use the **Playwright MCP** (tier 3) in step 4.
## Workflow
1. Resolve the URL. If it's a local app, make sure the dev server is already running first.
2. Run the tool (it prints the absolute PNG path as its last stdout line):
```bash
pal cli skill run playwright shot <url> \
[--viewport 1440x900] [--full-page] [--selector "<css>"] [-o <out.png>]
```
3. `Read` the printed path so the screenshot enters your context. For a responsive check, run once per width (e.g. `--viewport 1440x900` then `--viewport 390x844`) and Read each.
4. If the tool exits with `NO_PLAYWRIGHT_CLI`:
- If Playwright MCP tools (`mcp__playwright__browser_*`) are available: `browser_navigate` to the URL, `browser_take_screenshot` to a file, then `Read` it.
- Otherwise, tell the user Playwright isn't installed and suggest running `pal cli install`.
## Output format
The screenshot image (via `Read`) plus one line stating the URL and viewport captured. Add a review only if the caller asked you to assess the design.
## When to use
- "check visually", "use playwright", "screenshot this", "see/look at the design yourself", "does this look right", desktop/mobile layout verification.
## Do NOT use
- To scrape page text or DOM data — fetch the page directly instead; this returns an image.
- To measure computed styles, element sizes, or horizontal overflow — use the Playwright MCP `browser_evaluate` for metrics; this skill does not return numbers.
Files in this package (3)
- SKILL.md 3 KB
- tools/shot-lib.ts 2 KB
- tools/shot.ts 4 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · kovrichard/portable-agent-layer | 100 | MIT |
| magnus919/agent-skills | 100 | MIT |
| kriscard/kriscard-claude-plugins | 100 | MIT |
| zenobi-us/dotfiles | 100 | MIT |
| dreamlab-ai/agentbox | 100 | AGPL-3.0 |
| DroBov1Tya/dusk_code | 100 | MIT |
| ivy00johns/skill-madness | 100 | MIT |
| musingfox/cc-plugins | 100 | MIT |
| netease-youdao/LobsterAI | 100 | MIT |
Database snapshot: 13.11.2026 · package version f472b76c097a (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100visual-proof
Capture before/after screenshot evidence of a web page at real breakpoints (375, 768, 1440) in both light and dark themes, using Playwright against a local dev server or a deployed URL. Use before starting any visual change to capture the current state, and again after to prove… - 100playwright-testing
UI/E2E test automation with Playwright MCP. Use when the user asks to "test the UI", "automate browser tests", "check the page", "take a screenshot", "run Playwright", "write E2E tests", or anything about browser-based testing. - 100playwright-e2e
End-to-end test and click-verify a web app with Playwright — write specs, drive authenticated pages, screenshot, and run in CI. Use when a web change has to be proven in a real browser rather than by unit tests. - 100screenshot-intake
Use when a user provides a URL or screenshot files and wants to build an app from them, or when starting /build-from-screenshot. Captures pages via Chrome DevTools or Playwright MCP, analyzes structure with Claude vision, and produces build-spec.json. Keywords: screenshot… - 100qa-screenshot
Screenshot a page (deploy preview or a dev server on localhost) in the sandbox's headless Chromium, look at it, and embed it in a task comment. Use to verify a visual change or record before/after evidence. - 98web-screenshot
Captures web page screenshots with the best available browser tool (a real-browser extension, browser MCP, shot-scraper, or Playwright), including full-page, element, mobile, dark mode, and batch shots. Use when asked to screenshot a URL or element, or to produce PNG or JPEG from a page.