playwright-cli SKILL.md skillA

playwright-cli from mancerayder42/jarvis-os is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add mancerayder42/jarvis-os/playwright-cli@git:20260905.fd1ce5a

Pins git:20260905.fd1ce5a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
mancerayder42/jarvis-os
Path
optional-skills/playwright-cli/SKILL.md
Versions recorded
1
Latest version
git:20260905.fd1ce5a, committed Sep 5, 2026
Size
4,808 bytes
Repository stars
5
License
MIT

Disk-based Playwright QA scan for a running dev server or deployed site — screenshots, console-error capture, page-error capture, and same-origin link checks in one process with one compact report. Use this instead of an interactive Playwright-MCP navigate/snapshot loop whenever you're verifying a KNOWN site you (or a build pipeline) control — confirming a change renders, checking a build for console errors, screenshotting routes at multiple viewports, or catching broken internal links. Not…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Playwright CLI — disk-based frontend QA

One bash call, one compact text report, screenshots on disk. Replaces the
`browser_navigate` -> `browser_snapshot` -> `browser_take_screenshot` -> repeat
MCP loop for the common case: a site whose DOM you already control (your own
build, a scaffold, any local dev server) and you just need to confirm it
renders clean.

**Why this exists over MCP:** MCP's snapshot-per-step loop pays a full
accessibility-tree or screenshot round-trip in tokens for every single action.
A scripted Playwright run does the whole navigate-render-capture cycle for
every route x viewport in one process and returns a handful of text lines.
Screenshots land on disk — `Read` the PNG directly instead of paying for an
MCP image round-trip.

**When to still use Playwright MCP instead:** driving a page you don't control
the markup of (a competitor site, a social-profile scrape, any external SaaS
UI), or anything that needs live interaction — click a button, fill a form,
drag, handle a dialog, and see what happens next. This skill only navigates
and observes; it does not interact.

## Setup (one-time)

```bash
cd "${CLAUDE_PLUGIN_ROOT}/skills/playwright-cli" && npm install
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add mancerayder42/jarvis-os/playwright-cli@sha256:c5620d5486fa0ddb

The line at the top of this page pins the label git:20260905.fd1ce5a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_6tqb5nrb4m6utb5y.svg)](https://markdownregistry.com/a/art_6tqb5nrb4m6utb5y)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 5, 2026.

versioncommittedcommitsizeaudit
git:20260905.fd1ce5a latest2026-09-05 fd1ce5a 4,808 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4808 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

mancerayder42/jarvis-os · 5 stars · license MIT · pushed 2026-10-01 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_6tqb5nrb4m6utb5y
GET https://markdownregistry.com/api/v1/resolve?ref=mancerayder42/jarvis-os/playwright-cli
GET https://markdownregistry.com/api/v1/blob/c5620d5486fa0ddb781327d91cb79c8d4b35f1c658ac18aa5744903b6a339f5e

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from mancerayder42/jarvis-os

AGENTS.md AGENTS.md file
mancerayder42/jarvis-os · AGENTS.md
git:20261001.9eb0496 · audit A · 5 stars
json-canvas SKILL.md skill
mancerayder42/jarvis-os · optional-skills/json-canvas/SKILL.md
git:20260905.fd1ce5a · audit C · 5 stars
knowledge-pack SKILL.md skill
mancerayder42/jarvis-os · optional-skills/knowledge-pack/SKILL.md · Build a durable knowledge pack in the hub for one subject — a small always-read index plus numbered load-on-demand…
git:20261001.dbca020 · audit A · 5 stars
obsidian-bases SKILL.md skill
mancerayder42/jarvis-os · optional-skills/obsidian-bases/SKILL.md
git:20260905.fd1ce5a · audit C · 5 stars
obsidian-cli SKILL.md skill
mancerayder42/jarvis-os · optional-skills/obsidian-cli/SKILL.md
git:20260905.fd1ce5a · audit C · 5 stars
obsidian-markdown SKILL.md skill
mancerayder42/jarvis-os · optional-skills/obsidian-markdown/SKILL.md
git:20260905.fd1ce5a · audit C · 5 stars
preflight SKILL.md skill
mancerayder42/jarvis-os · optional-skills/preflight/SKILL.md · Pre-deploy sanity check for environment files and project paths. Use when the user says /preflight, "preflight check"…
git:20261001.dbca020 · audit A · 5 stars
release-watch SKILL.md skill
mancerayder42/jarvis-os · optional-skills/release-watch/SKILL.md · Watch the Claude Code changelog (and optionally the Anthropic news feed) and report only what matters for how this user…
git:20261001.06cedb9 · audit A · 5 stars
voice SKILL.md skill
mancerayder42/jarvis-os · optional-skills/voice/SKILL.md · Turn spoken audio into text, and text into a spoken reply, via ElevenLabs (needs an ELEVENLABS_API_KEY). Use when the…
git:20260905.fd1ce5a · audit A · 5 stars
council SKILL.md skill
mancerayder42/jarvis-os · skills/council/SKILL.md · Pressure-test a real decision with several independent advisors, an anonymous peer review and a chair's verdict. Use…
git:20261001.06cedb9 · audit A · 5 stars
defuddle SKILL.md skill
mancerayder42/jarvis-os · skills/defuddle/SKILL.md
git:20260825.4c71f00 · audit C · 5 stars
done SKILL.md skill
mancerayder42/jarvis-os · skills/done/SKILL.md · End-of-session wrap-up — saves a session note to the hub, updates CONTEXT.md, and commits hub changes. Use this skill…
git:20260905.fd1ce5a · audit A · 5 stars

Every file in mancerayder42/jarvis-os

Other files named playwright-cli

playwright-cli SKILL.md skill
zebbern/claude-code-guide · skills/playwright/playwright-cli/SKILL.md · Automates browser interactions for web testing, form filling, screenshots, and data extraction using playwright-cli…
git:20260531.164971d · audit A · 4,678 stars
playwright-cli SKILL.md skill
dicklesworthstone/pi_agent_rust · tests/ext_conformance/artifacts/agents-mikeastock/skills/playwright-cli/SKILL.md · Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs…
git:20260205.788be98 · audit A · 1,915 stars
playwright-cli SKILL.md skill
asymmetric-al/core · .agents/skills/playwright-skill/playwright-cli/SKILL.md · Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you…
git:20260526.54acd2a · audit A · 379 stars
playwright-cli SKILL.md skill
asymmetric-al/core · .agents/skills/playwright-cli/SKILL.md · Use Playwright CLI for ad hoc browser automation and interactive verification of Core UI: opening local routes…
git:20260715.8ffc146 · audit A · 379 stars
playwright-cli SKILL.md skill
gaia-react/gaia · frontend/.claude/skills/playwright-cli/SKILL.md · Automate browser interactions, test web pages and work with Playwright tests.
git:20261003.2e3d776 · audit A · 24 stars
playwright-cli SKILL.md skill
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.opencode/skills/playwright-cli/SKILL.md · Drive a real browser from the terminal using the Playwright CLI (snapshot, click, fill, screenshots,
git:20260831.856ee57 · audit A · 19 stars
playwright-cli SKILL.md skill
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.github/skills/playwright-cli/SKILL.md · Drive a real browser from the terminal using the Playwright CLI (snapshot, click, fill, screenshots,
git:20260831.856ee57 · audit A · 19 stars
playwright-cli SKILL.md skill
kissgyorgy/coding-agents · skills/playwright-cli/SKILL.md · Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs…
git:20260221.18d4498 · audit A · 15 stars

Browse by kind, by grade A, or by owner.