browser SKILL.md skillB

browser from bug-ops/zeph is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add bug-ops/zeph/browser@v1.0

Pins v1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
bug-ops/zeph
Path
.zeph/skills/browser/SKILL.md
Versions recorded
2
Latest version
v1.0, committed Mar 30, 2026
First version recorded
Mar 27, 2026
Size
6,939 bytes
Repository stars
66
License
MIT

Browser automation via Playwright MCP — navigate pages, click elements, fill forms, take screenshots, extract text, manage tabs, and run JavaScript in the browser. Use when the user asks to open a website, interact with a web page, scrape dynamic content, fill out forms, take a page screenshot, test a web application, or automate browser workflows. Requires a Playwright MCP server configured in [[mcp.servers]].

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

# Browser Automation

Automate web browser interactions using the Playwright MCP server.

## Prerequisites

Before any browser action, verify the Playwright MCP server is configured:

1. Check that an MCP server with `id` containing `"playwright"` or `"browser"` is present in `[[mcp.servers]]`.
2. If not found, instruct the user:
   ```toml
   # Add to config.toml — stdio transport (Node.js):
   [[mcp.servers]]
   id = "playwright"
   command = "npx"
   args = ["-y", "@playwright/mcp@latest", "--headless"]
   timeout = 60

   # Or Docker transport (no Node.js required):
   [[mcp.servers]]
   id = "playwright"
   command = "docker"
   args = ["run", "-i", "--rm", "mcr.microsoft.com/playwright/mcp"]
   timeout = 60
   ```
   Then restart the agent.

## Decision Tree

Select the approach based on what the user needs:

```
User request
├── Simple navigation / read
│   (open URL, get page text, take screenshot)
│   └── navigate → get_page_text / screenshot
├── Form interaction
│   (fill field, click button, select option, submit)
│   └── navigate → fill / click / select_option → screenshot to confirm
├── Multi-step workflow
│   (login + navigate + extract data)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add bug-ops/zeph/browser@sha256:72ee685622fbc9a4

The line at the top of this page pins the label v1.0, 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_65qr7ycbjjezfdlk.svg)](https://markdownregistry.com/a/art_65qr7ycbjjezfdlk)

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

Versions

The registry has recorded 2 versions of this file, between Mar 27, 2026 and Mar 30, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
v1.0 latest2026-03-30 c68c5de 6,939 BB view · diff
v1.02026-03-27 f883539 6,925 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No prompt-injection phrasing (matched: ignore previous instructions)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6939 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 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

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

bug-ops/zeph · 66 stars · license MIT · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_65qr7ycbjjezfdlk
GET https://markdownregistry.com/api/v1/resolve?ref=bug-ops/zeph/browser
GET https://markdownregistry.com/api/v1/blob/72ee685622fbc9a4f5e9a89eb3394bcb083b9688e1a359fc178a0218b27016cd

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 bug-ops/zeph

AGENTS.md@.github AGENTS.md file
bug-ops/zeph · .github/AGENTS.md
git:20260606.583c571 · audit A · 66 stars
api-request SKILL.md skill
bug-ops/zeph · .zeph/skills/api-request/SKILL.md · Send HTTP API requests using curl. Use when the user asks to call an API, fetch data from a URL, send…
v1.0 · audit A · 66 stars
archive SKILL.md skill
bug-ops/zeph · .zeph/skills/archive/SKILL.md · Create, extract, list, and convert compressed archives using tar, zip, gzip, bzip2, xz, zstd, and 7z. Use when the user…
v1.0 · audit A · 66 stars
caveman SKILL.md skill
bug-ops/zeph · .zeph/skills/caveman/SKILL.md · Switch to ultra-compressed, telegraphic output. Use when the user asks for terse, brief, minimal, "caveman", or…
v1.0 · audit A · 66 stars
code-analysis SKILL.md skill
bug-ops/zeph · .zeph/skills/code-analysis/SKILL.md · LSP-based code analysis via mcpls MCP server. Use for compiler-accurate type inspection, go-to-definition…
v1.0 · audit A · 66 stars
cron SKILL.md skill
bug-ops/zeph · .zeph/skills/cron/SKILL.md · Schedule recurring and one-time tasks using cron, crontab, at, and launchd. Use when the user asks to set up scheduled…
v1.0 · audit A · 66 stars
database SKILL.md skill
bug-ops/zeph · .zeph/skills/database/SKILL.md · Query and manage SQLite, PostgreSQL, and MySQL databases from the command line. Use when the user asks to run SQL…
v1.0 · audit A · 66 stars
docker SKILL.md skill
bug-ops/zeph · .zeph/skills/docker/SKILL.md · Manage Docker containers, images, volumes, networks, and Compose stacks. Use when the user asks to build, run, stop…
v1.0 · audit A · 66 stars
file-ops SKILL.md skill
bug-ops/zeph · .zeph/skills/file-ops/SKILL.md · File system operations — list directory contents, find files by name or glob pattern, search text inside files with…
v1.0 · audit A · 66 stars
git SKILL.md skill
bug-ops/zeph · .zeph/skills/git/SKILL.md · Run git version control commands for repository management. Use when the user asks to check status, view history or…
v1.0 · audit A · 66 stars
github SKILL.md skill
bug-ops/zeph · .zeph/skills/github/SKILL.md · GitHub CLI (gh) for repository management, issues, pull requests, releases, workflows, search, gists, and API access…
v1.0 · audit A · 66 stars
json-yaml SKILL.md skill
bug-ops/zeph · .zeph/skills/json-yaml/SKILL.md · Parse, query, transform, validate, and convert JSON and YAML data using jq and fy (fast-yaml). Use when the user asks…
v1.0 · audit A · 66 stars

Every file in bug-ops/zeph

Other files named browser

browser SKILL.md skill
code-yeongyu/oh-my-openagent · packages/shared-skills/skills/browser/SKILL.md · Drives a real browser through the omowright library from the js eval kernel: sites the user is already signed into…
git:20261023.4664dbb · audit A · 70,648 stars
browser SKILL.md skill
vibiumdev/vibium · skills/browser/SKILL.md · Automate browsers with the Vibium CLI. Use to navigate websites, inspect pages, fill forms, extract page data, debug UI…
git:20261022.d7d1c41 · audit A · 2,940 stars
browser SKILL.md skill
agent-sh/agnix · tests/fixtures/mcp-clients/.agents/skills/browser/SKILL.md · Browses web pages. Use when the user asks to read a web page.
git:20261017.3b8047d · audit B · 467 stars
browser SKILL.md skill
spencermarx/open-code-review · .claude/skills/browser/SKILL.md · Web browser automation with AI-optimized snapshots for claude-flow agents
v1.0.0 · audit A · 382 stars
browser SKILL.md skill
betterwright/betterwright · SKILL.md · Drive a persistent, policy-guarded real web browser via the betterwright CLI. Use for any task that needs the live web…
git:20261019.11b0412 · audit A · 347 stars
browser SKILL.md skill
blackbelttechnology/pi-agent-dashboard · packages/extension/.pi/skills/browser/SKILL.md · Browser automation via the `agent-browser` CLI. Use when the user needs to drive websites or Electron apps —…
v1.2 · audit A · 339 stars
browser SKILL.md skill
gtapps/hermitd · plugins/hermitd/skills/browser/SKILL.md · Use the hermit's own browser for web tasks, or the operator's Chrome when their account is needed.
git:20261102.f575c0a · audit A · 83 stars
browser SKILL.md skill
gtapps/claude-code-hermit · plugins/hermitd/skills/browser/SKILL.md · Use the hermit's own browser for web tasks, or the operator's Chrome when their account is needed.
git:20261103.ae0d584 · audit A · 83 stars

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