Playwright Cli
Browser-automation skill for terminal-driven Playwright work. Use when Codex needs to navigate websites, inspect pages, interact with forms, capture screenshots or traces, manage browser sessions, mock requests, or generate test code through a local `playwright-cli` workflow instead of writing a full test first.
Install
$ agentstack add skill-jovd83-playwright-skill-playwright-cli ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-jovd83-playwright-skill-playwright-cli) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Playwright CLI
Use this skill when terminal-driven browser automation is the fastest path.
Assumptions
- A local
playwright-cliinstallation is available. - If command names differ by version, inspect local help output before assuming an exact subcommand shape.
Operating Rules
- Snapshot or inspect the page before interacting with referenced elements.
- Prefer deterministic session naming for parallel or long-running work.
- Save and restore auth state deliberately when login is expensive.
- Capture traces before reproducing a failure, not after.
- Drop into custom code only when the built-in command surface is not enough.
Command Families
| Need | Guide | |---|---| | Basic browser interaction | [core-commands.md](core-commands.md) | | Request interception and mocking | [request-mocking.md](request-mocking.md) | | Custom Playwright API execution | [running-custom-code.md](running-custom-code.md) | | Session and storage management | [session-management.md](session-management.md), [storage-and-auth.md](storage-and-auth.md) | | Test generation | [test-generation.md](test-generation.md) | | Tracing and debugging | [tracing-and-debugging.md](tracing-and-debugging.md) | | Media capture | [screenshots-and-media.md](screenshots-and-media.md) | | Device and environment emulation | [device-emulation.md](device-emulation.md) | | Multi-step workflows | [advanced-workflows.md](advanced-workflows.md) |
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: jovd83
- Source: jovd83/playwright-skill
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.