playwright
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.
Savant verdict: Review advised
Security analysis or source-hub review identified patterns requiring attention.
Live evaluation
40overall
38quality
27compliance
48grounding
32actionability
64efficiency
Why this score may understate the skillThe live evaluation is a chat-only run: the model follows the skill's instructions but can't execute its scripts, call tools or reach the network.
- Ships 1 script the live run can't execute; outputs describe those steps rather than perform them.
- Expects tools, MCP servers, installs or network access that a chat-only run doesn't have.
- Works with files or media (documents, images, designs) that the run can only describe in text.
0 pass · 0 investigate · 6 fail across 6 cases. Independent evaluation accepted 6 of 16 model-drafted cases. Drafted and run by nvidia/nemotron-3-super-120b-a12b, validated and scored by jev-latest.
- I need to automate logging into https://example.com/login, filling in username 'testuser' and password 'securepass', then clicking the submit button and taking a screenshot of the resulting page.positive case · fail
- Help me debug a UI issue on https://example.com/dashboard where a modal doesn't open when clicking the 'Settings' button. I want to start a trace, click the button, check if the modal appears, stop the trace, and take a screenshot.positive case · fail
- Extract the page title and the text content of the main article element (identified by CSS selector 'article.main') from https://example.com/news using Playwright CLI.positive case · fail
- Automate the search flow on https://example.com: type 'playwright' in the search box and press Enter.edge case · fail
- Use Playwright to scrape all product prices from https://example.com/products and save them to a CSV file.negative case · fail
- Help me navigate to https://example.com/app and check if the user is logged in by looking for a profile icon, but I don't know what the icon looks like or where it is located.edge case · fail
Security assessment
Risk score
28/100
Recommendation
CAUTION
Severity
MEDIUM
Savant decision
Review advised
The assessment recommends caution with a risk score of 20/100 or more; review its findings before use. Static security analysis completed.
6 patterns found
- Agent Snooping: skills/playwright-cli/SKILL.mdmedium · NOTICE.txt:5 · Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
- Agent Snooping: ls install under `$CODEX_HOME/skills` (default: `~/.codex/skillsmedium · SKILL.md:41 · Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
- Agent Snooping: ls install under `$CODEX_HOME/skills` (default: `~/.codex/skillsmedium · references/cli.md:11 · Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
- MCP Rug Pull: npx --package @playwright/climedium · SKILL.md:124 · npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
- MCP Rug Pull: npx ismedium · scripts/playwright_cli.sh:5 · npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
- MCP Rug Pull: npx --yes --package @playwright/climedium · scripts/playwright_cli.sh:19 · npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
Structure
- Ships 1 executable scriptscripts/playwright_cli.sh. Review what they do before enabling the skill for agents with tool access.
SKILL.md
---
name: "playwright"
description: "Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script."
---
# Playwright CLI Skill
Drive a real browser from the terminal using `playwright-cli`. Prefer the bundled wrapper script so the CLI works even when it is not globally installed.
Treat this skill as CLI-first automation. Do not pivot to `@playwright/test` unless the user explicitly asks for test files.
## Prerequisite check (required)
Before proposing commands, check whether `npx` is available (the wrapper depends on it):
```bash
command -v npx >/dev/null 2>&1
```
If it is not available, pause and ask the user to install Node.js/npm (which provides `npx`). Provide these steps verbatim:
```bash
# Verify Node/npm are installed
node --version
npm --version
# If missing, install Node.js/npm, then:
npm install -g @playwright/cli@latest
playwright-cli --help
```
Once `npx` is present, proceed with the wrapper script. A global install of `playwright-cli` is optional.
## Skill path (set once)
```bash
export CODEX_HOME="${CODEX_HOME:-$HOME/.codex}"
export PWCLI="$CODEX_HOME/skills/playwright/scripts/playwright_cli.sh"
```
User-scoped skills install under `$CODEX_HOME/skills` (default: `~/.codex/skills`).
## Quick start
Use the wrapper script:
```bash
"$PWCLI" open https://playwright.dev --headed
"$PWCLI" snapshot
"$PWCLI" click e15
"$PWCLI" type "Playwright"
"$PWCLI" press Enter
"$PWCLI" screenshot
```
If the user prefers a global install, this is also valid:
```bash
npm install -g @playwright/cli@latest
playwright-cli --help
```
## Core workflow
1. Open the page.
2. Snapshot to get stable element refs.
3. Interact using refs from the latest snapshot.
4. Re-snapshot after navigation or significant DOM changes.
5. Capture artifacts (screenshot, pdf, traces) when useful.
Minimal loop:
```bash
"$PWCLI" open https://example.com
"$PWCLI" snapshot
"$PWCLI" click e3
"$PWCLI" snapshot
```
## When to snapshot again
Snapshot again after:
- navigation
- clicking elements that change the UI substantially
- opening/closing modals or menus
- tab switches
Refs can go stale. When a command fails due to a missing ref, snapshot again.
## Recommended patterns
### Form fill and submit
```bash
"$PWCLI" open https://example.com/form
"$PWCLI" snapshot
"$PWCLI" fill e1 "user@example.com"
"$PWCLI" fill e2 "password123"
"$PWCLI" click e3
"$PWCLI" snapshot
```
### Debug a UI flow with traces
```bash
"$PWCLI" open https://example.com --headed
"$PWCLI" tracing-start
# ...interactions...
"$PWCLI" tracing-stop
```
### Multi-tab work
```bash
"$PWCLI" tab-new https://example.com
"$PWCLI" tab-list
"$PWCLI" tab-select 0
"$PWCLI" snapshot
```
## Wrapper script
The wrapper script uses `npx --package @playwright/cli playwright-cli` so the CLI can run without a global install:
```bash
"$PWCLI" --help
```
Prefer the wrapper unless the repository already standardizes on a global install.
## References
Open only what you need:
- CLI command reference: `references/cli.md`
- Practical workflows and troubleshooting: `references/workflows.md`
## Guardrails
- Always snapshot before referencing element ids like `e12`.
- Re-snapshot when refs seem stale.
- Prefer explicit commands over `eval` and `run-code` unless needed.
- When you do not have a fresh snapshot, use placeholder refs like `eX` and say why; do not bypass refs with `run-code`.
- Use `--headed` when a visual check will help.
- When capturing artifacts in this repo, use `output/playwright/` and avoid introducing new top-level artifact folders.
- Default to CLI commands and workflows, not Playwright test specs.