Agent skill
playwright
Browser automation scripts for testing, screenshots, and web interaction. 16 scripts with persistent state.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/development/playwright
SKILL.md
Playwright Skill
Browser automation with persistent state between commands.
Setup
cd .claude/skills/playwright/scripts
npm install && npm run install-browsers
Scripts
All in .claude/skills/playwright/scripts/:
Navigation: navigate.js <url>, go-back.js, go-forward.js
Discovery: snapshot.js - Get element refs (run first)
Interaction: click.js <ref>, hover.js <ref>, type.js <text> [ref], select-option.js <ref> <value>, press-key.js <key>
Forms: fill-form.js <json>
Wait: wait.js <ms>, wait-for.js <selector> [timeout]
Capture: screenshot.js [file] [--full], pdf-save.js [file]
Utility: evaluate.js <script>, close.js, generate-test.js [name]
Basic Workflow
node navigate.js "http://localhost:5173"
node snapshot.js # Get refs: ref1, ref2...
node click.js ref1 # Use refs from snapshot
node type.js "text" ref2
node screenshot.js "out.png"
node close.js # Always close when done
Key Concepts
Refs: snapshot.js returns [ref=ref1] markers. Use these in subsequent commands. Refs expire on page changes - run snapshot again.
State: Browser stays open between commands. close.js clears state.
Output: All scripts return JSON: {"success": true, "data": {...}}
Documentation
- EXAMPLES.md - Complete workflow examples
- TROUBLESHOOTING.md - Common issues and fixes
- ARCHITECTURE.md - Technical details
- scripts/README.md - Quick reference
Limitations
- Single browser instance at a time
- Refs expire on DOM changes
- Browser opens visually (not headless)
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?