Playwright
Skill shane9coy/katana-agent/agent/skills/agent-tools/playwright
⚡ Drop your AI agent into any project. Centralized Obsidian memory across Claude Code, Codex, Gemini, Cursor & more. Self-hosted, private, model-agnostic.
npx -y skills add shane9coy/katana-agent --skill playwrightAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Browser automation via Playwright MCP — reservations, ordering, scraping, form filling. Always confirm before final submission.
SKILL.md
1.8 KB, as published. Nobody here has run it
Playwright Skill
Auto-activate when browser automation is needed for bookings, ordering, scraping, or form filling.
Also used internally by Vibe Curator — prefer /vibe book or /vibe order for those flows.
Safety Rules (Non-Negotiable)
- Stop before final submit on ANY transaction — show screenshot, ask confirmation
- Human-like delays (1–2s between actions) to avoid bot detection
- If CAPTCHA appears: stop, screenshot, wait for manual solve
- Ticketmaster: reconnaissance only — never attempt queue bypass
Common Task Templates
| Task | Use Template |
|---|---|
| Restaurant reservation | Template 1: OpenTable |
| Food delivery | Template 2: DoorDash |
| Amazon shopping | Template 3: Amazon |
| Flight search | Template 4: Expedia (search only) |
| Ticket availability | Template 5: Ticketmaster (recon only) |
| Web scraping | Template 6 |
| Form filling | Template 7 |
| Price comparison | Template 8 |
Protocol (every task)
- Navigate → screenshot to confirm load
- Check login status before proceeding
- Execute task steps with delays
- Screenshot key states
- Pause before submit — show user, await "confirm"
Troubleshooting
- No Playwright tools? Check Node.js 18+ installed, run
npx playwright install chromium, restart Claude - Sessions not persisting? Verify storage state file + permissions
→ Full templates + examples: .claude/commands/playwright.md
Gives 0 of the 12 instructions most e2e browser skills give
Counted across 407 of the 410 authors here whose files we hold, read 2026-08-06
- use page object model patternin 35 of 407, across 25 files
- Snapshot to get element refsin 24 of 407, across 14 files
- keep tests independentin 23 of 407, across 18 files
- Interact using refs from the latest snapshotin 23 of 407, across 11 files
- clean up test data after each testin 21 of 407, across 15 files
- test user behavior not implementationin 20 of 407, across 14 files
- quarantine flaky tests explicitlyin 19 of 407, across 10 files
- wait for specific network conditionsin 18 of 407, across 8 files
- re-snapshot after navigation or dom changesin 17 of 407, across 10 files
- Detect running dev servers before writing test codein 17 of 407, across 7 files
- use web-first assertionsin 17 of 407, across 14 files
- capture screenshots or videos on test failurein 17 of 407, across 14 files
Said here and by no other author read
- pause before any final submit
- show screenshot before transaction submission
- insert human-like delays between actions
- stop and screenshot on CAPTCHA appearance
- wait for manual CAPTCHA solve
- navigate then screenshot to confirm page load
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.