Test the Expensify App using Playwright browser automation. Use when user requests browser testing, after making frontend changes, or when debugging UI issues
Use Playwright testing when:
Proactively use after making frontend changes to verify your work functions correctly.
Before using Playwright tools, verify the dev server is running:
ps aux | grep "rspack" | grep -v grep
If server not running: Inform user to start with cd App && npm run web
https://dev.new.expensify.com:8082/https://dev.new.expensify.com:8082/ in the browserDo NOT add arbitrary waits after actions. Instead, take a snapshot to check the result and only add short waits if the page hasn't updated yet.
When signing in to dev environment:
user+throwaway<random>@gmail.com)
000000SKIP_ONBOARDING env flag is set to false by default in .env. When false, onboarding screens will appear after sign-in for new accounts. Unless you are specifically asked to test onboarding, update the flag to true before starting the dev server so that onboarding is bypassed entirely:
sed -i '' 's/SKIP_ONBOARDING=false/SKIP_ONBOARDING=true/' .env
false:
sed -i '' 's/SKIP_ONBOARDING=true/SKIP_ONBOARDING=false/' .env
grep SKIP_ONBOARDING .env
SKIP_ONBOARDING in .env, the web dev server must be restarted for the change to take effect.Scenario 1: User requests testing
User: "Test sign in to app"
→ Use this skill to verify server and test sign-in flow
Scenario 2: After making UI changes
You: "I've updated the expense form validation"
→ Proactively use this skill to verify the changes work in browser
Scenario 3: Investigating bug
User: "The submit button doesn't work on this page"
→ Use this skill to reproduce and verify the issue
Skip Playwright for:
npx skills add Expensify/playwright-app-testing下载完整 Skill 目录，包含 SKILL.md 及所有相关文件
OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.
ElevenLabs text-to-speech with mac-style say UX.
Control Philips Hue lights and scenes via the OpenHue CLI.
Query Google Places API (New) via the goplaces CLI for text search, place details, resolve, and reviews. Use for human-friendly place lookup or JSON output for scripts.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Category:developer