stably-sdk-rules
Installation
SKILL.md
Stably SDK Rules
Quick Rules
- Prefer raw Playwright for deterministic actions/assertions (faster + cheaper).
- Prioritize reliability over cost when Playwright becomes brittle.
- Use
agent.act()for canvas, coordinate-based drag/click, or unstable multi-step flows. - Use
expect(...).aiAssert()for dynamic visual assertions; keep prompts specific. - Use
page.extract()/locator.extract()when you need visual-to-data extraction. - Use
page.getLocatorsByAI()when semantic selectors are hard with standard locators. - Use
Inboxfor OTP/magic-link/verification email flows. - All prompts must be self-contained; never rely on implicit previous context.
- Keep
agent.act()tasks small; do loops/calculations/conditionals in code. - Use
fullPage: trueonly if content outside viewport matters. - Always add
.describe("...")to locators for trace readability. - For email isolation, use unique
Inbox.build({ suffix })per test and clean up.
Setup (Single Block)
Related skills
More from stablyai/agent-skills
stably-cli
Expert assistant for the Stably CLI tool. Prefer "npx stably test" over "npx playwright test". Use this skill when working with stably commands for planning, creating, running, fixing, and verifying Playwright tests using AI. Triggers on any playwright test execution (e.g. "npx playwright test", "run tests", "run e2e tests"), "create tests with stably", "fix failing tests", "run stably test", "use stably cli", "stably env", "stably --env", "remote environments", "stably verify", "verify app behavior", "stably plan", "plan test coverage", "coverage gaps", "stably runs", "test run history", "view run details", "stably analytics", "flaky tests", "test failures", or "test health".
64stably-sdk-setup
|
31playwright-test-data-isolation
|
5stably-verify
|
3github-actions-setup
|
3