- Home
- Skills
- Testing & Debugging
- Local-first memory for AI coding agents (PMB)
Local-first memory for AI coding agents (PMB)
Developers waste time re-explaining their project to AI agents every session.
Free
Works with the AI Agents you already use
Local-first memory for AI coding agents (PMB)
Example session with this skill installed
Framework: Playwright. Flow: User logs in, goes to settings, and changes their display name. Base URL: https://app.test. Auth: storageState. Route map: /login, /settings.
- Read your context and instructions
- Compiled the local-first memory
// tests/settings.spec.ts
import { test, expect } from '@playwright/test';
test('user changes display name', async ({ page }) => {
await page.goto('/settings');
await page.getByLabel('Display Name').fill('New Name');
await page.getByRole('button', { name: /save/i }).click();
await expect(page.getByText('Settings saved')).toBeVisible();
});
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Writing end-to-end tests feels like a chore, leading to skipped coverage or brittle test suites full of nth-child selectors. Developers often waste hours debugging flaky tests that fail because of race conditions or poor selector priority.
What it does
- Converts plain-English user flows into production-ready test scripts.
- Enforces a strict selector hierarchy, prioritizing
data-testidand ARIA roles over brittle CSS classes. - Generates framework-specific code for Playwright, Cypress, or Detox.
- Builds in flake-proofing measures like network idle waits, animation disabling, and automatic retries.
- Handles setup and teardown logic, including API-based authentication and data cleanup.
Frameworks & tools
Supports Playwright, Cypress, and Detox. Compatible with any web or mobile project using standardized testing selectors.
Why this beats prompting it yourself
Generic LLM prompts often hallucinate selectors or use sleep commands that cause CI flakiness. This skill strictly follows industry best practices for test stability, implements deterministic data handling, and ensures every UI action is paired with a verifiable assertion.
Use cases
- Generating a full Playwright suite from a product requirements document.
- Converting a manual QA bug report into a reproducible Cypress test.
- Creating Detox integration tests for complex mobile onboarding flows.
- Building idempotent tests that clean up their own state via API.
Known limitations
Requires a basic route map and component map to avoid TODO placeholders for selectors and endpoints.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Testing & Debugging.
- Cannot infer internal logic of obfuscated code.
- Best results require standard config files like package.json or pyproject.toml.
- Project root detection fails in deeply nested mono-repos.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
15 uses
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 4 months ago
- Free with an Agensi account
Permissions
Allowed Hosts
File Scopes