← ClaudeAtlas

mushi-mushilisted

Set up, configure, and use Mushi Mushi — the AI-powered QA platform for automatic bug detection, user story mapping, TDD scenario generation, and PDCA auto-improvement. Use when setting up Mushi, configuring SDK/CLI/MCP, managing API keys, or asking how any Mushi feature works.
kensaurus/mushi-mushi · ★ 2 · AI & Automation · score 71
Install: claude install-skill kensaurus/mushi-mushi
# Mushi Mushi — AI QA Platform Setup & Usage Mushi Mushi is an AI-powered quality engineering platform that provides: - **Bug Intelligence** — capture and triage reports from real users - **Story Mapping** — automatically discover user stories from a live URL (no YAML required) - **TDD Generation** — turn user stories into Playwright test specs with one command - **PDCA Auto-improve** — failing tests are automatically rewritten by Claude - **Multi-key BYOK** — quota-aware API key pool with automatic failover ## Quick Start ### 1. Install the SDK ```bash npm install @mushi-mushi/web ``` ```ts import { Mushi } from '@mushi-mushi/web' Mushi.init({ projectId: 'YOUR_PROJECT_ID', apiKey: process.env.MUSHI_API_KEY!, capture: { discoverInventory: { enabled: true }, }, }) ``` ### 2. Install the CLI ```bash npm install -g @mushi-mushi/cli mushi login --api-key mushi_... --endpoint https://<ref>.supabase.co/functions/v1/api --project-id <pid> ``` ### 3. Map user stories from a live URL (no YAML needed) ```bash mushi stories map --url https://your-app.vercel.app --wait ``` Or in the console: **Inventory → Discovery → "Map from live app"** ### 4. Generate TDD tests from user stories ```bash # List discovered stories first (from accepted inventory) # Then generate a test for a specific story mushi tdd gen login-flow --mode review # Approve/reject the generated test mushi tdd pending mushi tdd approve <qa-story-id> ``` ### 5. Auto-improve failing tests (PDCA) ```