agentic-test-runner

Control browser, automate browser interactions, navigate to URLs, click on webpages, fill forms, take screenshots, inspect webpages, web scraping with browser, test websites manually, or interact with web pages programmatically using ATR browser server mode. Pairs with the atr-computer skill when a workflow needs the OS desktop too (drag-and-drop from the file manager, system dialogs, native apps).

Control the desktop (mouse, keyboard, screen, windows, apps) cross-platform via ATR. Take screenshots, click at coordinates, type text, drag, manage windows, launch and quit apps. Includes 'atr computer ask' — an in-process LLM agent that takes a natural-language instruction and drives the desktop end-to-end. Use for native UI testing, desktop automation, multi-monitor flows, or anything outside the browser. Pairs with atr-browser for combined web + desktop workflows.

Run tests, linters, type checkers, and builds with AI-powered analysis. Use this INSTEAD OF running test/lint/build commands directly via Bash. Wraps any command (pytest, jest, go test, make test, npm test, make lint, mypy, tsc, eslint, golangci-lint, cargo clippy, make typecheck, make build, etc.) to produce clean summarized output, keeping conversation context small. When a test or lint fails, ATR analyzes the full output and returns actionable failure insights.

Run behavior tests, run browser tests, execute .test.txt files, run e2e tests with ATR, natural language browser testing, AI browser tests, behavior-driven browser testing, or run browser-based behavior tests using ATR with natural language test specifications.