by sahajamit · Agent Tool · ★ 120
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/sahajamit/promptwright.gitTaken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 120 |
| Forks | 28 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 70/100 |
| Last Updated | 2026-07-10 |
| Created | 2025-02-14 |
| Platforms | browser, node |
| Est. Tokens | ~16k |
Promptwright Prompt or record your browser. Get runnable tests. An AI QA agent that drives a real browser from natural language, or watches you click and turns it into Gherkin you can replay. Login-less. Bring your own model. Available as a desktop app and a CLI. Heads-up: migrated and rebuilt. Promptwright has moved from the organization to , and it has been completely revamped.
Looking for a promptwright alternative? If you're comparing promptwright with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Computer-Use SDK for E2E QA Testing
QA Skills Directory QA Skills is a curated directory of testing-specific skills for AI coding agents (Claude C
Open-source AI meeting copilot - real-time transcription, echo cancellation, and AI assistance. Captures syste
AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero config. Works with Claude, Cursor, Windsurf, Copi
50 QA and test-automation skills for Claude Code, Codex, Cursor, and any Agent Skills Standard runtime.
CLI, MCP server, and npm library that turns any website into an API — no docs, no SDK, no browser.
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: