testdriverai — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by testdriverai · Claude Skill · ★ 243

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is testdriverai safe to install? View the security audit →

About testdriverai

Computer-Use SDK for E2E QA Testing The TestDriver SDK is a JS plugin for vitest that makes it easy to spawn ephemeral devices and use vision-based LLMs to construct detemanistic and reliable tests. 🚀 Quick Start • 📖 Documentation • 💻 Examples • 📖 Pricing • 💬 Discord • 🌐 Website Why TestDriver? Don't ship bugs because flows are too hard to test. TestDriver helps engineering teams easily test, debug, and monitor E2E flows that are hard or impossible to cover with other tools like: Third-Party Web Apps • Desktop Apps • VS Code Extensions • Chrome Extensions • AI Chatbots • OAuth Flows • PDF Content • Spelling & Grammar • File System & Uploads • OS Accessibility • Visual Content • • • Example js // Click on the new text document await testdriver.find("New text doc

agentagent-skillsagentic-codingaiai-agentai-testingai-toolsclaudeclaude-codeclaude-plugin

Quick Facts

Stars243
Forks35
LanguageJavaScript
CategoryClaude Skill
Quality Score66.0613119774211/100
Open Issues46
Last Updated2026-09-21
Created2024-08-25
Platformsclaude-code, codex, node
Est. Tokens~13k

Compatible Skills

These tools work well together with testdriverai for enhanced workflows:

  • qaskills — semantic(0.43)+complementary+rare_topics+similar_pop+shared_platform (69%)
  • kane-cli — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (59%)
  • claude-code-playwright-mcp-test — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)
  • awesome-agv — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)

testdriverai alternative? Top 6 similar tools

Looking for a testdriverai alternative? If you're comparing testdriverai with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • qaskills by PramodDutta · ⭐ 214

    QA Skills Directory QA Skills is a curated directory of testing-specific skills for AI coding agents (Claude C

  • Mysti by DeepMyst · ⭐ 1.1k

    AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate

  • smart-ralph by tzachbon · ⭐ 544

    Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured

  • claudepro-directory by JSONbored · ⭐ 217

    HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve

  • palot by ItsWendell · ⭐ 187

    Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes

  • claude-codex-settings by fcakyon · ⭐ 1.2k

    Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is testdriverai?

testdriverai is Computer-Use SDK for E2E QA Testing. It is categorized as a Claude Skill with 243 GitHub stars.

What programming language is testdriverai written in?

testdriverai is primarily written in JavaScript. It covers topics such as agent, agent-skills, agentic-coding.

How do I install or use testdriverai?

You can find installation instructions and usage details in the testdriverai GitHub repository at github.com/testdriverai/testdriverai. The project has 243 stars and 35 forks, indicating an active community.

What are the best alternatives to testdriverai?

The top alternatives to testdriverai on Agent Skills Hub include qaskills, Mysti, smart-ralph. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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:

View on GitHub → Browse Claude Skill tools