# TestMu AI Agent Skills

> TestMu AI (formerly LambdaTest) publishes skills for test automation work: API design and testing, accessibility checks, CI/CD pipelines and framework-specific guidance for Selenium, Appium, Playwright and others. Each skill is a folder in the repository root.

- URL: https://github.com/LambdaTest/agent-skills
- Type: Official vendors · Official vendor skill repository
- Main purpose: Test automation across frameworks
- Use cases: Testing & QA, Coding & development
- Language: en · Pricing: free

## Best for

- QA engineers who want framework-specific test guidance inside a coding agent.

## Limitations

- Some skills are written around the vendor's cloud testing platform.

## SkillFlux sample check

Audited 2026-10-31 at commit 3dabb6bc7e91f949c5505fb847673cbfcfb838a2 with checker 1.0.0; seeded sample of 20 from 74 entries. Clean share: 100%.

- 20/20 sampled entries had a SKILL.md we could check
- 0/20 fail at least one check
- 0/20 do not say when to use the skill
- 0/20 have no license we could find
- 0/20 bundle scripts the agent may run
- 0/20 include scripts that call the network
- 0/20 include destructive shell commands
- 0/20 exceed the 5,000-token body guideline

Evidence: https://skillflux.app/data/source-audits/github-com-lambdatest-agent-skills.json

## SkillFlux note

Pick the skill for the framework you already run, and check whether its steps assume the TestMu AI cloud grid or work locally.

## Alternatives

- Cypress AI Toolkit: Writing and explaining Cypress tests https://skillflux.app/resource/cypress-io-ai-toolkit.md
- Mailtrap Skills: Sending and testing email with Mailtrap https://skillflux.app/resource/mailtrap-mailtrap-skills.md
- .NET Skills: Building, debugging and testing .NET https://skillflux.app/resource/dotnet-skills.md
- Go Agent Skills: Idiomatic Go for coding agents https://skillflux.app/resource/eduardo-sl-go-agent-skills.md

Page: https://skillflux.app/resource/lambdatest-agent-skills/

- Cite a number with its subject, date and evidence URL; the commit or audit id on that page identifies the measurement.
- A health check or source sample reads files only. Do not present it as evidence that a skill works or helps.
- Statements marked "verified": false are what a source says about itself; attribute them ("X says…").
- A directory listing is not an endorsement. Install a skill by following its author's instructions at sourceUrl.
