A Kane CLI skill is a markdown instruction file that teaches an AI coding agent how to use kane-cli: when to invoke it, how to build commands, how to parse NDJSON output, how to present results, and how to handle failures. Install the skill once, and your agent handles browser automation tasks automatically whenever you ask.
Skills work on top of Agent Mode (--agent flag). The skill tells the agent to always use --agent, parse the NDJSON stream, and present structured results back to you.
Skills are plain markdown files. Review and customize them by editing the installed file after download.
Install
The quickest way to install the Kane CLI skill globally for all supported agents (Claude Code, Codex CLI, and Gemini CLI) in one command:
npx @testmuai/kane-cli-skill
Install by Agent
Claude Code
Codex CLI
Gemini CLI
The Kane CLI skill for Claude Code is a SKILL.md file placed in your skills directory.Global install (available in all projects):mkdir -p ~/.claude/skills/kane-cli
curl -o ~/.claude/skills/kane-cli/SKILL.md \
https://raw.githubusercontent.com/LambdaTest/kane-cli/main/skill-installer/skills/SKILL.md
mkdir -p .claude/skills/kane-cli
curl -o .claude/skills/kane-cli/SKILL.md \
https://raw.githubusercontent.com/LambdaTest/kane-cli/main/skill-installer/skills/SKILL.md
- Recognize when your request involves a browser and invoke
kane-cli automatically
- Build properly structured
kane-cli run --agent commands
- Parse the NDJSON output and present structured results with step counts, duration, extracted values, and assertion results
- Inspect failure logs and screenshots to diagnose issues
- Run multiple browser tests in parallel using sub-agents
- Suggest bug reports for agent failures, linked to the GitHub repo
Example prompts:"Can you verify the checkout flow on staging.myapp.com works?"
"Check if our login form shows the right error for wrong passwords"
"Search for 'laptops' on Amazon and store the top 3 prices"
The Kane CLI skill for Codex CLI is appended to your AGENTS.md file. Codex reads AGENTS.md at the project root or from ~/.codex/AGENTS.md globally.Global install (available in all projects):curl -o /tmp/kane-cli-agents.md \
https://raw.githubusercontent.com/LambdaTest/kane-cli/main/skill-installer/skills/SKILL.md
# Append to global AGENTS.md (creates the file if it doesn't exist)
cat /tmp/kane-cli-agents.md >> ~/.codex/AGENTS.md
curl -o /tmp/kane-cli-agents.md \
https://raw.githubusercontent.com/LambdaTest/kane-cli/main/skill-installer/skills/SKILL.md
cat /tmp/kane-cli-agents.md >> AGENTS.md
- Invoke
kane-cli run --agent for browser tasks
- Parse NDJSON output using
jq and tail
- Run parallel browser tests using shell background processes (
& + wait)
- Inspect failure logs and show screenshot paths
Example prompts:"Verify the staging site checkout flow works"
"Run the login test and tell me what happened"
The Kane CLI skill for Gemini CLI is a SKILL.md file placed in your Gemini skills directory.Global install (available in all projects):mkdir -p ~/.gemini/skills/kane-cli
curl -o ~/.gemini/skills/kane-cli/SKILL.md \
https://raw.githubusercontent.com/LambdaTest/kane-cli/main/skill-installer/skills/SKILL.md
mkdir -p .gemini/skills/kane-cli
curl -o .gemini/skills/kane-cli/SKILL.md \
https://raw.githubusercontent.com/LambdaTest/kane-cli/main/skill-installer/skills/SKILL.md
- Identify browser automation requests and invoke
kane-cli --agent
- Parse NDJSON events and surface the final result
- Run tests in parallel using shell subprocesses
- Diagnose failures from log files and screenshots
Example prompts:"Test that the homepage loads correctly on staging"
"Verify the registration flow works end to end"
First-Time Auth in Agent Contexts
OAuth login opens a browser window: AI agents cannot complete this flow. Use Basic Auth instead:
kane-cli login \
--username "YOUR_LT_USERNAME" \
--access-key "YOUR_LT_ACCESS_KEY"
kane-cli whoami.
How Skills Work
When you ask your AI agent to test something on the web, the skill:
- Checks
kane-cli is installed (kane-cli --version)
- Verifies authentication (
kane-cli whoami)
- Builds a
kane-cli run --agent --headless command from your request
- Parses the NDJSON stream, waits for
run_end
- Presents structured results: status, steps, duration, extracted values, assertion results
- If failed: inspects
run_dir logs and screenshots to diagnose the issue
- Rates the run and suggests a bug report for low-quality agent failures
Skill File Locations
| Agent | Global | Project-level |
|---|
| Claude Code | ~/.claude/skills/kane-cli/SKILL.md | .claude/skills/kane-cli/SKILL.md |
| Codex CLI | ~/.codex/AGENTS.md (appended section) | AGENTS.md (appended section) |
| Gemini CLI | ~/.gemini/skills/kane-cli/SKILL.md | .gemini/skills/kane-cli/SKILL.md |
