What does the Kane CLI skill do for Gemini CLI?

The Kane CLI skill gives Gemini CLI a browser verification layer it does not have natively. With the skill active, the terminal agent translates validation requirements into plain-English browser checks, runs them in real Chrome, and reads a deterministic pass or fail.

Should I install the Kane CLI skill globally or scoped to a project?

A global install at ~/.gemini/skills/kane-cli makes the skill available to every repository you work in from that machine. A scoped install at .gemini/skills/kane-cli lives inside a single project and travels with it, which is useful when you want the skill committed alongside the code.

What does Gemini CLI agent mode do?

In agent mode Gemini CLI builds a clean kane-cli run --agent command and runs the check headless. It skips human-friendly formatting and streams raw NDJSON so the agent can parse the output programmatically instead of reading it on screen.

How does the verification loop self-correct on a failure?

Gemini CLI applies file updates, triggers Kane CLI, and reads the run_end payload from the stream. On a pass it commits, and on a fail it uses the structured failure logs and screenshots to fix its own code and run the check again.

What is the run_end payload in the NDJSON stream?

Kane CLI in agent mode streams newline-delimited JSON, and the run_end object carries the final outcome of the run. Gemini CLI parses the stream, reads that run_end payload, and handles the result programmatically by committing on a pass or self-correcting on a fail.

Next-Gen App & Browser Testing Cloud

Trusted by 2 Mn+ QAs & Devs to accelerate their release cycles

Start free with Google

Start free with Email

TestMu AI (Formerly LambdaTest)
/
Blog
/
Verify Gemini CLI Output with Kane CLI

Product AI

Verify Gemini CLI Output with Kane CLI

Q: Can Gemini CLI run multiple Kane CLI checks in parallel?

Yes. When a task needs multiple disjoint routes tested at once, the skill instructs Gemini CLI to use shell subprocesses to trigger parallel Kane CLI runs. It tracks each background process, parses the distinct logs, and summarizes a scannable report.

Gemini CLI writes code but cannot confirm it works in a browser. Install the Kane CLI skill and it runs any flow in real Chrome and reads a pass or fail.

June 29, 2026

On This Page

Extending LLM Coding Capabilities to the Browser
Step-By-Step Skill Installation
The Autonomous Verification Loop
Skill-Driven Multi-Processing

Gemini CLI is an excellent terminal utility for drafting code, modifying files, and applying git diffs from a prompt. Like all terminal-scoped LLM engines it has one limit: it cannot interact with live user interfaces. It can write a flawless React component but has no native way to open a browser, click through the rendering, and confirm the component works.

Connecting Gemini CLI with Kane CLI gives the terminal agent a browser verification layer.

Extending LLM Coding Capabilities to the Browser

With the Kane CLI skill active, Gemini CLI translates validation requirements into plain-English browser checks, runs them in real Chrome, and reads the deterministic outcome.

Gemini CLI loads the Kane CLI SKILL.md, invokes kane-cli run, and parses NDJSON output

Note: Give your terminal agent a real browser and a deterministic pass or fail. Start free. Try Kane CLI

Step-By-Step Skill Installation

Gemini CLI uses structured Markdown skill definitions. You can configure the Kane CLI skill globally or scoped to a single repository.

Option A: Global Environment Setup

mkdir -p ~/.gemini/skills/kane-cli
curl -o ~/.gemini/skills/kane-cli/SKILL.md \
  https://raw.githubusercontent.com/LambdaTest/kane-cli/main/.agents/skills/kane-cli/SKILL.md

Option B: Scoped Project Setup

mkdir -p .gemini/skills/kane-cli
curl -o .gemini/skills/kane-cli/SKILL.md \
  https://raw.githubusercontent.com/LambdaTest/kane-cli/main/.agents/skills/kane-cli/SKILL.md

Gemini CLI scans these directories on startup. No extra config is required; it understands how to invoke and parse Kane CLI operations.

The Autonomous Verification Loop

Once the skill is linked, Gemini CLI moves to a continuous closed-loop workflow.

Gemini CLI applies code, triggers Kane CLI, reads the run_end JSON, then completes or self-corrects

When asked to build or modify a web workflow, the agent applies file updates, constructs a clean kane-cli run --agent command, and runs the check headless. In agent mode it skips human formatting and streams raw NDJSON.

It parses the stream, reads the run_end payload, and handles the outcome programmatically: on a pass it commits, on a fail it uses the structured failure logs and screenshots to fix its own code.

This is the same loop another coding agent closes when Claude Code writes a feature and Kane CLI proves it works.

Skill-Driven Multi-Processing

The skill file instructs the model how to coordinate complex testing. If a task needs multiple disjoint routes tested at once, Gemini CLI uses shell subprocesses to trigger parallel Kane CLI runs. It tracks each background process, parses the distinct logs, and summarizes a scannable report.

Note: Want the agent mode and skill setup behind this loop? Read the Kane CLI docs. Read the docs

The same skill drives interactive, headless, and agent workflows, so once it is installed you can pick whichever fits the moment. See how the three modes of Kane CLI map onto everyday development.

Author