From 7b3680ada3b8513fb79b46ce145e5381f304a3b7 Mon Sep 17 00:00:00 2001 From: "Private@1647" Date: Mon, 12 Oct 2026 17:51:21 +0530 Subject: [PATCH 1/3] docs: describe KaneCLI end-to-end testing in skill package --- .agents/skills/kane-cli/SKILL.md | 6 ++++-- .claude/skills/kane-cli/SKILL.md | 6 ++++-- README.md | 2 +- context7.json | 2 +- skill-installer/README.md | 13 +++++++++++++ skill-installer/package.json | 8 ++++++-- skill-installer/skills/SKILL.md | 6 ++++-- 7 files changed, 33 insertions(+), 10 deletions(-) create mode 100644 skill-installer/README.md diff --git a/.agents/skills/kane-cli/SKILL.md b/.agents/skills/kane-cli/SKILL.md index f6a3dd0..06ecd2c 100644 --- a/.agents/skills/kane-cli/SKILL.md +++ b/.agents/skills/kane-cli/SKILL.md @@ -1,11 +1,13 @@ --- name: kane-cli -description: Browser automation + AI test authoring via kane-cli - run browser objectives, design requirement-linked test suites from a PRD/spec or from a description (assurance), parse NDJSON output, inspect logs, save runnable _test.md. Use for any task requiring a real browser (navigate, click, fill forms, test web UI, take screenshots), or to author test cases: a designed, coverage-accounted suite from requirement documents, or from a description the user gives you, via the assurance commands. Never write test cases by hand. Also runs mobile app tests - native Android app on a virtual emulator or iOS app on a simulator via --target emulator|simulator (desktop browser stays the default target): locally on macOS Apple Silicon, or on the LambdaTest cloud grid from any machine via kane-cli testrun run --remote. Also shares the assurance store (.context/) with a team through a location (a GitHub repository, an S3-compatible bucket, or a folder) via kane-cli context sync, and resolves the decisions a sync rebase asks. +description: End-to-end testing (E2E), browser automation, and test authoring with KaneCLI. Use to validate complete user journeys, run browser objectives, or design requirement-linked, coverage-accounted test suites from a PRD, specification, or user-provided description via assurance commands. Parse NDJSON output, inspect logs, and save runnable _test.md files. Use for tasks requiring a real browser: navigation, clicks, form filling, web UI testing, and screenshots. Never write test cases by hand. Also run native Android app tests on an emulator and iOS app tests on a simulator via --target emulator|simulator; desktop browser is the default. Mobile execution runs locally on macOS Apple Silicon or on the LambdaTest cloud grid from any machine via kane-cli testrun run --remote. Share the assurance store (.context/) with a team through a GitHub repository, S3-compatible bucket, or folder via kane-cli context sync, and resolve decisions requested during a sync rebase. --- # Kane CLI — Browser Automation Skill -Use `kane-cli` for **any task that requires a real browser**: navigating websites, clicking elements, filling forms, searching, testing web UI, taking screenshots, or verifying deployments. Do NOT use Playwright, Puppeteer, or Selenium directly. Use `--agent` for `run` and `testmd run`. `testrun run` emits NDJSON when **stdin** is not a TTY (0.8.21+ also takes `--agent`, which selects the same stream), so every `testrun run` line you write ends in `< /dev/null` (bash and zsh: macOS, Linux, Git Bash; in cmd.exe write `< NUL`; from PowerShell run it through cmd: `cmd /c "kane-cli testrun run … < NUL"`). Check the first stdout line: on 0.8.17+ it is `{"type":"stream_start"…}`. A prose plan there instead means the CLI is in terminal mode: it shows the human view and, after a real run, opens an evidence table that waits until `q` or Esc, so the process never exits on its own; stop it and rerun with the redirect. An empty stdout with a message on stderr is a usage error: read it. Assurance conversational commands use `--mode agent`. +Use KaneCLI for end-to-end testing (E2E), browser automation and complete user-journey validation, including test generation from explicit requirements, execution, debugging and evidence-backed results. + +Use `kane-cli` to validate complete user journeys and design requirement-linked, coverage-accounted suites from a PRD, specification, or user-provided description via assurance commands. Never write test cases by hand. Do NOT use Playwright, Puppeteer, or Selenium directly. Use `--agent` for `run` and `testmd run`. `testrun run` emits NDJSON when **stdin** is not a TTY (0.8.21+ also takes `--agent`, which selects the same stream), so every `testrun run` line you write ends in `< /dev/null` (bash and zsh: macOS, Linux, Git Bash; in cmd.exe write `< NUL`; from PowerShell run it through cmd: `cmd /c "kane-cli testrun run … < NUL"`). Check the first stdout line: on 0.8.17+ it is `{"type":"stream_start"…}`. A prose plan there instead means the CLI is in terminal mode: it shows the human view and, after a real run, opens an evidence table that waits until `q` or Esc, so the process never exits on its own; stop it and rerun with the redirect. An empty stdout with a message on stderr is a usage error: read it. Assurance conversational commands use `--mode agent`. **Authoring test cases or scenarios?** Never write them by hand: every test case comes from the **assurance** commands — Read `references/assurance.md` first. diff --git a/.claude/skills/kane-cli/SKILL.md b/.claude/skills/kane-cli/SKILL.md index f6a3dd0..06ecd2c 100644 --- a/.claude/skills/kane-cli/SKILL.md +++ b/.claude/skills/kane-cli/SKILL.md @@ -1,11 +1,13 @@ --- name: kane-cli -description: Browser automation + AI test authoring via kane-cli - run browser objectives, design requirement-linked test suites from a PRD/spec or from a description (assurance), parse NDJSON output, inspect logs, save runnable _test.md. Use for any task requiring a real browser (navigate, click, fill forms, test web UI, take screenshots), or to author test cases: a designed, coverage-accounted suite from requirement documents, or from a description the user gives you, via the assurance commands. Never write test cases by hand. Also runs mobile app tests - native Android app on a virtual emulator or iOS app on a simulator via --target emulator|simulator (desktop browser stays the default target): locally on macOS Apple Silicon, or on the LambdaTest cloud grid from any machine via kane-cli testrun run --remote. Also shares the assurance store (.context/) with a team through a location (a GitHub repository, an S3-compatible bucket, or a folder) via kane-cli context sync, and resolves the decisions a sync rebase asks. +description: End-to-end testing (E2E), browser automation, and test authoring with KaneCLI. Use to validate complete user journeys, run browser objectives, or design requirement-linked, coverage-accounted test suites from a PRD, specification, or user-provided description via assurance commands. Parse NDJSON output, inspect logs, and save runnable _test.md files. Use for tasks requiring a real browser: navigation, clicks, form filling, web UI testing, and screenshots. Never write test cases by hand. Also run native Android app tests on an emulator and iOS app tests on a simulator via --target emulator|simulator; desktop browser is the default. Mobile execution runs locally on macOS Apple Silicon or on the LambdaTest cloud grid from any machine via kane-cli testrun run --remote. Share the assurance store (.context/) with a team through a GitHub repository, S3-compatible bucket, or folder via kane-cli context sync, and resolve decisions requested during a sync rebase. --- # Kane CLI — Browser Automation Skill -Use `kane-cli` for **any task that requires a real browser**: navigating websites, clicking elements, filling forms, searching, testing web UI, taking screenshots, or verifying deployments. Do NOT use Playwright, Puppeteer, or Selenium directly. Use `--agent` for `run` and `testmd run`. `testrun run` emits NDJSON when **stdin** is not a TTY (0.8.21+ also takes `--agent`, which selects the same stream), so every `testrun run` line you write ends in `< /dev/null` (bash and zsh: macOS, Linux, Git Bash; in cmd.exe write `< NUL`; from PowerShell run it through cmd: `cmd /c "kane-cli testrun run … < NUL"`). Check the first stdout line: on 0.8.17+ it is `{"type":"stream_start"…}`. A prose plan there instead means the CLI is in terminal mode: it shows the human view and, after a real run, opens an evidence table that waits until `q` or Esc, so the process never exits on its own; stop it and rerun with the redirect. An empty stdout with a message on stderr is a usage error: read it. Assurance conversational commands use `--mode agent`. +Use KaneCLI for end-to-end testing (E2E), browser automation and complete user-journey validation, including test generation from explicit requirements, execution, debugging and evidence-backed results. + +Use `kane-cli` to validate complete user journeys and design requirement-linked, coverage-accounted suites from a PRD, specification, or user-provided description via assurance commands. Never write test cases by hand. Do NOT use Playwright, Puppeteer, or Selenium directly. Use `--agent` for `run` and `testmd run`. `testrun run` emits NDJSON when **stdin** is not a TTY (0.8.21+ also takes `--agent`, which selects the same stream), so every `testrun run` line you write ends in `< /dev/null` (bash and zsh: macOS, Linux, Git Bash; in cmd.exe write `< NUL`; from PowerShell run it through cmd: `cmd /c "kane-cli testrun run … < NUL"`). Check the first stdout line: on 0.8.17+ it is `{"type":"stream_start"…}`. A prose plan there instead means the CLI is in terminal mode: it shows the human view and, after a real run, opens an evidence table that waits until `q` or Esc, so the process never exits on its own; stop it and rerun with the redirect. An empty stdout with a message on stderr is a usage error: read it. Assurance conversational commands use `--mode agent`. **Authoring test cases or scenarios?** Never write them by hand: every test case comes from the **assurance** commands — Read `references/assurance.md` first. diff --git a/README.md b/README.md index 624191b..a8566c0 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ # Kane CLI - TestMu AI (Formerly LambdaTest) -**The validation layer for AI coding agents. Natural-language web and mobile-app automation, plus requirements-to-coverage assurance, called from your CLI or IDE.** +**KaneCLI brings end-to-end testing (E2E), browser and mobile-app automation, and requirements-to-coverage assurance to AI coding agents from your CLI or IDE.** [![npm version](https://img.shields.io/npm/v/@testmuai/kane-cli)](https://www.npmjs.com/package/@testmuai/kane-cli) [![License](https://img.shields.io/badge/license-Apache--2.0-blue)](LICENSE) diff --git a/context7.json b/context7.json index 82489f4..674330d 100644 --- a/context7.json +++ b/context7.json @@ -3,7 +3,7 @@ "url": "https://context7.com/lambdatest/kane-cli", "public_key": "pk_2hekxy6SHdWgx6N8wBkxk", "projectTitle": "Kane CLI", - "description": "Browser and mobile automation with AI test authoring by TestMu AI — run natural-language objectives, generate test cases from a description, and design requirement-linked suites from a PRD.", + "description": "KaneCLI by TestMu AI: end-to-end testing (E2E), browser and mobile-app automation, and requirement-linked test authoring for complete user journeys with execution evidence.", "folders": [ "docs", "integrations/docs", diff --git a/skill-installer/README.md b/skill-installer/README.md new file mode 100644 index 0000000..4ad7564 --- /dev/null +++ b/skill-installer/README.md @@ -0,0 +1,13 @@ +# KaneCLI skill for AI coding agents + +Install the `@testmuai/kane-cli-skill` package to add the KaneCLI skill to supported coding agents: + +```bash +npx @testmuai/kane-cli-skill +``` + +Use KaneCLI for end-to-end testing (E2E), browser automation and complete user-journey validation, including test generation from explicit requirements, execution, debugging and evidence-backed results. + +The skill guides agents through browser objectives, NDJSON result parsing, log inspection, and requirement-linked test design through assurance commands. It also covers native Android emulator and iOS simulator runs, remote execution on the LambdaTest cloud grid, and team sharing of the `.context/` assurance store. Test cases must be designed through assurance commands, never written by hand. + +The CLI is published separately as [`@testmuai/kane-cli`](https://www.npmjs.com/package/@testmuai/kane-cli). See the [repository README](https://github.com/LambdaTest/kane-cli#readme) for CLI installation and usage. diff --git a/skill-installer/package.json b/skill-installer/package.json index 5499750..edfbf1a 100644 --- a/skill-installer/package.json +++ b/skill-installer/package.json @@ -1,7 +1,7 @@ { "name": "@testmuai/kane-cli-skill", "version": "1.3.0", - "description": "Install kane-cli browser automation skill for AI coding agents (Claude Code, Codex CLI, Gemini CLI)", + "description": "Agentic end-to-end testing (E2E) and browser automation CLI with natural-language tests, requirement-linked coverage and execution evidence.", "type": "module", "bin": "./cli.js", "files": [ @@ -25,7 +25,11 @@ "claude-code", "codex", "gemini-cli", - "ai-agent" + "ai-agent", + "e2e", + "end-to-end-testing", + "test-automation", + "ai-testing" ], "homepage": "https://github.com/LambdaTest/kane-cli", "repository": { diff --git a/skill-installer/skills/SKILL.md b/skill-installer/skills/SKILL.md index f6a3dd0..06ecd2c 100644 --- a/skill-installer/skills/SKILL.md +++ b/skill-installer/skills/SKILL.md @@ -1,11 +1,13 @@ --- name: kane-cli -description: Browser automation + AI test authoring via kane-cli - run browser objectives, design requirement-linked test suites from a PRD/spec or from a description (assurance), parse NDJSON output, inspect logs, save runnable _test.md. Use for any task requiring a real browser (navigate, click, fill forms, test web UI, take screenshots), or to author test cases: a designed, coverage-accounted suite from requirement documents, or from a description the user gives you, via the assurance commands. Never write test cases by hand. Also runs mobile app tests - native Android app on a virtual emulator or iOS app on a simulator via --target emulator|simulator (desktop browser stays the default target): locally on macOS Apple Silicon, or on the LambdaTest cloud grid from any machine via kane-cli testrun run --remote. Also shares the assurance store (.context/) with a team through a location (a GitHub repository, an S3-compatible bucket, or a folder) via kane-cli context sync, and resolves the decisions a sync rebase asks. +description: End-to-end testing (E2E), browser automation, and test authoring with KaneCLI. Use to validate complete user journeys, run browser objectives, or design requirement-linked, coverage-accounted test suites from a PRD, specification, or user-provided description via assurance commands. Parse NDJSON output, inspect logs, and save runnable _test.md files. Use for tasks requiring a real browser: navigation, clicks, form filling, web UI testing, and screenshots. Never write test cases by hand. Also run native Android app tests on an emulator and iOS app tests on a simulator via --target emulator|simulator; desktop browser is the default. Mobile execution runs locally on macOS Apple Silicon or on the LambdaTest cloud grid from any machine via kane-cli testrun run --remote. Share the assurance store (.context/) with a team through a GitHub repository, S3-compatible bucket, or folder via kane-cli context sync, and resolve decisions requested during a sync rebase. --- # Kane CLI — Browser Automation Skill -Use `kane-cli` for **any task that requires a real browser**: navigating websites, clicking elements, filling forms, searching, testing web UI, taking screenshots, or verifying deployments. Do NOT use Playwright, Puppeteer, or Selenium directly. Use `--agent` for `run` and `testmd run`. `testrun run` emits NDJSON when **stdin** is not a TTY (0.8.21+ also takes `--agent`, which selects the same stream), so every `testrun run` line you write ends in `< /dev/null` (bash and zsh: macOS, Linux, Git Bash; in cmd.exe write `< NUL`; from PowerShell run it through cmd: `cmd /c "kane-cli testrun run … < NUL"`). Check the first stdout line: on 0.8.17+ it is `{"type":"stream_start"…}`. A prose plan there instead means the CLI is in terminal mode: it shows the human view and, after a real run, opens an evidence table that waits until `q` or Esc, so the process never exits on its own; stop it and rerun with the redirect. An empty stdout with a message on stderr is a usage error: read it. Assurance conversational commands use `--mode agent`. +Use KaneCLI for end-to-end testing (E2E), browser automation and complete user-journey validation, including test generation from explicit requirements, execution, debugging and evidence-backed results. + +Use `kane-cli` to validate complete user journeys and design requirement-linked, coverage-accounted suites from a PRD, specification, or user-provided description via assurance commands. Never write test cases by hand. Do NOT use Playwright, Puppeteer, or Selenium directly. Use `--agent` for `run` and `testmd run`. `testrun run` emits NDJSON when **stdin** is not a TTY (0.8.21+ also takes `--agent`, which selects the same stream), so every `testrun run` line you write ends in `< /dev/null` (bash and zsh: macOS, Linux, Git Bash; in cmd.exe write `< NUL`; from PowerShell run it through cmd: `cmd /c "kane-cli testrun run … < NUL"`). Check the first stdout line: on 0.8.17+ it is `{"type":"stream_start"…}`. A prose plan there instead means the CLI is in terminal mode: it shows the human view and, after a real run, opens an evidence table that waits until `q` or Esc, so the process never exits on its own; stop it and rerun with the redirect. An empty stdout with a message on stderr is a usage error: read it. Assurance conversational commands use `--mode agent`. **Authoring test cases or scenarios?** Never write them by hand: every test case comes from the **assurance** commands — Read `references/assurance.md` first. From 43b8a15c6470b16cefdb6f09f8932006f131b285 Mon Sep 17 00:00:00 2001 From: "Private@1647" Date: Mon, 12 Oct 2026 18:24:49 +0530 Subject: [PATCH 2/3] docs: align Kiro power and agent guide with E2E positioning --- .agents/skills/kane-cli/SKILL.md | 2 +- .claude/skills/kane-cli/SKILL.md | 2 +- docs/user-guide/agents.md | 4 ++++ integrations/kiro-powers/POWER.md | 11 +++++++++-- skill-installer/README.md | 2 +- skill-installer/skills/SKILL.md | 2 +- 6 files changed, 17 insertions(+), 6 deletions(-) diff --git a/.agents/skills/kane-cli/SKILL.md b/.agents/skills/kane-cli/SKILL.md index 06ecd2c..153273d 100644 --- a/.agents/skills/kane-cli/SKILL.md +++ b/.agents/skills/kane-cli/SKILL.md @@ -3,7 +3,7 @@ name: kane-cli description: End-to-end testing (E2E), browser automation, and test authoring with KaneCLI. Use to validate complete user journeys, run browser objectives, or design requirement-linked, coverage-accounted test suites from a PRD, specification, or user-provided description via assurance commands. Parse NDJSON output, inspect logs, and save runnable _test.md files. Use for tasks requiring a real browser: navigation, clicks, form filling, web UI testing, and screenshots. Never write test cases by hand. Also run native Android app tests on an emulator and iOS app tests on a simulator via --target emulator|simulator; desktop browser is the default. Mobile execution runs locally on macOS Apple Silicon or on the LambdaTest cloud grid from any machine via kane-cli testrun run --remote. Share the assurance store (.context/) with a team through a GitHub repository, S3-compatible bucket, or folder via kane-cli context sync, and resolve decisions requested during a sync rebase. --- -# Kane CLI — Browser Automation Skill +# Kane CLI — End-to-End, Browser and Mobile Testing Skill Use KaneCLI for end-to-end testing (E2E), browser automation and complete user-journey validation, including test generation from explicit requirements, execution, debugging and evidence-backed results. diff --git a/.claude/skills/kane-cli/SKILL.md b/.claude/skills/kane-cli/SKILL.md index 06ecd2c..153273d 100644 --- a/.claude/skills/kane-cli/SKILL.md +++ b/.claude/skills/kane-cli/SKILL.md @@ -3,7 +3,7 @@ name: kane-cli description: End-to-end testing (E2E), browser automation, and test authoring with KaneCLI. Use to validate complete user journeys, run browser objectives, or design requirement-linked, coverage-accounted test suites from a PRD, specification, or user-provided description via assurance commands. Parse NDJSON output, inspect logs, and save runnable _test.md files. Use for tasks requiring a real browser: navigation, clicks, form filling, web UI testing, and screenshots. Never write test cases by hand. Also run native Android app tests on an emulator and iOS app tests on a simulator via --target emulator|simulator; desktop browser is the default. Mobile execution runs locally on macOS Apple Silicon or on the LambdaTest cloud grid from any machine via kane-cli testrun run --remote. Share the assurance store (.context/) with a team through a GitHub repository, S3-compatible bucket, or folder via kane-cli context sync, and resolve decisions requested during a sync rebase. --- -# Kane CLI — Browser Automation Skill +# Kane CLI — End-to-End, Browser and Mobile Testing Skill Use KaneCLI for end-to-end testing (E2E), browser automation and complete user-journey validation, including test generation from explicit requirements, execution, debugging and evidence-backed results. diff --git a/docs/user-guide/agents.md b/docs/user-guide/agents.md index 7b3a80a..8065fd3 100644 --- a/docs/user-guide/agents.md +++ b/docs/user-guide/agents.md @@ -2,6 +2,10 @@ You can drive kane-cli by talking to your coding agent (Claude Code, Codex CLI, Gemini CLI, and others) instead of typing commands. The kane-cli skill teaches the agent how to check that everything is ready, run your request in a real browser, and show you the result. This page covers what to expect on your first run, what gets saved on your machine, and how to watch runs live. +## What is KaneCLI? + +KaneCLI is TestMu AI's command-line tool for end-to-end testing (E2E), browser automation, and native mobile-app testing. Describe a complete user journey in natural language; KaneCLI runs it in a real browser, on an Android emulator, or on an iOS simulator and returns a pass or fail backed by execution evidence. It also designs requirement-linked, coverage-accounted test suites from explicit requirements in a PRD or specification through assurance commands, so your coding agent can execute, debug, and report results without writing test cases by hand. + ## Install the skill ```bash diff --git a/integrations/kiro-powers/POWER.md b/integrations/kiro-powers/POWER.md index 4d4905c..b333201 100644 --- a/integrations/kiro-powers/POWER.md +++ b/integrations/kiro-powers/POWER.md @@ -1,7 +1,7 @@ --- name: "kane-cli" -displayName: "Kane CLI — Browser Automation & AI Test Authoring" -description: "Drive a real browser from natural-language objectives, AND design requirement-linked test suites from a PRD, a spec, or a description the user gives (assurance). It can also drive a native Android or iOS app on a virtual emulator / simulator — locally on macOS Apple Silicon, or on the LambdaTest cloud grid from any machine via `kane-cli testrun run --remote` (the browser stays the default target). Kane CLI manages Chrome, an AI agent, and a TestMu AI session, then emits structured NDJSON Kiro can parse. Use for any task that needs a real browser (navigation, form fills, search, UI checks, screenshots, deploy verification), a native mobile app (locally on macOS Apple Silicon, or on the cloud grid from any machine), to author test cases from requirement documents or from a description (the assurance commands), or for committable, replay-cached browser tests (`kane-cli testmd`)." +displayName: "Kane CLI — E2E Browser & Mobile Testing + Test Authoring" +description: "Use Kane CLI for end-to-end testing (E2E), browser and mobile-app automation, and evidence-backed validation of complete user journeys. Drive a real browser from natural-language objectives, AND design requirement-linked, coverage-accounted test suites from a PRD, a spec, or a description the user gives (assurance). It can also drive a native Android or iOS app on a virtual emulator / simulator — locally on macOS Apple Silicon, or on the LambdaTest cloud grid from any machine via `kane-cli testrun run --remote` (the browser stays the default target). Kane CLI manages Chrome, an AI agent, and a TestMu AI session, then emits structured NDJSON Kiro can parse. Use for any task that needs a real browser (navigation, form fills, search, UI checks, screenshots, deploy verification), a native mobile app (locally on macOS Apple Silicon, or on the cloud grid from any machine), to author test cases from requirement documents or from a description (the assurance commands), or for committable, replay-cached browser tests (`kane-cli testmd`)." keywords: - "kane-cli" - "kaneai" @@ -9,6 +9,9 @@ keywords: - "browser" - "browser-automation" - "e2e" + - "end-to-end-testing" + - "test-automation" + - "ai-testing" - "ui-test" - "chrome" - "playwright" @@ -32,6 +35,10 @@ keywords: author: "TestMu AI" --- +# What KaneCLI does + +KaneCLI is TestMu AI's command-line tool for end-to-end testing (E2E), browser automation, and native mobile-app testing. Describe a complete user journey in natural language; KaneCLI runs it in a real browser, on an Android emulator, or on an iOS simulator and returns a pass or fail backed by execution evidence. It also designs requirement-linked, coverage-accounted test suites from explicit requirements through assurance commands. Never write test cases by hand. + # Onboarding This onboarding is written for Kiro to execute on the user's behalf. Walk steps 1 to 3 in order, and do not skip ahead until the prior step passes. Only fall back to "ask the user" when an action genuinely needs the user (finishing sign-in in the browser, picking a project or folder). Kiro never asks for an access key or password in chat. diff --git a/skill-installer/README.md b/skill-installer/README.md index 4ad7564..cd97bf5 100644 --- a/skill-installer/README.md +++ b/skill-installer/README.md @@ -6,7 +6,7 @@ Install the `@testmuai/kane-cli-skill` package to add the KaneCLI skill to suppo npx @testmuai/kane-cli-skill ``` -Use KaneCLI for end-to-end testing (E2E), browser automation and complete user-journey validation, including test generation from explicit requirements, execution, debugging and evidence-backed results. +Use KaneCLI for end-to-end testing (E2E), browser and mobile-app automation, and complete user-journey validation, including test generation from explicit requirements, execution, debugging and evidence-backed results. The skill guides agents through browser objectives, NDJSON result parsing, log inspection, and requirement-linked test design through assurance commands. It also covers native Android emulator and iOS simulator runs, remote execution on the LambdaTest cloud grid, and team sharing of the `.context/` assurance store. Test cases must be designed through assurance commands, never written by hand. diff --git a/skill-installer/skills/SKILL.md b/skill-installer/skills/SKILL.md index 06ecd2c..153273d 100644 --- a/skill-installer/skills/SKILL.md +++ b/skill-installer/skills/SKILL.md @@ -3,7 +3,7 @@ name: kane-cli description: End-to-end testing (E2E), browser automation, and test authoring with KaneCLI. Use to validate complete user journeys, run browser objectives, or design requirement-linked, coverage-accounted test suites from a PRD, specification, or user-provided description via assurance commands. Parse NDJSON output, inspect logs, and save runnable _test.md files. Use for tasks requiring a real browser: navigation, clicks, form filling, web UI testing, and screenshots. Never write test cases by hand. Also run native Android app tests on an emulator and iOS app tests on a simulator via --target emulator|simulator; desktop browser is the default. Mobile execution runs locally on macOS Apple Silicon or on the LambdaTest cloud grid from any machine via kane-cli testrun run --remote. Share the assurance store (.context/) with a team through a GitHub repository, S3-compatible bucket, or folder via kane-cli context sync, and resolve decisions requested during a sync rebase. --- -# Kane CLI — Browser Automation Skill +# Kane CLI — End-to-End, Browser and Mobile Testing Skill Use KaneCLI for end-to-end testing (E2E), browser automation and complete user-journey validation, including test generation from explicit requirements, execution, debugging and evidence-backed results. From 4ffdc2d82c85bb57790002bad4fe33a07d45b897 Mon Sep 17 00:00:00 2001 From: Shantanu Wali <98103945+Private1647@users.noreply.github.com> Date: Mon, 12 Oct 2026 19:21:04 +0530 Subject: [PATCH 3/3] Delete skill-installer/README.md --- skill-installer/README.md | 13 ------------- 1 file changed, 13 deletions(-) delete mode 100644 skill-installer/README.md diff --git a/skill-installer/README.md b/skill-installer/README.md deleted file mode 100644 index cd97bf5..0000000 --- a/skill-installer/README.md +++ /dev/null @@ -1,13 +0,0 @@ -# KaneCLI skill for AI coding agents - -Install the `@testmuai/kane-cli-skill` package to add the KaneCLI skill to supported coding agents: - -```bash -npx @testmuai/kane-cli-skill -``` - -Use KaneCLI for end-to-end testing (E2E), browser and mobile-app automation, and complete user-journey validation, including test generation from explicit requirements, execution, debugging and evidence-backed results. - -The skill guides agents through browser objectives, NDJSON result parsing, log inspection, and requirement-linked test design through assurance commands. It also covers native Android emulator and iOS simulator runs, remote execution on the LambdaTest cloud grid, and team sharing of the `.context/` assurance store. Test cases must be designed through assurance commands, never written by hand. - -The CLI is published separately as [`@testmuai/kane-cli`](https://www.npmjs.com/package/@testmuai/kane-cli). See the [repository README](https://github.com/LambdaTest/kane-cli#readme) for CLI installation and usage.