Restructure AI docs as top-level section with linked prerequisites

Move AI docs from test-packages/ to top-level ai/ directory:
- ai/getting-started.md — plugin install (trimmed: removed common
  mistakes and best practices sections, renamed to "AI-Assisted Development")
- ai/test-packages/writing-with-agents.md — methodology with linked
  prerequisite pages instead of "fetch from llms.txt" instructions
- ai/test-packages/browser-observation.md — Playwright MCP guide

Sidebar: AI-Assisted Development is now a top-level category with
nested Test Packages sub-category.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: Luc45

docs/ai/getting-started.md

@@ -0,0 +1,60 @@
+---
+description: "Install the QIT plugin for Claude Code to get AI-powered test creation, debugging, and quality automation. For other AI assistants, use the QIT documentation index at llms.txt to provide context."
+---
+
+# AI-Assisted Development
+
+QIT integrates with AI assistants to help you develop test packages, debug failures, and automate quality workflows.
+
+## Claude Code Plugin (Recommended)
+
+The QIT CLI ships as a **Claude Code plugin**. Once installed, Claude can handle any QIT task autonomously — it fetches live documentation, runs commands, creates test packages, and debugs failures without you needing to provide manual context.
+
+### Install
+
+In Claude Code, run:
+
+```
+/plugin marketplace add woocommerce/qit-cli
+/plugin install qit@woocommerce-qit
+```
+
+That's it. Claude now has QIT expertise. Try asking:
+
+- "Run a security scan on my plugin"
+- "Create E2E tests for this extension"
+- "My QIT tests are failing, help me debug"
+- "Set up qit.json for this project"
+- "What test packages are available for cross-compatibility testing?"
+
+### How It Works
+
+The plugin provides a skill that uses **progressive disclosure** from QIT's live documentation:
+
+1. Claude fetches the [documentation index](https://qit.woo.com/docs/llms.txt) to find relevant pages
+2. It reads the specific docs needed for your task
+3. It acts on what it learned — running commands, writing code, interpreting results
+
+This means Claude always has current information, even as QIT evolves.
+
+### What Claude Can Do
+
+With the QIT plugin, Claude can:
+
+- **Run any QIT test** — managed tests, test packages, or both
+- **Create test packages** — follows a [structured methodology](./test-packages/writing-with-agents.md) that includes user research, UI observation, and persona-based test design
+- **Debug failures** — read CTRF reports, analyze artifacts, identify root causes
+- **Configure projects** — generate `qit.json` with profiles, environments, and groups
+- **Manage environments** — start, stop, and interact with Docker test environments
+- **Publish packages** — validate and publish test packages to the QIT registry
+
+---
+
+## Other AI Assistants
+
+If you're using GPT-4, GitHub Copilot, or another AI assistant, QIT provides two machine-readable documentation files you can feed to your AI:
+
+- **[llms.txt](https://qit.woo.com/docs/llms.txt)** — Documentation index with descriptions. Feed this to your AI and ask it to fetch the pages relevant to your task.
+- **[llms-full.txt](https://qit.woo.com/docs/llms-full.txt)** — Complete documentation in a single file. Use when your AI can accept large context.
+
+These follow the [llmstxt.org](https://llmstxt.org) standard and contain the same documentation that the Claude Code plugin accesses.

…st-packages/how-to/ai-browser-testing.md …/ai/test-packages/browser-observation.mddocs/test-packages/how-to/ai-browser-testing.md renamed to docs/ai/test-packages/browser-observation.md docs/test-packages/how-to/ai-browser-testing.md renamed to docs/ai/test-packages/browser-observation.md

@@ -8,16 +8,16 @@ This is the methodology to follow when creating QIT E2E test packages for a WooC
 
 ## Prerequisites
 
-Before starting, fetch and read the documentation pages you will need. Use the [documentation index](https://qit.woo.com/docs/llms.txt) to find the current pages for:
+Before starting, fetch and read the documentation pages you will need:
 
-- **How to create test packages** — scaffolding, manifest structure, package types
-- **Test package manifest reference** — all fields and validation rules for `qit-test.json`
-- **Test package lifecycle** — execution phases, database isolation, command context
-- **Global setup concepts** — what goes in globalSetup vs setup, cross-compatibility design
-- **Development workflow** — how to use `env:up`, `env:source`, `env:reset` for iterative testing
-- **How to write tests with AI browser observation** — using Playwright MCP to see the real UI
-- **How to handle secrets** — declaring and providing API keys and credentials
-- **Test results and artifacts** — CTRF format, blob directory, screenshots, traces
+- [How to Create Test Packages](/test-packages/how-to/create-packages/) — scaffolding, manifest structure, package types
+- [Test Package Manifest Reference](/test-packages/manifest/) — all fields and validation rules for `qit-test.json`
+- [Test Package Lifecycle](/test-packages/lifecycle/) — execution phases, database isolation, command context
+- [Global Setup Concepts](/test-packages/concepts/global-setup/) — what goes in globalSetup vs setup, cross-compatibility design
+- [Development Workflow](/environment/development-workflow/) — how to use `env:up`, `env:source`, `env:reset` for iterative testing
+- [AI Browser Observation](./browser-observation.md) — using Playwright MCP to see the real UI before writing selectors
+- [How to Handle Secrets](/test-packages/how-to/use-secrets/) — declaring and providing API keys and credentials
+- [Test Results and Artifacts](/test-packages/results/) — CTRF format, blob directory, screenshots, traces
 
 Also run `qit package:scaffold --help`, `qit env:up --help`, and `qit run:e2e --help` to get current command syntax. Never guess at flags — use `--help` output.
 
@@ -108,7 +108,7 @@ Use `qit env:up` to start a local environment with the extension and test packag
 
 **Do not skip this step.** Navigate the running site using Playwright MCP browser tools.
 
-Refer to the [browser observation guide](./ai-browser-testing.md) for detailed instructions.
+Refer to the [browser observation guide](./browser-observation.md) for detailed instructions.
 
 ### Explore the merchant experience (admin)
 

…t-packages/how-to/ai-test-methodology.md …/ai/test-packages/writing-with-agents.mddocs/test-packages/how-to/ai-test-methodology.md renamed to docs/ai/test-packages/writing-with-agents.md docs/test-packages/how-to/ai-test-methodology.md renamed to docs/ai/test-packages/writing-with-agents.md

@@ -108,7 +108,7 @@ qit run:security --help
 
 **[Configuration](configuration/)** — Save your test settings in `qit.json` so you don't retype them.
 
-**[AI-Assisted Testing](/test-packages/ai-development/)** — Use QIT with Claude Code for AI-powered test development and debugging.
+**[AI-Assisted Development](/ai/getting-started/)** — Use QIT with Claude Code for AI-powered test development and debugging.
 
 ---