What it does
AI-powered E2E testing MCP server. Detects and auto-fixes UI bugs via DevQA Loop and Vision AI.
- Connects Runs on your computer
- Account or key Needs ANTHROPIC_API_KEY, OPENAI_API_KEY
- Category Developer tools
Use together with
Skills that teach the AI this kind of work; they work alongside this one
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Why it ranks here
Lists are ordered by a usage score (out of 100) built from these parts
| Popularity | 6/80 | GitHub stars or weekly downloads: the larger counts 60, the smaller 20 |
|---|---|---|
| Freshness | 12/12 | Full marks for a release or code change within 30 days |
| Still answering | 0/8 | The cloud endpoint answered at the last check |
| Usage score | 18/100 |
Quality: Passed 3/3 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)
Install
Pick the AI app you use, then copy the settings.
Let your AI install it with one sentence
Please install AWT (AI Watch Tester). Follow https://mcp.popnx.com/i/ksgisang-awt.md, show me the commands and wait for my OK before running them.Paste it into an AI that can work on your computer (such as Claude Code or Cursor). It reads our steps, shows you the commands and waits for your OK. No key, no sign-up. · See the full text your AI reads
Passed 3/3 checks · Runs on your computer · ✓ Commands checked Nov 14, 2026
First: which AI do you use?
Pick your app and the steps appear below.
Works with Claude, with some setup first
You need a AWT (AI Watch Tester) key (create it on the maker’s site) · Install Python (uv) on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
Let AI install it
Copy this message into a Claude chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.
Please install the MCP server AWT (AI Watch Tester) for Claude on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "awt": { "command": "uvx", "args": [ "aat-devqa" ], "env": { "ANTHROPIC_API_KEY": "your-value", "OPENAI_API_KEY": "your-value" } } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) For ANTHROPIC_API_KEY, OPENAI_API_KEY, leave "your-value" in place and tell me to paste the real value myself into the file or the app’s field. Never ask me to type a key in chat. 5) Do what we agreed, then check that the AWT (AI Watch Tester) tools really show up.This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.
Install uv (if you don’t have it)
Already installed? Check first · Open Terminal, type this command and press Enter
uv --version- A version number such as uv … = installed, skip this step
- "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
How to open Terminal
Mac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required
When it’s done, close Terminal, open it again and run the same command. You should see a version number:
uv --versionInstall once; it works for everything that needs uv
Sign up and create a AWT (AI Watch Tester) key
Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.
How to get a key is in the maker’s README below
Open the Claude desktop app’s settings file
SettingsDeveloperEdit Config
Paste these settings and save the file
{ "mcpServers": { "awt": { "command": "uvx", "args": [ "aat-devqa" ], "env": { "ANTHROPIC_API_KEY": "your-value", "OPENAI_API_KEY": "your-value" } } } }Paste the key only into the app’s field, never into a chat or to anyone
Quit Claude and open it again
Try it
Use AWT (AI Watch Tester) and tell me what you can do for me, then show me one thing✓ If Claude says it is using AWT (AI Watch Tester) or shows a AWT (AI Watch Tester) tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
ChatGPT cannot connect AWT (AI Watch Tester) yet
AWT (AI Watch Tester) runs on your computer, but ChatGPT can only connect servers that run on the web
What you can do instead
A · Use an app that can connect AWT (AI Watch Tester)
- You need a AWT (AI Watch Tester) key (create it on the maker’s site) · Install Python (uv) on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
- You need a AWT (AI Watch Tester) key (create it on the maker’s site) · Install Python (uv) on your computer first (one time)
- You need a AWT (AI Watch Tester) key (create it on the maker’s site) · Install Python (uv) on your computer first (one time)
- You need a AWT (AI Watch Tester) key (create it on the maker’s site) · Install Python (uv) on your computer first (one time)
B · Others in Developer tools that work with ChatGPT
Picked from the most used in the same category, only ones that connect by address with no key
- Sentry✓ ChatGPT
- Compiler Explorer✓ ChatGPT
- GitDiagram✓ ChatGPT
Works with Claude Code, with some setup first
You need a AWT (AI Watch Tester) key (create it on the maker’s site) · Install Python (uv) on your computer first (one time)
Let AI install it
Copy this message into a Claude Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.
Please install the MCP server AWT (AI Watch Tester) for Claude Code on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): claude mcp add --scope user awt --env ANTHROPIC_API_KEY=your-value --env OPENAI_API_KEY=your-value -- uvx aat-devqa 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) For ANTHROPIC_API_KEY, OPENAI_API_KEY, leave "your-value" in place and tell me to paste the real value myself into the file or the app’s field. Never ask me to type a key in chat. 5) Do what we agreed, then check that the AWT (AI Watch Tester) tools really show up.This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.
Install uv (if you don’t have it)
Already installed? Check first · Open Terminal, type this command and press Enter
uv --version- A version number such as uv … = installed, skip this step
- "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
How to open Terminal
Mac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required
When it’s done, close Terminal, open it again and run the same command. You should see a version number:
uv --versionInstall once; it works for everything that needs uv
Sign up and create a AWT (AI Watch Tester) key
Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.
How to get a key is in the maker’s README below
Open Terminal
Mac: press Command+Space and type Terminal · Windows: open PowerShell
Paste this command and press Enter
claude mcp add --scope user awt --env ANTHROPIC_API_KEY=your-value --env OPENAI_API_KEY=your-value -- uvx aat-devqaReplace “your-value” with your key before pressing Enter
Paste the key only into the app’s field, never into a chat or to anyone
Type /mcp in Claude Code
You should see AWT (AI Watch Tester) listed as connected
Try it
Use AWT (AI Watch Tester) and tell me what you can do for me, then show me one thing✓ If Claude Code says it is using AWT (AI Watch Tester) or shows a AWT (AI Watch Tester) tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with Cursor, with some setup first
You need a AWT (AI Watch Tester) key (create it on the maker’s site) · Install Python (uv) on your computer first (one time)
Let AI install it
Copy this message into a Cursor chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.
Please install the MCP server AWT (AI Watch Tester) for Cursor on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "awt": { "command": "uvx", "args": [ "aat-devqa" ], "env": { "ANTHROPIC_API_KEY": "your-value", "OPENAI_API_KEY": "your-value" } } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) For ANTHROPIC_API_KEY, OPENAI_API_KEY, leave "your-value" in place and tell me to paste the real value myself into the file or the app’s field. Never ask me to type a key in chat. 5) Do what we agreed, then check that the AWT (AI Watch Tester) tools really show up.This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.
Install uv (if you don’t have it)
Already installed? Check first · Open Terminal, type this command and press Enter
uv --version- A version number such as uv … = installed, skip this step
- "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
How to open Terminal
Mac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required
When it’s done, close Terminal, open it again and run the same command. You should see a version number:
uv --versionInstall once; it works for everything that needs uv
Sign up and create a AWT (AI Watch Tester) key
Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.
How to get a key is in the maker’s README below
Fill in your key
In the AWT (AI Watch Tester) settings, ANTHROPIC_API_KEY, OPENAI_API_KEY is empty; add your key and save
Paste the key only into the app’s field, never into a chat or to anyone
Open the AI chat in Cursor in Agent mode
Try it
Use AWT (AI Watch Tester) and tell me what you can do for me, then show me one thing✓ If Cursor says it is using AWT (AI Watch Tester) or shows a AWT (AI Watch Tester) tool in the answer, you are connected
Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with VS Code, with some setup first
You need a AWT (AI Watch Tester) key (create it on the maker’s site) · Install Python (uv) on your computer first (one time)
Let AI install it
Copy this message into a VS Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.
Please install the MCP server AWT (AI Watch Tester) for VS Code on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "servers": { "awt": { "type": "stdio", "command": "uvx", "args": [ "aat-devqa" ], "env": { "ANTHROPIC_API_KEY": "your-value", "OPENAI_API_KEY": "your-value" } } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) For ANTHROPIC_API_KEY, OPENAI_API_KEY, leave "your-value" in place and tell me to paste the real value myself into the file or the app’s field. Never ask me to type a key in chat. 5) Do what we agreed, then check that the AWT (AI Watch Tester) tools really show up.This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.
Install uv (if you don’t have it)
Already installed? Check first · Open Terminal, type this command and press Enter
uv --version- A version number such as uv … = installed, skip this step
- "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
How to open Terminal
Mac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required
When it’s done, close Terminal, open it again and run the same command. You should see a version number:
uv --versionInstall once; it works for everything that needs uv
Sign up and create a AWT (AI Watch Tester) key
Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.
How to get a key is in the maker’s README below
Fill in your key
In the AWT (AI Watch Tester) settings, ANTHROPIC_API_KEY, OPENAI_API_KEY is empty; add your key and save
Paste the key only into the app’s field, never into a chat or to anyone
Open the AI chat in VS Code in Agent mode
Try it
Use AWT (AI Watch Tester) and tell me what you can do for me, then show me one thing✓ If VS Code says it is using AWT (AI Watch Tester) or shows a AWT (AI Watch Tester) tool in the answer, you are connected
Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.
JSON settings are under “For developers” below
For developers: Terminal commands and JSON settings
Installed on your computer
Claude Code
claude mcp add --scope user awt --env ANTHROPIC_API_KEY=your-value --env OPENAI_API_KEY=your-value -- uvx aat-devqaClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"awt": {
"command": "uvx",
"args": [
"aat-devqa"
],
"env": {
"ANTHROPIC_API_KEY": "your-value",
"OPENAI_API_KEY": "your-value"
}
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"awt": {
"command": "uvx",
"args": [
"aat-devqa"
],
"env": {
"ANTHROPIC_API_KEY": "your-value",
"OPENAI_API_KEY": "your-value"
}
}
}
}VS Code (mcp.json)
{
"servers": {
"awt": {
"type": "stdio",
"command": "uvx",
"args": [
"aat-devqa"
],
"env": {
"ANTHROPIC_API_KEY": "your-value",
"OPENAI_API_KEY": "your-value"
}
}
}
}Values you fill in
ANTHROPIC_API_KEYsecret required envAnthropic API key (optional — required only when using provider=claude)OPENAI_API_KEYsecret required envOpenAI API key (optional — required only when using provider=openai)
Descriptions are as written by the maker.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
At a glance
Which apps can use it
Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Run on your computer in
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
Related guides
What it can do
Runs on your computer; the tool list appears in your AI app after you install it.
Basic checksi
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 19, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account ksgisang, which owns the repo
- ✓ Pass
Still maintained
Code last changed 13 days ago
- ✓ Pass
Has a licence
Uses AGPL-3.0
- – Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
- – Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
- … Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints
Published vulnerabilities (OSV.dev)
No entries on OSV.dev for aat-devqa@1.8.0
Checks only this package version, not every dependency · checked Nov 15, 2026
Makers: ask for a re-check or report wrong info
For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/servers/ksgisang-awt)Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
User reviews
No reviews yet
Compared with others in Developer toolsi
- More stars than 77% of the other 6116 servers in this category
- Published to the registry more recently than 48% of the other 6116 servers in this category
- Basic checks equal to or better than 99% of the other 6116 servers in this category
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
Common questions
Is AWT (AI Watch Tester) safe?
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
What keys or codes does it need?
You need to fill in: ANTHROPIC_API_KEY, OPENAI_API_KEY
Does it run on my computer or in the cloud?
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
Is it still maintained?
The GitHub repo last changed 13 days ago, and the latest version (1.8.0) reached the registry 35 days ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
What can I use instead?
In the same category: GitDiagram, Appllama, Cloudflare MCP, Omnara, Repowise
Similar alternatives
Same category, other makers, commands already checked. Official ones first, then by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
GitDiagram
Architecture diagrams, explanations and Mermaid source for public GitHub repositories.
Appllama
Study screens, flows and paywalls from top-earning iOS apps, then build from what wins.
Cloudflare MCP
Cloudflare MCP servers
Omnara
Deploy durable AI agents with Omnara, an open-source managed-agent platform.
Repowise
Codebase intelligence for AI coding agents: graph, git history, docs, decisions, code health.
| This one AWT (AI Watch Tester) | GitDiagram | Appllama | Cloudflare MCP | Omnara | Repowise | |
|---|---|---|---|---|---|---|
| Runs where | Installs on your computer | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Cloud or install on your computer |
| Needs a key | Yes | No | No | No | No | No |
| Add with + in Claude | No | No | No | Yes | No | No |
| Basic checks | 3/3 | 4/4 | 4/4 | 4/4 | 4/4 | 5/5 |
| License | AGPL-3.0 | MIT | MIT | Apache-2.0 | Apache-2.0 | AGPL-3.0 |
| Price | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry |
README from the maker
Open the README
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
AWT — Eyes and Hands for Your AI Coding Tool
Your AI coding tool is smart. But it can't see or click a web page. AWT gives it a real browser — so it can test, find bugs, and fix them without you lifting a finger.
Works without AI API — write YAML scenarios manually and run
aat run. No API key needed. AI coding tools make it easier, but are not required.
What is AWT?
AWT is the execution engine for AI-powered E2E testing. Your AI coding tool designs the tests; AWT runs them in a real browser with Playwright.
How it works in Skill Mode (no extra AI API key needed):
You: "Test the login flow on https://mysite.com"
Your AI coding tool: → Writes 5 YAML scenarios (30 steps) → Runs: aat run scenarios/ → Reads failure: "Step 4: Dashboard text not visible" → Reads screenshot + source code → Fixes src/pages/login.js:23 → Re-runs: aat run scenarios/ → All 5 scenarios pass ✓
Key capabilities:
- Execute tests in a real browser with human-like mouse/keyboard interaction
- See — take screenshots, detect elements via OCR and image matching
- Report — step-by-step pass/fail with error details and screenshots
- Self-heal (CLI mode) —
aat loopauto-fixes failures with its own AI - Learn — successful matches stored in SQLite, getting faster over time
Installation
Install the aat command first — every route below drives it:
pip install aat-devqa
python -m playwright install chromium
Claude Code plugin (recommended)
This repository is a plugin bundle that ships the awt skill.
claude plugin marketplace add ksgisang/awt-skill
claude plugin install ai-watch-tester@awt
Verify what got installed:
claude plugin details ai-watch-tester@awt
You should see Skills (1) awt.
Other AI coding tools
The skill is a directory of Markdown, so anything that reads skills can take it:
npx skills add ksgisang/awt-skill --skill awt -g
Or copy it by hand, globally or per project:
git clone https://github.com/ksgisang/awt-skill.git /tmp/awt-skill
cp -r /tmp/awt-skill/skills/awt ~/.claude/skills/awt # or .claude/skills/awt rm -rf /tmp/awt-skill
After installation, the skill auto-triggers on testing-related prompts.
Updating
claude plugin update ai-watch-tester@awt # plugin
npx skills add ksgisang/awt-skill --skill awt -g -y # skill only
For hand-copied installations: cd ~/.claude/skills/awt && git pull
MCP tools (optional, separate)
The skill drives the aat command directly, which is all it needs. If you would rather call AWT as MCP tools (aat_scan, aat_run_skill_mode, aat_diff, and nine more), the server lives in the main repository and is installed separately:
pip install "mcp[cli]>=1.0.0"
git clone https://github.com/ksgisang/AI-Watch-Tester.git claude mcp add awt -- python3 "$PWD/AI-Watch-Tester/mcp/server.py"
Setup for other MCP clients is in mcp/README.md. This plugin does not bundle that server: the Claude Code plugin directory accepts MCP servers that run on your own machine only from verified organizations, so the bundle ships the skill alone.
Comparison with Other Testing Skills
| Feature | webapp-testing | playwright-skill | AWT |
|---|---|---|---|
| Scenario format | Python scripts | Python scripts | Declarative YAML |
| No-code test creation | No | No | Yes |
| Natural language → test | No | No | Yes |
| Self-healing loop | No | No | Yes (DevQA Loop) |
| Auto-fix on failure | No | No | Yes (AI → PR) |
| Visual matching (OpenCV + OCR) | No | No | Yes (OpenCV + OCR) |
| Pattern learning | No | No | Yes (SQLite) |
| Server lifecycle mgmt | Yes | Yes | Yes (aat dashboard) |
| Multiple AI providers | No | No | Yes (5 providers) |
| Human-like interaction | No | No | Yes (Bezier mouse) |
| Approval modes | No | No | Yes (manual/branch/auto) |
| Cost optimization | N/A | N/A | $0.02–0.05/test |
| Live screenshots | No | Screenshot only | Yes (WebSocket stream) |
| Multi-language OCR | No | No | Yes (10+ languages) |
| Offline support | No | No | Yes (Ollama) |
| Cost tracking | No | No | Yes (per-call logging + aat cost) |
| Source code analysis | No | No | Yes (Skill-exclusive) |
| Scenario caching | No | No | Yes (same spec = no re-call) |
| Browser test overlay | No | No | Yes (live step progress) |
| Dependency ordering | No | No | Yes (depends_on field) |
| Skill Mode (no extra AI cost) | No | No | Yes |
| Canvas/Flutter OCR fallback | No | No | Yes (auto) |
| Platform auto-detection | No | No | Yes (7 frameworks) |
| Structured failure diagnosis | No | No | Yes (AI-independent) |
| Multi-document YAML | No | No | Yes (--- separator) |
| Strict validation | No | No | Yes (aat validate --strict) |
When to use each:
- webapp-testing — Quick one-off Playwright scripts for simple page checks
- playwright-skill — When you need fine-grained Playwright API control
- AWT Skill Mode — Your AI coding tool designs tests, AWT executes them. No extra AI API key needed.
- AWT CLI Mode — Standalone automated testing with
aat generate+aat loopfor CI/CD
Supported AI Coding Tools
AWT follows the Agent Skills open standard and works with:
| Tool | Status |
|---|---|
| Claude Code | Supported |
| Cursor | Compatible |
| Codex | Compatible |
| Gemini CLI | Compatible |
| Amp | Compatible |
| Cline | Compatible |
| Aider | Compatible |
| Windsurf | Compatible |
| Roo Code | Compatible |
| PearAI | Compatible |
| Antigravity | Supported |
Quick Example
YAML Scenario
id: "SC-001"
name: "User Login" tags: ["auth", "login"] depends_on: ["SC-000"] steps:
- step: 1 action: navigate value: "{{url}}/login" description: "Go to login page"
- step: 2 action: find_and_type target: text: "Email" match_method: ocr value: "test@example.com" humanize: true description: "Enter email"
- step: 3 action: find_and_click target: text: "Login" description: "Click login button"
- step: 4 action: assert assert_type: text_visible expected:
- type: text_visible value: "Welcome back" description: "Verify login success"
Natural Language (in Claude Code)
"Login to mysite.com with test@example.com, then check if the dashboard loads"
AWT converts this to a YAML scenario and executes it automatically.
5-Step DevQA Workflow
Scan → Plan → Review → Execute → Heal
↑ | └─── Loop back on failure ────────┘
- Scan — Crawl site, analyze DOM, detect features
- Plan — AI generates YAML test scenarios
- Review — User reviews/edits before execution
- Execute — Playwright runs with live screenshots
- Heal — AI analyzes failure → suggests fix → re-tests
AI Providers
| Provider | Vision | Cost | Offline |
|---|---|---|---|
| Claude (default) | Yes | Medium | No |
| OpenAI (GPT-4o) | Yes | Higher | No |
| Gemini (default: free) | Yes | Free tier | Yes |
| DeepSeek | No | Low | No |
| Ollama | No | Free | Yes |
Project Structure
awt-skill/ # ← this repository is the plugin folder
├── .claude-plugin/ │ ├── plugin.json # Plugin manifest │ └── marketplace.json # Marketplace entry for this one plugin ├── assets/ │ └── icon.png # Plugin icon ├── skills/ │ └── awt/ # ← Skill content (installed by npx skills) │ ├── SKILL.md # Main skill definition │ ├── references/ │ │ ├── scenario-schema.md # Full YAML schema reference │ │ ├── cli-reference.md # CLI command reference │ │ └── config-reference.md # Configuration options │ └── templates/ │ ├── scenario-template.yaml │ └── config-template.yaml ├── README.md ├── LICENSE ├── CONTRIBUTING.md └── package.json
Key CLI Commands
| Command | Description |
|---|---|
aat doctor | Check environment (Python, Playwright, Tesseract, AI) |
aat init | Initialize project + AI setup + environment check |
aat setup | Configure AI provider and API key |
aat generate | AI-generate scenarios (with cost estimate + caching) |
aat run --learn | Execute tests + learn from fixes (always use --learn) |
aat loop | Self-healing DevQA loop |
aat cost | View AI API usage costs |
aat validate --strict | Validate YAML + quality checks |
aat learn platform -p -t | Add platform-specific tip |
System Dependencies
macOS:
brew install python@3.12 tesseract
pipx install aat-devqa playwright install chromium
Linux (Ubuntu/Debian):
sudo apt install python3.12 python3.12-venv tesseract-ocr
pipx install aat-devqa playwright install chromium
Windows:
winget install Python.Python.3.12
choco install tesseract pip install aat-devqa playwright install chromium
After install, run aat doctor to verify everything works.
OCR language packs. Tesseract installs English only. If you test an app in another language, install that language's pack too — otherwise text assertions that fall back to OCR report not visible on page for text that is plainly there. aat doctor names any missing pack.
brew install tesseract-lang # macOS, all languages
sudo apt install tesseract-ocr-kor # Linux, one language
What this plugin runs, sends, and fetches
Everything below is in this repository in readable source. Nothing is minified, compiled, or downloaded at install time.
Runs on your machine: nothing of its own. This bundle contains no executable code. It is Markdown and YAML templates that tell your AI coding tool which aat commands to run, and your tool shows you each command before running it. The work is done by the aat command you installed with pip install aat-devqa, which drives a local Chromium through Playwright and, for OCR, the local tesseract binary. The rest of this section describes what aat does when you let it run, because that is what the skill asks for.
Writes to disk. Under your project: .aat/ (config, run history, screenshots, the SQLite learning database, the append-only audit log) and reports/. Under your home directory: ~/.awt/templates/ / for the element images AWT saves so it can find a target again after a selector breaks.
Sends over the network. There is no telemetry and no analytics. Every destination below is either one you named yourself or the single call AWT makes on its own, which is listed first so it is not buried:
- `api.github.com`, once a day, by AWT itself. The CLI asks for the latest release so it can print a hint when a newer one exists. No request body, no account, no machine id, no version string, nothing about what you are testing; the request is identical for every user. It times out after 3 seconds and every failure is swallowed, so blocking the host breaks nothing. This is the only call AWT initiates.
- The site you are testing. Chromium loads the URL in your scenario. That is the whole point of the tool, and no other site is contacted by a test run.
- An AI provider, only for the commands that need one —
aat generate,aat loop,aat devqa, and Vision matching. The request carries the page text or screenshot and your scenario. You choose the provider and supply the key; with Ollama the reque