Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By cn-dataworks
Composable agentic UI testing, dashboard validation, and browser automation suite
npx claudepluginhub cn-dataworks/web-squire-plugin --plugin web-squireRun a saved browser automation workflow with configurable skill, mode, and vision settings
Parallel data gathering — discovers automation YAML stories, fans out data-gatherer agents, aggregates results with monitoring alerts
Discover dashboard test stories from YAML files, fan out parallel `dashboard-tester` instances to validate each, then aggregate and report pass/fail results with screenshots.
Discover user stories from YAML files, fan out parallel `qa-agent` instances to validate each story, then aggregate and report pass/fail results with screenshots.
Visual testing agent for Power BI and complex dashboards rendered in canvas/SVG. Reports pass/fail with visual findings and screenshots at every step. Supports parallel instances. Keywords - dashboard, Power BI, Tableau, canvas, SVG, visual testing.
Data extraction agent for web scraping, monitoring, and data gathering. Uses Playwright CLI for standard scraping or Chrome MCP for SSO/auth-dependent pages. Supports parallel instances (Playwright only). Keywords - scrape, data, extract, monitor, gather.
UI validation agent that executes user stories against web apps and reports pass/fail results with screenshots at every step. Use for QA, acceptance testing, user story validation, or UI verification. Supports parallel instances. Keywords - QA, validation, user story, UI testing, acceptance testing.
Observable browser automation using Chrome MCP tools. Use when you need to browse websites, take screenshots, interact with web pages, or perform browser tasks in your current Chrome. Keywords - browse, screenshot, browser, chrome, ui testing, observable.
Headless browser automation using Playwright CLI. Use when you need headless browsing, parallel browser sessions, UI testing, screenshots, web scraping, or browser automation that can run in the background. Keywords - playwright, headless, browser, test, screenshot, scrape, parallel.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Canary browser automation + recorded QA sessions: a sandbox scripting reference, verify/automate/session/review skills, JTBD subagents, and /canary slash commands.
Playwright E2E test debugging and interactive browser exploration. Runs tests with action capture (DOM snapshots, network, console, screenshots), diagnoses failures, and provides browser tools for navigating, clicking, and inspecting pages through ARIA snapshots.
Browser automation and E2E testing with Playwright. Auto-detects dev servers, writes clean test scripts. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use for cross-browser testing, visual regression, API testing, component testing in TypeScript/JavaScript and Python projects.
AI-powered browser automation -- lets Claude control real web browsers to navigate, click, type, extract content, and automate workflows
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Create and manage Power BI Enhanced Report Format (PBIR) visuals with templates. Includes visual creation from templates and extraction of existing visuals to reusable templates.
PBI Squire - Complete Power BI development assistant. Diagnose issues, create DAX measures, transform data with M code, document dashboards, and deploy changes.
Composable agentic UI testing, dashboard validation, and browser automation suite for Claude Code.
Built on the four-layer composable architecture from Bowser: Skill → Subagent → Command → Just.
Get from zero to running tests in 5 minutes.
Inside Claude Code:
/plugin marketplace add https://github.com/cn-dataworks/web-squire-plugin
/plugin install web-squire
See INSTALL.md for alternative install methods and full details.
npm install -g @playwright/cli@latest
playwright-cli --help # verify it works
In your project, create ai_user_stories/web/smoke-test.yaml:
stories:
- name: "Homepage loads correctly"
url: "https://myapp.example.com"
workflow: |
Navigate to https://myapp.example.com
Verify the page loads without errors
Verify a navigation bar is visible at the top
Verify the main content area contains a heading
/web-squire:ui-review
The command discovers your story files, spawns one QA agent per story, and each agent:
screenshots/qa/✅ SUCCESS
**Story:** Homepage loads correctly
**Steps:** 4/4 passed
**Screenshots:** ./screenshots/qa/homepage-loads-correctly_a1b2c3d4/
| # | Step | Status | Screenshot |
| --- | --- | --- | --- |
| 1 | Navigate to homepage | PASS | 00_navigate.png |
| 2 | Verify page loads | PASS | 01_page-loads.png |
| 3 | Verify nav bar | PASS | 02_nav-bar.png |
| 4 | Verify heading | PASS | 03_heading.png |
RESULT: PASS | Steps: 4/4
| I want to... | Command | Story directory |
|---|---|---|
| Test UI workflows (login, forms, navigation) | /web-squire:ui-review | ai_user_stories/web/ |
| Validate dashboards visually (Power BI, Tableau) | /web-squire:test-dashboards | ai_user_stories/dashboard/ |
| Scrape data or monitor pages | /web-squire:run-browser-automation | ai_user_stories/browser_automation/ |
| Run a single saved workflow | /web-squire:automate <file> | Any path |
| Situation | Use | Why |
|---|---|---|
| Standard web testing (default) | playwright-cli | Headless, fast, supports parallel sessions |
| Site requires SSO/cookies/extensions | chrome-mcp | Uses your real Chrome session with existing auth |
| Not sure | playwright-cli | Works for 90% of cases |
Note: When using commands (Layer 3), you don't pick skills directly — the agents choose automatically. Skill selection matters when you invoke skills directly at Layer 1.
Stories use a stories array with name, url, and workflow keys. The workflow field is natural language — be specific about what to verify.
/web-squire:ui-review)stories:
- name: "User can login"
url: "https://myapp.example.com/login"
workflow: |
Navigate to https://myapp.example.com/login
Verify the login page loads with username and password fields
Enter username "testuser" and password "testpass"
Click the Login button
Verify the dashboard page loads
Verify the user's name appears in the top-right corner
- name: "Dashboard shows recent activity"
url: "https://myapp.example.com/dashboard"
workflow: |
Navigate to https://myapp.example.com/dashboard
Verify the dashboard loads with an activity feed
Verify at least 3 activity items are visible
/web-squire:test-dashboards)Dashboard tests use vision mode automatically — the agent screenshots each step and visually reads chart values, KPIs, and filter states from the image.
stories:
- name: "Revenue dashboard shows correct Q4 data"
url: "https://app.powerbi.com/reports/abc123/ReportSection"
workflow: |
Navigate to the revenue dashboard
Verify the dashboard loads with at least 3 chart tiles
Click the Q4 filter button
Verify the revenue chart updates to show Q4 data
Verify the KPI card shows revenue above $2M
Hover over the trend line chart and verify the tooltip shows monthly values
/web-squire:run-browser-automation)