agentleFS
pskoettpskoett/pmx-canvas/skills/playwright-cli/SKILL.md

playwright-cli

Skill30 starsChanged 9 days agoMITView on GitHub

Browser automation via the Playwright CLI for validating PMX Canvas, embedded web artifacts, and external integrations from the terminal. Use when you need to open pages, click through UI flows, inspect element structure, take screenshots, or verify that a canvas-hosted app actually works in the browser.

  • Installs packages

180 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use fabric-sdk, ecosystem-reference and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    fabric-sdk

    How to use @microsoft/fabric-app-data to connect web applications to Fabric data sources at runtime. Build browser-based apps that query semantic models via DAX using the FabricClient API.

    Also in 9 projects that use this

  • naman10parikhSkill

    ecosystem-reference

    Quick-access directory of Claude Code ecosystem repos, skills, plugins, MCPs, and patterns. Use when improving the harness.

    Also in 5 projects that use this

  • naman10parikhSkill

    fractal-delegation

    Also in 5 projects that use this

  • MicrosoftSkill

    schema-discovery

    Explore Power BI semantic model schemas using DAX INFO functions. Progressive metadata discovery strategy, scope estimation, and narrowing techniques for tables, columns, measures, and relationships.

    Also in 9 projects that use this

  • +6 more from naman10parikh
  • +2 more from microsoft

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 6 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 161 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when PMX Canvas work needs a real browser check instead of static inspection.

    line 8
  2. Distinctive:

    Verify a PMX Canvas UI flow after changing the client

    line 12
  3. Distinctive:

    Read the saved snapshot file to find element refs

    line 30
  4. Distinctive:

    Verify with another snapshot or a screenshot

    line 32
  5. Very specific:

    Start the canvas first: bun run src/cli/index.ts --no-open

    line 58
  6. Very specific:

    Use this skill after canvas_app { action: "build-artifact" } when you need browser validation

    line 59
  7. Distinctive:

    Prefer visible browser automation for UI investigation so the human can follow along

    line 60
  8. Very specific:

    Use pmx-canvas to create, pin, connect, and inspect nodes

    line 65
  9. Very specific:

    Use web-artifacts-builder to scaffold richer React/shadcn artifacts

    line 66
  10. Distinctive:

    Use this skill to validate the generated artifact route and embedded canvas node in a browser

    line 67

“Common” is measured: kept by at least 6 in 10 of the 161 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Playwright CLI

Use this skill when PMX Canvas work needs a real browser check instead of static inspection.

When To Use

  • Verify a PMX Canvas UI flow after changing the client
  • Open an embedded mcp-app or /artifact?path=... route and confirm it renders
  • Click through context menus, pins, groups, snapshots, and other browser-only interactions
  • Capture screenshots or accessibility snapshots while keeping terminal context small

Prerequisites

npm install -g @playwright/cli@latest
playwright-cli --version

Requires Node.js 18+.

Core Workflow

  1. Open the target URL with playwright-cli open <url>
  2. Capture a structural snapshot with playwright-cli snapshot
  3. Read the saved snapshot file to find element refs
  4. Interact with the page using click, fill, press, or goto
  5. Verify with another snapshot or a screenshot
  6. Close the session when done

For PMX Canvas work, prefer a named session so you can keep a browser attached to the canvas while testing artifact tabs separately.

playwright-cli -s=canvas open http://localhost:4313
playwright-cli -s=canvas snapshot
playwright-cli -s=canvas screenshot
playwright-cli -s=canvas close

Commands You Will Use Most

  • open [url] — launch browser and optionally navigate
  • goto <url> — move to another page
  • snapshot — save page structure to disk
  • screenshot [ref] — capture page or element image
  • click <ref> — click an element by snapshot ref
  • fill <ref> <text> — fill an input or textarea
  • press <key> — send keyboard input
  • tab-new [url], tab-list, tab-select <index> — manage multiple pages
  • close — close the current browser session

PMX Canvas Guidance

  • Start the canvas first: bun run src/cli/index.ts --no-open
  • Use this skill after canvas_app { action: "build-artifact" } when you need browser validation
  • Prefer visible browser automation for UI investigation so the human can follow along
  • Store screenshots and snapshots on disk, then only read back the specific files you need

Pairing With Other Skills

  • Use pmx-canvas to create, pin, connect, and inspect nodes
  • Use web-artifacts-builder to scaffold richer React/shadcn artifacts
  • Use this skill to validate the generated artifact route and embedded canvas node in a browser

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.