Automated summary
Opens a URL through Playwright MCP, performs the described interactions (clicks, form fills, selections, key presses) and returns a report with DOM snapshots and before/after screenshots.
Strengths
- Chains navigation, initial snapshot, interactions and final verification in a single call
- Takes a free-form description of the actions to run, with no Playwright script to write
- Produces evidence of the outcome: DOM snapshot and screenshot of the final page state
- Delegates every MCP tool call to the zzaia-workspace-manager agent, keeping execution in one place
Limitations
- Requires a configured Playwright MCP server and the zzaia-workspace-manager agent to be available
- No explicit waiting, assertions or retry logic: the outcome depends entirely on the description supplied
- Leaves no reusable scenario behind — no test script is generated
To quickly check that a form or a flow works on a specific URL, or to inspect a page's DOM structure.
For versioned, CI-reproducible E2E test suites that need explicit Playwright scripts.
Security analysis
CautionThe skill delegates to Playwright MCP for browser navigation and interaction. While there are no destructive or exfiltrating instructions, the ability to access arbitrary URLs, interact with pages, and capture DOM/screenshots poses a legitimate but moderate risk, especially if used against internal or authenticated endpoints.
- •Uses browser automation to navigate to arbitrary URLs, including potentially internal or localhost services.
- •Can perform interactions such as form fills, clicks, and screenshots, which may access or expose sensitive page content.
- •No explicit restrictions on target domains or sensitive data handling.
Examples
/capability:playwright:navigate --url https://localhost:3000/capability:playwright:navigate --url https://localhost:3000/login --description "Fill username admin and password secret, then click submit"/capability:playwright:navigate --url https://example.com/form --description "Select option 'Brazil' from country dropdown and submit the form"name: capability:playwright:navigate description: Navigate to a URL and interact with the page via Playwright MCP argument-hint: "--url <page-url> [--description <interaction-details>]" user-invocable: true agent: zzaia-workspace-manager metadata: parameters: - name: url description: Target URL to navigate to required: true - name: description description: Broader description of what to do on the page (clicks, fills, assertions, etc.) required: false
PURPOSE
Navigate to a specific URL using Playwright MCP and perform interactions on the page as described. Supports clicks, form fills, key presses, selections, screenshots, and DOM inspection.
EXECUTION
- Navigate — Open or reuse a browser tab and navigate to
--url - Snapshot — Capture initial DOM/accessibility snapshot to understand page structure
- Interact — Execute interactions derived from
--description(click, fill, press, select, hover, drag, etc.) - Verify — Capture post-interaction snapshot and screenshot to confirm result
- Report — Return structured summary of actions taken and final page state
DELEGATION
MANDATORY: Always invoke the agents defined in this command's frontmatter for their designated responsibilities. Never skip, replace, or simulate their behavior directly.
zzaia-workspace-manager— Executes all Playwright MCP tool calls for navigation and page interaction
WORKFLOW
sequenceDiagram
participant U as User
participant C as Command
participant W as zzaia-workspace-manager
participant P as Playwright MCP
U->>C: /capability:playwright:navigate --url <url> [--description <details>]
C->>W: Delegate with url and description
W->>P: browser_navigate(url)
P-->>W: Page loaded
W->>P: browser_snapshot
P-->>W: Initial DOM snapshot
W->>P: browser_* (click, fill, press, select, etc.)
P-->>W: Interaction results
W->>P: browser_snapshot + browser_take_screenshot
P-->>W: Final page state
W-->>C: Actions summary and page state
C-->>U: Structured interaction report
ACCEPTANCE CRITERIA
- Navigates to the provided
--urlsuccessfully - Executes interactions described in
--description - Captures before/after page state via snapshots and screenshots
- Returns structured report of all actions taken and final page state
EXAMPLES
/capability:playwright:navigate --url https://localhost:3000
/capability:playwright:navigate --url https://localhost:3000/login --description "Fill username admin and password secret, then click submit"
/capability:playwright:navigate --url https://example.com/form --description "Select option 'Brazil' from country dropdown and submit the form"
OUTPUT
- Navigation confirmation (URL, page title)
- List of interactions performed
- Before/after DOM snapshots
- Final page screenshot
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/playwright-navigation-and-interaction-mrwakeih/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/playwright-navigation-and-interaction-mrwakeih' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/playwright-navigation-and-interaction-mrwakeih/download' --output '.skill-downloads/playwright-navigation-and-interaction-mrwakeih/SKILL.md.part' && mv '.skill-downloads/playwright-navigation-and-interaction-mrwakeih/SKILL.md.part' '.skill-downloads/playwright-navigation-and-interaction-mrwakeih/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/playwright-navigation-and-interaction-mrwakeih/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
ClickHouse Performance Comparison
Testing
Evaluate ClickHouse performance test results, check PR performance changes, compare with history, and assess whether a result is actionable.
Analyze CI Performance Reports
Testing
Analyze CI performance comparison reports for a ClickHouse PR. Cross-references master history to distinguish real regressions from flaky tests.
Santa Method
Testing
Multi-agent adversarial verification with two independent reviewers. Output is checked twice and iteratively fixed until both pass before shipping.