korchasa/browser-automation
framework/engineering/skills/browser-automation/SKILL.md
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
$ install --global
skillsauthnpx skillsauth add korchasa/flow browser-automationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 3, 2026, 4:15 AM47.9s5 files scanned
SKILL.md
- name:
- browser-automation
- description:
- Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Browser Automation
Overview
Automate browser interactions: navigate pages, click elements, fill forms, take
screenshots, extract data. Use whatever browser automation tool is available in
your environment (e.g., playwright-cli, Playwright MCP, WebFetch, curl).
Instructions
<step_by_step>
-
Detect Tool
- Check what browser tools are available. Prefer full browser (JS rendering, interaction) over HTTP-only tools.
- If no browser tool is found, fall back to
WebFetchorcurlfor read-only page access. Inform the user about limitations.
-
Navigate
- Open the target URL. Wait for the page to load.
-
Observe Before Acting
- Always capture page state (accessibility snapshot, DOM, or HTML) before interacting. Use structured data (accessibility tree, element refs) over raw screenshots when possible — structured data is better for reasoning.
-
Interact
- Click, fill, type, select using element references from the snapshot.
- After each interaction, re-capture page state to verify the result.
-
Capture Output
- Take screenshots or extract data as requested.
- Save files to the working directory.
-
Clean Up
- Close browser sessions when finished.
</step_by_step>
Best Practices
- Snapshot First: Always capture page state after navigation or interaction before taking next action.
- Isolation: Use separate sessions for independent tasks.
- Clean Up: Always close browser sessions when done.
- Prefer Structured Data: Accessibility snapshots > screenshots > raw HTML for element identification.
Related Skills
korchasa/setup-agent-code-style-strict
development
VerifiedTrustedCommunity
Use when the user asks to add TypeScript strict-mode code-style rules to AGENTS.md for a TypeScript project using strict mode. Do NOT trigger for Deno projects (use setup-agent-code-style-deno) or non-strict TS configurations.
2SKILL.mdUpdated Jun 4, 2026
korchasa/setup-agent-code-style-deno
development
VerifiedTrustedCommunity
Use when the user asks to add Deno/TypeScript code-style rules to AGENTS.md, or during initial Deno project setup when code-style guidelines need to be established. Do NOT trigger for non-Deno TypeScript projects (use setup-agent-code-style-strict), or for runtime-agnostic style advice.
2SKILL.mdUpdated Jun 4, 2026
korchasa/save
testing
VerifiedTrustedCommunity
Use when the user provides a source (URL, file path, or free text) to save into the project's memex — a long-term knowledge bank for AI agents. Stores the raw source, extracts entities into cross-linked pages, runs a backlink audit, and updates the index and activity log. Do NOT trigger on casual reads; only when the intent is to persist a source into the memex.
2SKILL.mdUpdated Jun 3, 2026
korchasa/audit
development
VerifiedTrustedCommunity
Use when the user asks to audit a memex (long-term knowledge bank for AI agents) for orphans, dead SALP REFs, missing sections, contradictions, or index drift. Runs a deterministic structural check, layers LLM-judgement findings, optionally auto-fixes trivial issues with `--fix`. Do NOT trigger on general code linting.
2SKILL.mdUpdated Jun 3, 2026