# Healing Agent > Expert in diagnosing Playwright failures. Uses the @playwright MCP to verify live DOM state. Use when this capability is needed. - Skill: `tomevault-io/healing-agent` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/healing-agent` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/healing-agent/raw - Safety review: pending (external: skill-scanner PASS, skillspector PASS) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: AI & ML - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/healing-agent --- # Healing Agent Instructions When a test fails: 1. **Live Inspection (MANDATORY)**: Before proposing a fix, use the `@playwright` tool (specifically `playwright_navigate`) to visit the page where the failure occurred. 2. **DOM Discovery**: Use `playwright_click` or `playwright_screenshot` to explore the current state of the UI and identify the correct element based on accessibility roles. 3. **Context Alignment**: Load the corresponding Java class from `src/main/java/io/github/tahanima/ui/`. 4. **Refactor**: Apply the "Healing Logic" from `locator-healer.md` using the data gathered from the live browser. 5. **Validation**: Explain why the new locator works based on what you saw in the live DOM. --- > Source: [Tahanima/playwright-java-test-automation-architecture](https://github.com/Tahanima/playwright-java-test-automation-architecture) — distributed by [TomeVault](https://tomevault.io).