Install
$ agentstack add skill-anhtester-claude-testing-kit-locator-healer-agent ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Locator Healer Agent
Purpose: Automatically repair broken locators when automation tests fail.
When to Use
Use this skill when:
- A test fails with "element not found" or "element detached" errors
- UI has changed and existing locators no longer work
- After a frontend deployment that modifies DOM structure
Responsibilities
When a locator fails:
- Inspect current DOM or UI hierarchy
- Compare old locator with current page structure
- Identify updated attributes
- Generate a replacement locator
- Re-run test to verify the fix
Detection Strategy
Locator is considered broken when:
- Element not found (NoSuchElementException / TimeoutError)
- Element detached from DOM
- Selector matches zero elements
- Selector matches wrong element (different text/position)
Healing Workflow
Step 1: Analyze the Error
- Read error log to identify which locator failed
- Identify the Page Object file and line number
Step 2: Inspect Current DOM
- Open the page using MCP tools
- Navigate to the same state as the failing test
- Inspect the target area in DOM
Step 3: Find Alternative Locator
Try the following in priority order:
- Accessibility attributes (
aria-label,role) data-testid/data-testid(if stable, not auto-generated)- Semantic locator (Playwright
getByRole,getByLabel) css selector(stable attributes)xpath(relative, not positional)
Step 4: Validate & Replace
- Verify the new locator matches exactly one element
- Verify the element is the correct one (text, position, behavior)
- Replace the broken locator in the Page Object class
- Re-run the test
Difference from Smart Locator Agent
| Aspect | Locator Healer | Smart Locator | |--------|---------------|---------------| | Trigger | Test failure (reactive) | New element (proactive) | | Input | Broken locator + error log | HTML/DOM element | | Goal | Fix existing locator | Generate new locator | | Workflow | Error → Inspect → Replace → Verify | Inspect → Generate → Validate |
Verification
After healing:
- [ ] Locator must match exactly one element
- [ ] Element is the correct target (verify text/attributes)
- [ ] Test must pass successfully
- [ ] Locator is stable across page reloads
Rules References
.claude/rules/locator_strategy.md— Master locator priority map.claude/rules/automation_rules.md— General automation best practices
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: anhtester
- Source: anhtester/claude-testing-kit
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.