locator-healer-agent

Name: locator-healer-agent
Author: anhtester

29stars8forks

How to install locator-healer-agent?

anhtester/codex-testing-kit/locator-healer-agent

$npx -y skills add anhtester/codex-testing-kit --skill locator-healer-agent

Installs into the current project.

Summary

Skill tự động phát hiện và sửa chữa locators bị hỏng khi automation tests fail do thay đổi DOM.

Files · 1

View on GitHub

SKILL.md

1	# Locator Healer Agent
2
3	Purpose: Automatically repair broken locators when automation tests fail.
4
5	---
6
7	## When to Use
8
9	Use this skill when:
10
11	- A test fails with "element not found" or "element detached" errors
12	- UI has changed and existing locators no longer work
13	- After a frontend deployment that modifies DOM structure
14
15	---
16
17	## Responsibilities
18
19	When a locator fails:
20
21	1. Inspect current DOM or UI hierarchy
22	2. Compare old locator with current page structure
23	3. Identify updated attributes
24	4. Generate a replacement locator
25	5. Re-run test to verify the fix
26
27	---
28
29	## Detection Strategy
30
31	Locator is considered broken when:
32
33	- Element not found (NoSuchElementException / TimeoutError)
34	- Element detached from DOM
35	- Selector matches zero elements
36	- Selector matches wrong element (different text/position)
37
38	---
39
40	## Healing Workflow
41
42	### Step 1: Analyze the Error
43	- Read error log to identify which locator failed
44	- Identify the Page Object file and line number
45
46	### Step 2: Inspect Current DOM
47	- Open the page using MCP tools
48	- Navigate to the same state as the failing test
49	- Inspect the target area in DOM
50
51	### Step 3: Find Alternative Locator
52	Try the following in priority order:
53
54	1. Accessibility attributes (`aria-label`, `role`)
55	2. `data-testid` / `data-test`
56	3. `id` (if stable, not auto-generated)
57	4. Semantic locator (Playwright `getByRole`, `getByLabel`)
58	5. `css selector` (stable attributes)
59	6. `xpath` (relative, not positional)
60
61	### Step 4: Validate & Replace
62	- Verify the new locator matches exactly one element
63	- Verify the element is the correct one (text, position, behavior)
64	- Replace the broken locator in the Page Object class
65	- Re-run the test
66
67	---
68
69	## Difference from Smart Locator Agent
70
71	\| Aspect \| Locator Healer \| Smart Locator \|
72	\|--------\|---------------\|---------------\|
73	\| Trigger \| Test failure (reactive) \| New element (proactive) \|
74	\| Input \| Broken locator + error log \| HTML/DOM element \|
75	\| Goal \| Fix existing locator \| Generate new locator \|
76	\| Workflow \| Error → Inspect → Replace → Verify \| Inspect → Generate → Validate \|
77
78	---
79
80	## Verification
81
82	After healing:
83
84	- [ ] Locator must match exactly one element
85	- [ ] Element is the correct target (verify text/attributes)
86	- [ ] Test must pass successfully
87	- [ ] Locator is stable across page reloads
88
89	---
90
91	## Rules References
92
93	- `.agents/rules/locator_strategy.md` — Master locator priority map
94	- `.agents/rules/automation_rules.md` — General automation best practices

People who liked this also viewed

6 picks

Type

azure-diagnosticsDebug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deploySkillsJul 2026472k1.3k
systematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesSkillsJul 2026197k259k
safe-debugRigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training SkillsMay 2026161k507
explore-runRigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subseSkillsMay 2026161k507
minimal-run-and-auditRigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation SkillsMay 2026161k507
insforge-debugUse when diagnosing problems in an InsForge project — reactive failures (SDK error object, HTTP 4xx/5xx, gateway timeout 502/503/504, edge function failure or timeout, login/OAuth/auth errors, RLS denSkillsJul 202618k31

locator-healer-agent

29stars8forks

View on GitHub

How to install locator-healer-agent?

anhtester/codex-testing-kit/locator-healer-agent

$npx -y skills add anhtester/codex-testing-kit --skill locator-healer-agent

Installs into the current project.

Summary

Skill tự động phát hiện và sửa chữa locators bị hỏng khi automation tests fail do thay đổi DOM.

Files · 1

View on GitHub

SKILL.md

1	# Locator Healer Agent
2
3	Purpose: Automatically repair broken locators when automation tests fail.
4
5	---
6
7	## When to Use
8
9	Use this skill when:
10
11	- A test fails with "element not found" or "element detached" errors
12	- UI has changed and existing locators no longer work
13	- After a frontend deployment that modifies DOM structure
14
15	---
16
17	## Responsibilities
18
19	When a locator fails:
20
21	1. Inspect current DOM or UI hierarchy
22	2. Compare old locator with current page structure
23	3. Identify updated attributes
24	4. Generate a replacement locator
25	5. Re-run test to verify the fix
26
27	---
28
29	## Detection Strategy
30
31	Locator is considered broken when:
32
33	- Element not found (NoSuchElementException / TimeoutError)
34	- Element detached from DOM
35	- Selector matches zero elements
36	- Selector matches wrong element (different text/position)
37
38	---
39
40	## Healing Workflow
41
42	### Step 1: Analyze the Error
43	- Read error log to identify which locator failed
44	- Identify the Page Object file and line number
45
46	### Step 2: Inspect Current DOM
47	- Open the page using MCP tools
48	- Navigate to the same state as the failing test
49	- Inspect the target area in DOM
50
51	### Step 3: Find Alternative Locator
52	Try the following in priority order:
53
54	1. Accessibility attributes (`aria-label`, `role`)
55	2. `data-testid` / `data-test`
56	3. `id` (if stable, not auto-generated)
57	4. Semantic locator (Playwright `getByRole`, `getByLabel`)
58	5. `css selector` (stable attributes)
59	6. `xpath` (relative, not positional)
60
61	### Step 4: Validate & Replace
62	- Verify the new locator matches exactly one element
63	- Verify the element is the correct one (text, position, behavior)
64	- Replace the broken locator in the Page Object class
65	- Re-run the test
66
67	---
68
69	## Difference from Smart Locator Agent
70
71	\| Aspect \| Locator Healer \| Smart Locator \|
72	\|--------\|---------------\|---------------\|
73	\| Trigger \| Test failure (reactive) \| New element (proactive) \|
74	\| Input \| Broken locator + error log \| HTML/DOM element \|
75	\| Goal \| Fix existing locator \| Generate new locator \|
76	\| Workflow \| Error → Inspect → Replace → Verify \| Inspect → Generate → Validate \|
77
78	---
79
80	## Verification
81
82	After healing:
83
84	- [ ] Locator must match exactly one element
85	- [ ] Element is the correct target (verify text/attributes)
86	- [ ] Test must pass successfully
87	- [ ] Locator is stable across page reloads
88
89	---
90
91	## Rules References
92
93	- `.agents/rules/locator_strategy.md` — Master locator priority map
94	- `.agents/rules/automation_rules.md` — General automation best practices

People who liked this also viewed

6 picks

Type