ui-test-selector-review

UI Test Selector Review

Review the stability and maintainability of UI selectors based on the DOM, component semantics, test code, and change history, and output USR-## findings. It only organizes traceable UI automation quality candidates; it does not execute tests, nor does it write a design checklist as coverage, pass, or release evidence.

When to Use

• When UI test selector review candidates need to be extracted from the DOM or component code, test code, accessible names, data-testid conventions, locator change history, and failure screenshots.
• When the selection rationale, applicable constraints, evidence gaps, and minimal verification actions need to be explained.
• When the materials are incomplete but a limited initial version still needs to be delivered, with blocked or unassessed boundaries clearly stated.

Not applicable to directly executing tests, generating behavior conclusions without sources, replacing a complete test strategy, or accepting risk on behalf of the Human.

Output Format Options

• Default output is Markdown; tables, JSON, or CSV are used only when the user explicitly needs them or the existing delivery format requires them.
• Keep static analysis, unexecuted items, evidence status, and Human decisions separate; when there is no execution evidence, keep them unassessed, blocked, or NOT_RUN.

How to Use

1. Read prompts/ui-test-selector-review.md, and provide the goal, scope, materials, environment, and existing evidence.
2. First complete the six-category input audit: known, missing, conflicting, stale, out_of_scope, assumptions.
3. Use USR-## to record the object, preconditions, concerns, source evidence, and verification method, retaining impact/priority, responsible role, closure conditions, and evidence status.
4. When materials conflict, constraints are missing, or there is no execution evidence, retain both sides and the open questions.

Domain Execution Points

• Clarify the target element from the DOM/component and user actions, and compare the actual semantics and maintenance contract of role+accessible name, stable test ID, scope, and CSS/XPath.
• Deliver a table of targets, match counts, stability sources, and alternative rationales; semantics/uniqueness matter more than locator syntax preference.
• When forming domain candidates, you must read and follow the domain operations and determination process of prompts/ui-test-selector-review.md , retaining legitimate comparisons, evidence gaps, and verification actions item by item.

Core Constraints

• Do not execute tests, do not assume rules, versions, thresholds, data, or results that were not provided, and do not treat the number of candidates as proof of coverage.
• File existence, name matching, design declarations, or Eval configuration do not equal real execution evidence.
• Mark unknown items as unassessed, blocked, or to be confirmed; do not fill them in with common sense.
• Do not modify requirements, code, test assets, or the target system.

Pre-Delivery Self-Check

• The six-category input audit has been recorded: known, missing, conflicting, stale, out_of_scope, assumptions.
• Each USR-## has a source, evidence status, impact/priority, responsible role, closure conditions, and verification method.
• Facts, inferences, recommendations, unexecuted items, and Human decisions have been distinguished.
• Design candidates have not been written as execution results, coverage proof, or release conclusions.

Reference Files

• During regression, read evals/eval.yaml and the matching test cases; configuration does not prove real project results.
• Trigger validation uses evals/trigger-prompts.csv and evals/local-rules.json; when skill.selection evidence is missing, report BLOCKED.

Common Pitfalls

• When the scope or evidence is incomplete, do not write method names, file existence, or candidate counts as test executed, covered, passed, or release evidence.
• Do not use common sense to fill in rules, thresholds, data, environments, or results that were not provided; retain unassessed, blocked, and to-be-confirmed items.
• Do not expand this Skill's specialized candidates into a complete strategy, complete test cases, actual execution, or release decisions.

Best Practices

• Complete the six-category input audit first, then choose the smallest, traceable, and verifiable discovery scope.
• For each finding, retain the source, evidence status, impact/priority, responsible role, closure conditions, and verification method, and clearly state the residual risk.
• Write verification recommendations as next-step actions, and do not upgrade the Skill package structure, candidate counts, or local Eval configuration into real quality conclusions.