ui-aqa-flow-test-implementation

<ui_aqa_flow_test_implementation>

<description_and_purpose> Create the automated UI test integrating all page objects and assertions from the test plan, validate it locally (lint-clean), then hand execution off to the user. The phase implements → validates → hands off → updates state without closing the workflow. </description_and_purpose>

<workflow_context>

• Phase 6 of 8 in ui-aqa-flow
• Input: complete test plan plans/ui-aqa-<test-name>/test-plan.md (all phases), page objects ready from Phase 5
• Output: implemented test file, lint-clean; state updated; user given an execution command
• Prerequisite: Phases 1-5 complete
• HITL: must stop and wait for the user to execute the test (this phase does not run it)
• Write boundary (single SSoT — referenced by other sections): writes ONLY test files (and the test plan's ## Test Implementation record). NO edits to application source or page-object files — a missing selector/method routes back to Phase 5, never authored inline here.
• Required skills: qa-knowledge (implementation_modes — UI impl + the Test Implementation record), qa-structure (<test-name> paths + state shape)
• Recommended skills: testing, coding (repo conventions) </workflow_context>

<implementation_handoff_contract> This phase OWNS the implement → validate-locally → hand-off-execution → update-state-without-closing contract. It is verified by <validation_checklist> independent of skill internals.

• Implement — author the test via qa-knowledge implementation_modes (UI impl) against the plan; USE SKILL testing for general test quality; use coding for repo conventions (read repo standards as authority; repo docs win).
• Validate locally — lint/format clean on the touched test file; every Phase 2 assertion implemented OR recorded in the test plan's ### Uncovered Assertions (silent drop forbidden).
• Hand off execution — provide the exact project test-execution command; STOP and WAIT for the user to run it (<stop_for_execution>). The phase never executes the test itself.
• Update state without closing — record outcome in agents/TEMP/<FEATURE>/ui-aqa-state.md, mark Phase 6 complete, set Phase 7 current; do NOT mark the overall UI-AQA workflow COMPLETE.

Test Implementation record → qa-knowledge's UI test-implementation record (full rendering template owned by the skill). Five ordered subsections: Test File (path · framework); Implementation Summary (assertions implemented/total · page objects used); Uncovered Assertions (per entry: assertion · reason · disposition); Conflicts and Precedence (doc-vs-skill conflict · resolution); Validation (lint status · coverage). </implementation_handoff_contract>

<phase_steps>

1. Implement and validate the test locally (step 6.1)
2. Validate against requirements (step 6.2)
3. Stop for user test execution (step 6.3)
4. Update state (step 6.4) </phase_steps>

<execute_implementation step="6.1" subagent="engineer" role="Test automation engineer">

1. USE SKILL qa-structure to resolve run paths/state. USE SKILL coding to read the repository standards as authority before authoring; repo docs beat model defaults.
2. USE SKILL qa-knowledge (implementation_modes — UI impl) and USE SKILL testing with the parent-supplied bindings: test plan path plans/ui-aqa-<test-name>/test-plan.md; write boundary = test files only (<workflow_context>); output record = the Test Implementation record per <implementation_handoff_contract>.
3. Author the test using page-object methods only (no raw selectors in test code), proper waits, project assertion style. If a required selector or page-object method is missing, do NOT author it inline — stop and route back to Phase 5 (selector implementation).
4. Record every plan assertion that cannot be implemented in the test plan's ### Uncovered Assertions with the reason. Silent drop is forbidden.
5. Validate locally: run the project lint/format command on the touched test file and resolve issues; emit the Test Implementation record.