verify-work

---

name: verify-work description: Validate built features through conversational UAT argument-hint: "[phase number, e.g., '4']" allowed-tools:

• Read
• Bash
• Glob
• Grep
• Edit
• Write

---

Purpose: Confirm what Claude built actually works from user's perspective. One test at a time, plain text responses, no interrogation.

Output: {phase}-UAT.md tracking all test results, gaps logged for /ag4:plan-phase --gaps

<execution_context> @/.claude/ag4one/workflows/verify-work.md @/.claude/ag4one/templates/UAT.md </execution_context>

@.planning/STATE.md @.planning/ROADMAP.md

<anti_patterns>

• Don't use AskUserQuestion for test responses — plain text conversation
• Don't ask severity — infer from description
• Don't present full checklist upfront — one test at a time
• Don't run automated tests — this is manual user validation
• Don't fix issues during testing — log as gaps for /ag4:plan-phase --gaps </anti_patterns>

<success_criteria>

• UAT.md created with tests from SUMMARY.md
• Tests presented one at a time with expected behavior
• Plain text responses (no structured forms)
• Severity inferred, never asked
• Batched writes: on issue, every 5 passes, or completion
• Committed on completion
• Clear next steps based on results </success_criteria>