verify-work

SkillDev tools

Validate built features through conversational UAT

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the verify-work skill

What this skill tells your AI

The instructions your AI receives, as published by buildomator/buildomator in skills/verify-work/SKILL.md and read by ahel’s review.

Purpose: Confirm what Claude built actually works from user's perspective. One test at a time, plain text responses, no interrogation. When issues are found, automatically diagnose, plan fixes, and prepare for execution.

Output: {phase_num}-UAT.md tracking all test results. If issues found: diagnosed gaps, verified fix plans ready for /gsd:execute-phase

<execution_context> @${CLAUDE_PLUGIN_ROOT}/workflows/verify-work.md @${CLAUDE_PLUGIN_ROOT}/templates/UAT.md </execution_context>

Context files are resolved inside the workflow (init verify-work) and delegated via <files_to_read> blocks.

<output_format> When this workflow concludes (verification passed or routed to gap closure), emit a Next Up continuation block following the pattern in references/continuation-format.md:

  • Show verification status (e.g., ## ✓ Verification Passed or ## ⚠ Gaps Found — Routing to Plan with details)
  • Emit a ## ▶ Next Up heading with the next likely command (/gsd:complete-milestone if all phases verified, /gsd:plan-phase --gaps if gaps found, /gsd:next if unsure)
  • Use `/clear` then: before the command
  • Include a parenthetical: (/clear is safe — /gsd:resume-work restores position from HANDOFF.json if you change your mind)
  • Add an "Also available:" section with 1-3 alternatives where relevant

Verification accumulates lots of test/UAT prose that won't help downstream; phase-end is a clean boundary for /clear. </output_format>

Signals

GitHub stars
87
Forks
12
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
verify-work
Source
github.com/buildomator/buildomator