Verify a completed phase by conversational UAT - a persistent checklist that survives /clear, plus cross-phase and goal-backward passes
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add crenshawdev/cadence --skill cad-verify --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Cad Verify?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/crenshawdev-cad-verify)More formats (shields.io, HTML) on the badges page.
---
name: cad-verify
description: "Verify a completed phase by conversational UAT - a persistent checklist that survives /clear, plus cross-phase and goal-backward passes"
argument-hint: "[phase] [--sweep] [--deep]"
allowed-tools:
- Read
- Write
- Edit
- Bash
- Grep
- Glob
- AskUserQuestion
- Task
---
<objective>
Walk the user through a phase's acceptance criteria one item at a time,
recording pass/fail/skip in a persistent .planning/phases/<N>/UAT.md.
Results survive /clear and session ends - re-run to resume at the first
untested item. Failures are diagnosed and routed through the normal
Cadence flow (user-approved atomic fix commit, or /cad-plan for
phase-sized gaps) - no internal auto-fixer loop. `--sweep` scans every
phase's UAT file and reports what is still outstanding. `--deep` spawns
cad-verifier for a goal-backward check of what the code actually delivers.
</objective>
<execution_context>
@${CLAUDE_PLUGIN_ROOT}/cadence-core/workflows/verify.md
</execution_context>
<process>
Execute end-to-end.
</process>
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
