Initialize a project through deep questioning - PROJECT.md, REQUIREMENTS.md, a phased ROADMAP.md and .planning/ state
Scanned 9/3/2026
Install to Claude Code
npx -y skills add crenshawdev/cadence --skill cad-new-project --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Cad New Project?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/crenshawdev-cad-new-project)More formats (shields.io, HTML) on the badges page.
---
name: cad-new-project
description: "Initialize a project through deep questioning - PROJECT.md, REQUIREMENTS.md, a phased ROADMAP.md and .planning/ state"
argument-hint: "[--research] [--brief <file>]"
allowed-tools:
- Read
- Write
- Edit
- Bash
- Grep
- Glob
- AskUserQuestion
- Task
---
<objective>
Start a project properly: question deeply until the idea is concrete, then
write PROJECT.md and REQUIREMENTS.md, derive a phased ROADMAP.md with
falsifiable per-phase success criteria, and initialize .planning/ (config
copied from the engine template, STATE.md cursor). Research is off by
default; `--research` or config `workflow.research` enables a single
research pass. `--brief <file>` reads a design brief an earlier conversation
produced and questions only what it leaves open.
</objective>
<execution_context>
@${CLAUDE_PLUGIN_ROOT}/cadence-core/workflows/new-project.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', ...