wiradeltaid

Wdi Method — AI skill for Claude Code

AI community

The review layer for AI coding agents: human review gates that check technical decisions before Claude Code, Cursor, or Codex write the code.

How to install Wdi Method

This entry records only its repository, not the path inside it, so there is no exact command to give. Open wiradeltaid/wdi-method and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Wdi Method does

The review layer for AI coding agents: human review gates that check technical decisions before Claude Code, Cursor, or Codex write the code. Wraps BMad.

Alternatives in AI

  • Bmad Method — Breakthrough Method for Agile Ai Driven Development 42712 382 2 42.9k ★
  • PR Review Check — AI PR 리뷰 코멘트를 triage하고 유효한 것만 안전하게 수정 2.1k ★
  • Claude Skills LLM Council — LLM Council — a Claude Code skill that runs your decisions through 5 AI advisors with peer review 1.7k ★

README

WDI Method

The review layer BMad leaves thin — verifiable specifications a human reads to check technical decisions before code is written, sized to what the change actually deserves.

[English](README.md) | [Bahasa Indonesia](README.id.md) | [简体中文](README.zh-CN.md) | [日本語](README.ja.md) | [한국어](README.ko.md) | [Español](README.es.md) | [Deutsch](README.de.md) | [Français](README.fr.md) | [Português (Brasil)](README.pt-BR.md) | [Русский](README.ru.md) [Website](https://wiradelta.id/wdi-method) | [Changelog](CHANGELOG.md) | [Contributing](CONTRIBUTING.md) | [License](LICENSE) | [Security](SECURITY.md) | [Privacy](PRIVACY.md)


[BMad](https://github.com/bmad-code-org/BMAD-METHOD) decides *what* to build and *how* to structure solutions well. WDI Method wraps it — without replacing it — providing the verifiable governance layer between high-level architectural decisions and working code: requirement registries, use case catalogues, component boundaries, automated drift validators, and unhindered autonomous daily loops.

This repository is **public and generic**. It MUST NOT carry a client name, a commercial product name, or a link to a private repository. Product identity lives entirely in the repository that installs it.


Helicopter View: AI-Driven Development (AiDD) vs. Vibe Coding

Speculative prompting ("vibe coding") inevitably fails on multi-month production systems: AI coding agents lose context, hallucinate completion states, and blur requirement boundaries. WDI Method establishes disciplined **AI-Driven Development (AiDD)** through a three-layer architectural triad:

┌─────────────────────────────────────────────────────────────────────────┐
│ 1. Intent & Strategy: BMad Method                                       │
│    Discovers user problems, draft product briefs, and architecture      │
├─────────────────────────────────────────────────────────────────────────┤
│ 2. Verifiable Review Layer: WDI Method (SSOT)