Wdi Method — AI skill for Claude Code
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)
Related Skills
Bmad Bmm Create Architecture
Create architecture solution design decisions for AI agent consistency. Use when the user says "lets create ar
Salient Core
Guardrail and permission layer for AI agent harnesses. A default-deny control kernel that gates every tool cal
Aar Loop
Run an After Action Review after any AI session and write concrete lessons so your agent stops repeating mista
Stat Review
Full statistical review of an analysis, model, notebook, query, or diff — establishes estimand, unit, and deci
SoloDawn
Catches and repairs AI hallucinations before delivery: three quality gates, 31 built-in rules, a self-healing
Code Harness Kit
Harness for Claude Code & Cursor · 让 AI 交付软件像一支工程团队——Leader 编排、阶段门禁、集体验证兜底。Multi-agent orchestration with stag
Related Agents
Reliability Engineer
Python delivery agent for quality gates and test infrastructure. Owns test suite (>=80% coverage enforced), go
Part 13: Memory Bridge (Give Coding Agents Your Brain)
When you spawn Codex or Claude Code to build something, they start blind. They don't know your architecture de
Constitutional Validator
Validates features, technical decisions, and code changes against the project's CONSTITUTION.md principles — e