bmad-quick-dev

Implements code changes through a spec-driven plan, implement, and adversarial review workflow.

Updated Aug 25, 2024
One-click install
npx skills add https://github.com/LeGeRyChEeSe/LanPlay-DiscordBot --skill bmad-quick-dev-legerycheese
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-quick-dev
Source: https://github.com/LeGeRyChEeSe/LanPlay-DiscordBot/tree/main/bmad/src/bmm-skills/4-implementation/bmad-quick-dev
Command: npx skills add https://github.com/LeGeRyChEeSe/LanPlay-DiscordBot --skill bmad-quick-dev-legerycheese

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a user request into working code often skips planning and review, producing unreviewable or misaligned changes. This Skill enforces a disciplined workflow that converts any intent, story, or bug fix into a written specification, implements it against project conventions, and runs multi-agent adversarial review before presenting the result. ## Core Features & Use Cases - Spec-Driven Implementation: Clarifies intent, investigates the codebase, and writes a structured spec with tasks, acceptance criteria, and boundaries before any code changes. - Dual Routing: Routes zero-blast-radius changes to a fast one-shot path and everything else through a full plan-code-review cycle. - Adversarial Review Loop: Launches blind, edge-case, and acceptance-auditor review subagents, classifies findings, and loops back to re-plan or re-implement when needed. - Use Case: A developer asks to add a new API endpoint. The Skill drafts a spec with acceptance criteria, gets human approval, implements the change via a sub-agent, runs three independent reviews, fixes findings, and presents a clickable review order with a local commit. ## Quick Start Ask the agent to implement a feature or fix a bug, for example: implement password reset functionality following the project conventions.

Frequently Asked Questions about bmad-quick-dev

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I implement a feature with a spec-driven AI workflow?▼

Invoke the skill with your intent; it clarifies requirements, investigates the codebase, writes a spec with tasks and acceptance criteria, then waits for your approval before implementing. After implementation it runs adversarial reviews and presents a clickable review order.

What is the difference between the one-shot and plan-code-review routes?▼

One-shot handles changes with zero blast radius: clear intent and no architectural decisions, implementing directly with a single review. Plan-code-review handles everything else with full spec drafting, human approval, implementation, and three-reviewer adversarial review.

Can this workflow run without sub-agent support?▼

Yes. For runtimes without sub-agents such as Copilot, Codex, or local models, it falls back to inline execution or writes review prompt files and asks the human to run each review in a separate session and paste back findings.

How does the review loop handle findings in generated code?▼

Findings are deduplicated and classified as intent_gap, bad_spec, patch, defer, or reject. Patches are auto-fixed, deferred items go to a deferred-work file, and intent or spec problems trigger a loopback to re-plan or re-implement, capped at five iterations.

Does the skill commit or push changes automatically?▼

It creates a local conventional commit if the tree is dirty, but never pushes or performs remote operations automatically. At the end it offers to push or create a pull request and waits for human confirmation.