BMAD Spec-to-Code Delivery
Turn coding goals into scoped specs, sequenced agent tasks, and verified delivery with explicit gates for changes and handoffs.
Before & after
Same prompt, same agent — the only difference is the skill.
That's a good question. You'd want to think about what you're trying to build, break it into smaller pieces, and then work through each piece systematically with your AI agent. You could start by writing out the requirements and the goals, then maybe sketch out the architecture. Then you could work on implementation step by step. It helps to test as you go and make sure each piece works before moving to the next one. You might want to document what you're building so the AI understands the context. Do you have a specific project in mind? What's the scope—frontend, backend, both?
BMAD-METHOD: SPEC-DRIVEN AI CODING FRAMEWORK (2-week project) PHASE 0: SPEC DEFINITION (Day 1, 4 hours) → Problem statement: 1 paragraph, max. What is the problem you're solving? → Success criteria: 5-8 acceptance tests (not 'code is clean', but 'API returns 200 and result.count equals X') → Tech stack: Explicit. Language, framework, DB, hosting. No "whatever works". → Scope boundary: IN-scope (3-5 features), OUT-of-scope (5+ explicitly excluded features) → Constraints: Performance targets, data-size limits, external API rate limits → Deliverable: Spec document in plaintext or Markdown, shared with AI agent before writing code PHASE 1: ARCH DESIGN (Day 2-3, given spec) → Agent task: 'Given this spec, design the data model and API endpoints. Return ERD and endpoint list.' → Validation: You review. Does it satisfy acceptance tests? Any missing edge cases? → Gate: Agent only codes after you approve design PHASE 2: IMPLEMENTATION (Day 4-9, spec + arch as input) → Agent task: Break into 3-day sprints (week 1: core API, week 2: UI or integrations) → Validation: Each sprint ends with you running tests against success criteria → Go/no-go: If sprint tests fail, fix before next sprint. No debt carried. PHASE 3: INTEGRATION + TEST (Day 10-13) → All pieces + integration tests. Agent tests against full acceptance-criteria list. → You spot-check 3 high-risk paths (error handling, data boundary cases) PHASE 4: VALIDATION (Day 14) → Final test run. Does it meet success criteria? Ship or cycle spec. → Outcome: Spec-to-shipped = 14 days, zero rewrites
About this skill
Your coding agent finishes tasks, but the feature still misses the point. Requirements drift, architectural decisions disappear between sessions, and "done" means the code was written. This skill applies a BMAD-style spec-driven process that connects the business goal to implementable stories and verified outcomes.
What it does
- Turns a loose request into a bounded brief with success conditions, constraints, and explicit exclusions.
- Checks existing code and interfaces before turning assumptions into architecture decisions.
- Breaks features into vertical slices with dependencies, acceptance criteria, and clear agent handoffs.
- Uses lightweight readiness gates to catch missing decisions before they become implementation guesses.
- Reconciles changed requirements across specifications, tasks, tests, and completed work.
- Reports delivery against acceptance criteria, separating verified results from remaining checks.
What you get
A project-sized delivery package: a concise brief, traceable requirements, necessary architecture decisions, ordered implementation tasks, and a verification ledger. Small fixes get a compact task card; larger projects get staged planning and execution.
Best for
Developers and teams using AI coding agents for features, existing-codebase changes, and projects whose scope keeps drifting between planning and implementation.
SKILL.md preview
---
name: bmad-spec-to-code-delivery
description: Applies a BMAD-style spec-driven delivery process that connects business goals, requirements, architecture decisions, agent-ready stories, and verification evidence. Use when the user says "plan this before coding", "use BMAD for this project", "turn this PRD into agent tasks", "my coding agent keeps losing the requirements", "the scope keeps changing", "break this feature into implementable stories", or "check whether this implementation meets the spec".
---
# BMAD Spec-to-Code Delivery
… (sign up to view the full skill)More development skills
View all Development skills →Performance Bottleneck Profiling: Node, Python, Go
Classifies a slowdown, gives exact profiler commands, reads the output, and proves the fix with same-conditions p95/p99 numbers.
Feature Scaffolding with Working Tests
Turn a short feature spec into code, runnable tests, and integration wiring that match your existing project.
Feature Flag Rollouts and Kill Switches
Design staged flag rollouts, verify rollback paths, and audit flag debt with explicit defaults, gates, and retirement plans.
Microcontroller Firmware and RTOS Engineering
Build and debug MCU firmware with bounded ISR/RTOS timing, safe DMA ownership, and measured power budgets.