bmad-generate-project-context

Generate project-context.md by discovering repository technology stack and implementation rules.

4|Updated Apr 26, 2026
One-click install
npx skills add https://github.com/curdx/curdx-flow --skill bmad-generate-project-context-curdx
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bmad-generate-project-context
Source: https://github.com/curdx/curdx-flow/tree/main/.agents/skills/bmad-generate-project-context
Command: npx skills add https://github.com/curdx/curdx-flow --skill bmad-generate-project-context-curdx

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps teams produce a concise, high-signal project-context document that prevents AI agents from drifting on architecture, conventions, and implementation rules.

Core Features & Use Cases

  • Generates project-context.md from repo evidence: Discovers the technology stack (with versions), existing patterns, and critical “don’t-miss” rules by scanning the repository.
  • Collaborative, stepwise rule capture: Guides the user through discovery and then iteratively builds rule categories with explicit A/P/C validation.
  • Optimized for agent consumption: Produces a lean, LLM-friendly rules file with tracked completion sections and clear usage boundaries.

Quick Start

Use the bmad-generate-project-context skill to create project-context.md by saying “generate project context” in your project workflow.

Frequently Asked Questions about bmad-generate-project-context

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

FAQPage Schema
How do I generate project context rules for LLM agents?

Generating project context involves scanning your repository to discover the technology stack and existing patterns, then collaboratively capturing implementation rules to output a structured project-context.md file optimized for LLM consumption.

What is a project context file used for in spec-driven agent workflows?

A project-context.md file provides persistent, restart-safe guidance for spec-driven agent workflows, ensuring consistent code generation by preventing AI agents from drifting on architecture, conventions, and implementation rules across multiple agents.

How do I ensure my AI coding agents follow existing repository patterns?

You ensure agents follow existing patterns by using a guided discovery process that scans the repository for established technology stacks and conventions, then iteratively captures these rules with enforced step gating and user approval.

Does generating an LLM-ready project context require manual rule input?

Generating project context requires collaborative, stepwise rule capture where the user validates discovered patterns, ensuring no rule categories proceed without explicit user approval and enforced step gating.

Can I use automated documentation discovery for multi-agent code generation?

Automated documentation discovery applies to multi-agent code generation by producing a lean, LLM-friendly rules file that provides tracked completion sections and clear usage boundaries for consistent guidance across agents.