Verified:GitHub

bmad-generate-project-context

Generate a project-context.md with implementation rules for AI agents.

36|16|Updated May 1, 2026

Search Tags:#anti-patterns #LLM optimization #project context #technology stack #ai agent rules #codebase discovery #implementation conventions

Ready to run

npx skills add https://github.com/tronghieu/lumina-wiki --skill bmad-generate-project-context-tronghieu

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: bmad-generate-project-context
Source: https://github.com/tronghieu/lumina-wiki/tree/main/.agents/skills/bmad-generate-project-context
Command: npx skills add https://github.com/tronghieu/lumina-wiki --skill bmad-generate-project-context-tronghieu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps teams turn scattered architecture knowledge, conventions, and gotchas into a single, concise rules file that AI agents can follow consistently when implementing code.

Core Features & Use Cases

Discovers existing project context by scanning for an existing project-context.md and analyzing the project’s stack, configuration, patterns, and constraints.
Creates an LLM-optimized project-context.md that captures unobvious implementation rules, including technology versions, code style, testing expectations, workflow guidance, and “don’t-miss” anti-patterns.
Runs a collaborative, step-based workflow with user gating so agents don’t generate or save content without explicit approval at each stage.

Quick Start

Tell the assistant: generate project context for this project so it can discover your current stack and produce an agent-ready project-context.md.

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 for AI agents to follow codebase conventions?▼

Generating project context involves scanning your codebase to discover your technology stack and constraints, then writing an LLM-optimized project-context.md file containing critical implementation rules and anti-patterns for AI agents to follow.

What is an LLM-optimized project-context.md file and why do I need one?▼

An LLM-optimized project-context.md is a concise rules file that captures unobvious implementation conventions, technology versions, and anti-patterns so AI agents consistently generate code that matches your project's architecture and avoids known gotchas.

How do I create AI agent rules from an existing technology stack and codebase?▼

You create AI agent rules by running a collaborative, step-based workflow that discovers your project's stack and patterns, requires explicit user approval at each stage, and writes the final conventions to a project-context.md file in your configured output language.

Does this project context generation require manual approval before writing rules?▼

Yes, project context generation runs a collaborative workflow with user gating, meaning the agent executes discovery and rule-generation steps sequentially and will not generate or save content without your explicit approval at each stage.

Can I update an existing project-context.md file with new implementation conventions?▼

Yes, you can update an existing project-context.md by asking the assistant to regenerate project context; it will discover the current file, analyze your updated stack and constraints, and apply new implementation rules through an approved workflow.

What limitations exist when discovering codebase patterns for AI agent rules?▼

The main limitation is that discovery relies on scanning existing configuration and code patterns to infer conventions; if critical implementation rules or anti-patterns are not present in the codebase, they must be provided manually during the user approval workflow.