bmad-generate-project-context

Generates a project-context.md file documenting implementation rules for AI coding agents.

Updated Aug 3, 2026
One-click install
npx skills add https://github.com/shaahy/quicknav-desktop --skill bmad-generate-project-context-shaahy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-generate-project-context
Source: https://github.com/shaahy/quicknav-desktop/tree/main/A%20%E6%95%99%E7%A8%8B%E9%9B%86%E5%90%88/BMAD-METHOD%E6%8A%80%E8%83%BD%E9%80%9F%E6%9F%A5/source-v6.10.0/src/bmm-skills/3-solutioning/bmad-generate-project-context
Command: npx skills add https://github.com/shaahy/quicknav-desktop --skill bmad-generate-project-context-shaahy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI coding agents often produce inconsistent code because they lack awareness of a project's specific technology versions, coding conventions, and critical anti-patterns. This Skill guides a collaborative discovery process to capture those unobvious rules into a single project-context.md file that agents read before implementing code. ## Core Features & Use Cases - Guided Discovery Workflow: Scans architecture documents, package files, and configuration files to identify the technology stack, existing patterns, and coding conventions. - Collaborative Rule Generation: Walks through rule categories (language, framework, testing, quality, workflow, anti-patterns) with A/P/C menus for advanced elicitation or multi-perspective review. - LLM-Optimized Output: Produces a lean, scannable project-context.md with exact versions and actionable rules, plus usage guidelines for agents and humans. - Use Case: After setting up a new TypeScript/React project, run this workflow to document strict-mode requirements, hooks patterns, and testing conventions so every AI agent implements code consistently with project standards. ## Quick Start Ask the AI to generate project context for this repository so it can discover the tech stack and write the implementation rules into 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 create a project context file for AI coding agents?▼

Run this workflow and it will scan your architecture documents, package files, and configs to discover your technology stack. It then collaborates with you category by category to document language, framework, testing, and workflow rules into project-context.md.

What should a project context file for AI agents include?▼

It should include exact technology versions, language-specific rules, framework patterns, testing requirements, code quality conventions, workflow rules, and critical anti-patterns. The focus is on unobvious details agents might otherwise miss, kept lean for LLM context efficiency.

Does this workflow update an existing project-context.md file?▼

Yes. The discovery step checks for an existing project-context.md under the project knowledge folder or project root. If found, it reads the current sections and lets you update or extend them instead of creating a new file.

Can I customize the workflow steps or add persistent rules?▼

Yes. The customize.toml file supports activation step overrides, persistent facts loaded on every run, and an on_complete hook. Team and user-level TOML overrides merge with the defaults using structural merge rules.

When should I regenerate the project context file?▼

Regenerate or update it when your technology stack changes, new conventions emerge, or dependencies are upgraded. The completion guidance recommends quarterly reviews to remove outdated rules and keep the file lean.