context-driven-development

Creates and maintains project context artifacts in a conductor directory for AI-assisted development.

Updated Apr 23, 2026
One-click install
npx skills add https://github.com/SanketAdlak/PDMProjectDesign --skill context-driven-development-sanketadlak
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: context-driven-development
Source: https://github.com/SanketAdlak/PDMProjectDesign/tree/main/.agents/skills/context-driven-development
Command: npx skills add https://github.com/SanketAdlak/PDMProjectDesign --skill context-driven-development-sanketadlak

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI-assisted development sessions lose consistency when project context lives in scattered docs or ad-hoc prompts. This Skill establishes a persistent, structured set of context artifacts (product.md, tech-stack.md, workflow.md, tracks.md) so every session and team member works from the same source of truth. ## Core Features & Use Cases - Project Scaffolding: Generate a complete conductor/ directory with product, tech stack, workflow, and track registry artifacts for greenfield projects. - Brownfield Extraction: Analyze an existing codebase to pre-populate context artifacts from discovered patterns, dependencies, and documentation. - Context Validation & Sync: Run a validation checklist before implementation and keep artifacts synchronized as features complete and dependencies change. - Use Case: Onboarding to an unfamiliar repository—run the setup flow to extract the tech stack, workflow conventions, and active work tracks into readable Markdown documents. ## Quick Start Ask the AI to set up Conductor context artifacts for this project and generate product.md, tech-stack.md, workflow.md, and tracks.md in a conductor directory.

Frequently Asked Questions about context-driven-development

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

FAQPage Schema
How do I set up project context documentation for AI-assisted development?

Run the Conductor setup flow to create a conductor directory containing product.md, tech-stack.md, workflow.md, and tracks.md. For new projects you answer questions interactively; for existing codebases the artifacts are pre-populated from detected patterns.

What files does a Conductor context structure include?

The conductor directory contains index.md, product.md, product-guidelines.md, tech-stack.md, workflow.md, tracks.md, setup_state.json, a code_styleguides folder, and a tracks folder with per-track spec.md, plan.md, and metadata.json files.

Can I use context-driven development with an existing codebase?

Yes, brownfield projects are supported. The setup analyzes existing code, configs, and documentation to pre-populate artifacts, then you review and refine the generated context to reconcile existing patterns with desired standards.

When should I update tech-stack.md and product.md?

Update tech-stack.md whenever you add dependencies, upgrade major versions, or change infrastructure. Update product.md when features complete, the product vision shifts, or target users change, keeping artifacts synchronized with each other.

What are common mistakes when maintaining project context documents?

Common anti-patterns include stale context that is never updated, context sprawl across scattered locations, implicit knowledge never written down, and over-specification that makes documents impossible to maintain. Update artifacts incrementally with each track.