context-driven-development
wshobson/agents
Create and maintain structured project context artifacts to align AI agents and teams during development.
What is context-driven-development?
This skill creates and maintains a set of project context documents (product.md, tech-stack.md, workflow.md, tracks.md) in a conductor/ directory. Use it when setting up new projects, onboarding to existing codebases, or keeping project documentation synchronized with evolving code.
- Scaffolds new projects with context artifact templates
- Extracts context from existing codebases into structured documents
- Validates consistency across product, tech stack, workflow, and tracking artifacts
- Synchronizes context documents as the project evolves
- Provides patterns and best practices for context-driven development
- Enables consistent AI agent interactions through structured documentation
How to install context-driven-development
npx skills add https://github.com/wshobson/agents --skill context-driven-developmentHow to use context-driven-development
- 1.Read the relevant context artifacts (product.md, tech-stack.md, workflow.md, tracks.md) before starting work
- 2.Make incremental updates to context documents rather than large rewrites
- 3.Reference context decisions when making implementation choices
- 4.Run context validation before major work phases
- 5.Commit context changes alongside code changes in git
- 6.Review context artifacts as part of code reviews
- 7.Update context when project direction or technical decisions change
Use cases
- Setting up a new project with initial context scaffolding
- Onboarding a team member or AI agent to an existing codebase by reading context artifacts
- Updating tech-stack.md when adding or changing dependencies
- Defining development workflows in workflow.md for team alignment
- Validating context consistency before starting major implementation work
- Development teams using AI-assisted coding
- Project leads managing documentation and context
- Developers onboarding to existing projects
- Teams practicing context-driven development workflows
context-driven-development FAQ
The skill manages product.md (product vision and requirements), tech-stack.md (technology decisions), workflow.md (development processes), tracks.md (work units and structure), and a conductor/ directory to organize them.
Update context incrementally when making significant decisions, changing the tech stack, modifying workflows, or when context feels stale or misaligned with actual development.
Structured context artifacts enable consistent AI agent interactions by providing clear project information, reducing hallucinations, and ensuring the AI understands product goals, technical constraints, and team workflows.
Yes, the skill can extract context from existing codebases and help you create or update context artifacts to document your current project state.
Treat context like code: version it in git, review it in code reviews, and question staleness when something feels wrong. Keep context actionable and aligned with actual development.
Full instructions (SKILL.md)
Source of truth, from wshobson/agents.
name: context-driven-development
description: >-
Creates and maintains project context artifacts (product.md, tech-stack.md, workflow.md, tracks.md)
in a conductor/ directory. Scaffolds new projects from scratch, extracts context from existing
codebases, validates artifact consistency before implementation, and synchronizes documents as the
project evolves. Use when setting up a project, creating or updating product docs, managing a tech
stack file, defining development workflows, tracking work units, onboarding to an existing codebase,
or running project scaffolding.
version: 1.0.0
Context-Driven Development
Guide for implementing and maintaining context as a managed artifact alongside code, enabling consistent AI interactions and team alignment through structured project documentation.
When to Use This Skill
- Setting up new projects with Conductor
- Understanding the relationship between context artifacts
- Maintaining consistency across AI-assisted development sessions
- Onboarding team members to an existing Conductor project
- Deciding when to update context documents
- Managing greenfield vs brownfield project contexts
Detailed patterns and worked examples
Detailed pattern documentation lives in references/details.md. Read that file when the navigation tier above is insufficient.
Best Practices
- Read context first: Always read relevant artifacts before starting work
- Small updates: Make incremental context changes, not massive rewrites
- Link decisions: Reference context when making implementation choices
- Version context: Commit context changes alongside code changes
- Review context: Include context artifact reviews in code reviews
- Validate regularly: Run context validation checklist before major work
- Communicate changes: Notify team when context artifacts change significantly
- Preserve history: Use git to track context evolution over time
- Question staleness: If context feels wrong, investigate and update
- Keep it actionable: Every context item should inform a decision or behavior
Related skills
More from wshobson/agents and the wider catalog.
cost-optimization
Optimize cloud costs across AWS, Azure, GCP, and OCI through rightsizing, tagging, and pricing strategies.
cqrs-implementation
Implement CQRS to separate read and write models for scalable, high-performance architectures.
data-quality-frameworks
Implement data quality validation with Great Expectations, dbt tests, and data contracts for reliable pipelines.
data-storytelling
Transform data into compelling narratives that drive decisions and inspire action.
database-migration
Execute database migrations across ORMs with zero-downtime strategies, data transformation, and rollback procedures.
dataset-curation
Prepare, format, and validate datasets for supervised fine-tuning and preference training.