Context Driven Development — Agent Skill by Seth Hobson

From the author

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.

— the description by Seth Hobson

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

Context-Driven Development establishes a systematic approach to project documentation by treating context artifacts as first-class citizens alongside source code. By maintaining structured files like product.md, tech-stack.md, workflow.md, and tracks.md within a dedicated directory, teams create a single source of truth that ensures AI agents and human developers remain aligned throughout the project lifecycle. This skill provides the templates and maintenance patterns necessary to keep project documentation living, actionable, and synchronized with implementation.

What it does

Provides standardized templates for project documentation including product vision, tech stack, and workflows.
Defines a structured directory layout for maintaining project context artifacts.
Establishes maintenance patterns to keep documentation synchronized with code changes.
Offers guidelines for evolving project context from greenfield setup to ongoing development.
Facilitates team alignment and AI agent consistency through shared, structured knowledge.

When to use it

When initializing a new software project to ensure clear documentation from the start.
When onboarding new team members to an existing project to provide immediate context.
When you need to ensure AI agents have a consistent, reliable source of project information.
When project requirements, tech stacks, or development workflows undergo significant changes.
When you need to track work units and project progress in a structured, transparent manner.

Advantages

Reduces ambiguity by centralizing project vision, technical decisions, and workflows.
Ensures AI agents operate with accurate, up-to-date project information.
Promotes consistency across development sessions and team members.
Encourages disciplined documentation practices by integrating them into the development workflow.
Provides a clear audit trail of project evolution through version-controlled artifacts.

Usage examples

“Initialize a new project structure using the context-driven development approach.”: The agent creates a conductor/ directory containing the standard template files (product.md, tech-stack.md, workflow.md, tracks.md) ready for project-specific configuration.
“I am adding a new dependency to the project. How should I update the context?”: The agent guides you to update tech-stack.md, documenting the new dependency, its version, and the rationale for its inclusion, ensuring the project context remains accurate.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/wshobson/context-driven-development/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip context-driven-development.zip -d .agents/skills

Documentation by Seth Hobson

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

Files

ATTRIBUTION.mdAdded by AutoGineer996 B
LICENSELicence file added by AutoGineer1.0 KiB
SKILL.md2.1 KiB
references/artifact-templates.md2.8 KiB
references/details.md9.8 KiB

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Setup TS Deep Modules
Matt Pocock· Community
Configures dependency-cruiser to enforce deep module boundaries in TypeScript repositories.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository317.5k
To Spec
Matt Pocock· Community
Synthesizes conversation context into a structured technical specification and publishes it to a project issue tracker.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Improve Codebase Architecture
Matt Pocock· Community
A systematic process to identify, visualize, and refine architectural deepening opportunities in a codebase.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Domain Modeling
Matt Pocock· Community
An expert assistant for defining project terminology, maintaining a glossary, and documenting architectural decisions.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Codebase Design
Matt Pocock· Community
A shared vocabulary and set of principles for designing deep, testable, and maintainable software modules.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Prototype
Matt Pocock· Community
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k