context-driven-development

Use it when:: You want every AI coding session on a project to start from the same written product goals, tech choices and working rules.
It does:: Creates and keeps current a conductor/ folder of Markdown files: product vision, product guidelines, tech stack, workflow rules and a registry of work units.
You get:: product.md, product-guidelines.md, tech-stack.md, workflow.md, tracks.md and an index.md under conductor/, with starter templates for the first five.
Before each task:: The agent reads the files, flags anything outdated and proposes updates before it starts.
Needs:: The Conductor plugin's /conductor:setup command for its setup steps; with the skill alone, the agent writes the files from the templates.

Skill 1 of 3 in the Conductor bundle, before track-management.

Its setup steps run /conductor:setup, a command of the repo's Conductor plugin; installed as a skill alone, the agent writes the conductor/ files itself, from the starter templates in its reference files.

TL;DR

The context step of Conductor, a plugin in the same repo whose workflow runs context, then spec and plan, then implementation. Each file answers one question: product.md what is built and why, product-guidelines.md how the product speaks to users, tech-stack.md which languages, dependencies and infrastructure, workflow.md how the team works (TDD, commit conventions, review, coverage targets), and tracks.md which work units, called tracks, are active or done. The files stay in sync: a new dependency goes into tech-stack.md with its reason and version, and a finished feature moves from planned to implemented in product.md. For a new project, setup asks about vision, tech and workflow; for an existing one it reads the code and configs and pre-fills the files for you to review. Before each track the agent runs a validation checklist over product, technical, workflow and track context. At the start of a session it reads index.md, tracks.md and the current plan; at the end it updates the plan, notes blockers and commits work in progress. It warns against stale, scattered, unwritten and over-detailed context.

Summarizes the skill at 4bde316.

npx skills add https://github.com/wshobson/agents --skill context-driven-development

skills.sh page Source on GitHub All skills from wshobson/agents

Total Downloads: 11,500 on skills.sh, Nov 9, 2026
Repo stars: 42,334 wshobson/agents
First seen: Jan 20, 2026 on skills.sh

Weekly Downloads

149

-23% over the 8 weeks to Nov 9

Weekly values

Week to	Installs
Sep 21	193
Sep 28	221
Oct 5	280
Oct 12	218
Oct 19	189
Oct 26	184
Nov 2	174
Nov 9	149

Category	category:planning category:software-engineering Make the agent question you and write the plan down before it writes code. Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills.
Type	type:workflow A multi-step process the agent follows: interview, debug, run a TDD loop, review.
Effect	effect:local Its own steps create or change files, git state or local tools.
Needs	needs:none Instructions only. Works in any agent that supports skills.
Publisher	by:community Everyone else. Unverified vendor claims default to community.
Topics	planning docs-writing memory

SKILL.md

From wshobson/agents at 4bde316. Checked daily, last changed Nov 6, 2026.

Frontmatter

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