skilld
All skills
wshobson avatar

/context-driven-development

@be57c0b
by Seth Hobsonwshobson/agents40k stars
4,281

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.

Ask your Agent

Use this Skill: https://skilld.dev/gh/wshobson/agents/context-driven-development

This session only. Nothing lands on disk.

SKILL.md

≈139 tokens always: the name and description. ≈379 when used: this file. ≈3.2k more on demand in 2 files.

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

  1. Read context first: Always read relevant artifacts before starting work
  2. Small updates: Make incremental context changes, not massive rewrites
  3. Link decisions: Reference context when making implementation choices
  4. Version context: Commit context changes alongside code changes
  5. Review context: Include context artifact reviews in code reviews
  6. Validate regularly: Run context validation checklist before major work
  7. Communicate changes: Notify team when context artifacts change significantly
  8. Preserve history: Use git to track context evolution over time
  9. Question staleness: If context feels wrong, investigate and update
  10. Keep it actionable: Every context item should inform a decision or behavior

Source: SKILL.md on GitHub

Third-party checks

No alerts2d5 checks · Risk SAFE
  • Gen Agent Trust Hub2d

    This skill provides a framework for project documentation and management through structured markdown files. It contains no executable scripts or malicious code. However, it presents a low-risk surface for indirect prompt injection because it instructs the agent to read and prioritize information from user-managed text files that could potentially contain untrusted instructions.

  • Socket2d

    No alerts

  • Snyk2d

    Risk: LOW · No issues

  • Runlayer7mo

    2 files scanned · No issues

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at be57c0b. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 4 months ago

Capability

version
1.0.0

Topics

  • Documentation
  • context
  • project-setup
  • onboarding
  • artifacts
  • scaffolding
  • workflow
  • knowledge-management

README badge

README badge for wshobson/agents/context-driven-development

What it does

Creates and maintains project context artifacts (product.md, tech-stack.md, workflow.md, tracks.md) in a conductor/ directory to enable consistent AI interactions and team alignment. Use when scaffolding projects, extracting context from existing codebases, validating artifact consistency, or onboarding to a codebase.

Generated from the current SKILL.md.

Frequently asked

What files does this skill create and maintain?
The skill creates and manages four context artifacts in a `conductor/` directory: product.md (product vision and goals), tech-stack.md (technology decisions), workflow.md (development process), and tracks.md (work units and tracking). These are stored alongside code and updated as the project evolves.
Can I use this skill to extract context from an existing codebase?
Yes. The skill can analyze existing codebases and extract context to populate the conductor artifacts, not just scaffold new projects from scratch.
Does this skill validate that context artifacts are consistent with each other?
Yes. The skill includes validation logic to check artifact consistency before implementation work begins, helping catch conflicts across product, tech, workflow, and tracking documents.
How does this skill help during AI-assisted development?
By maintaining structured context artifacts, the skill enables consistent AI interactions across multiple sessions and helps align team members on project direction, tech choices, and workflows without repeating setup work.
Does this work for both new projects and existing codebases?
Yes. The skill handles greenfield projects (scaffolding from scratch) and brownfield projects (extracting and structuring context from existing code).

Generated from the current SKILL.md. These answers refresh after source changes.