ark-documentation — community ark-documentation, agents-at-scale-ark, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for AI Agents needing structured documentation for agentic resources, utilizing Diataxis framework. Provider-agnostic operations for agentic resources. ARK codifies patterns and practices developed across dozens of agentic application projects.

mckinsey mckinsey
[0]
[0]
Updated: 3/5/2026

Agent Capability Analysis

The ark-documentation skill by mckinsey is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Perfect for AI Agents needing structured documentation for agentic resources, utilizing Diataxis framework.

Core Value

Empowers agents to create comprehensive and organized documentation using ARK's codified patterns and practices, incorporating provider-agnostic operations and adapting Diataxis for Ark's specific needs, including linear learning paths and task-oriented guides.

Capabilities Granted for ark-documentation

Creating new documentation with Introduction, Quickstart, and Tutorials sections
Restructuring existing documentation to fit ARK's Diataxis structure
Reviewing documentation PRs for consistency and accuracy

! Prerequisites & Limits

  • Requires understanding of Diataxis framework
  • Specific to ARK's documentation needs
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

ark-documentation

Install ark-documentation, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Ark Documentation

Guidance for structuring Ark documentation using Diataxis adapted for Ark's needs.

When to use this skill

  • Creating new documentation
  • Deciding where content belongs
  • Reviewing documentation PRs
  • Restructuring existing documentation

ARK's Diataxis structure

docs/content/
├── Introduction
├── Quickstart
├── Tutorials          → Linear learning paths
├── How-to Guides      → Task-oriented, by persona
├── Core Concepts      → Understanding "why" and "how"
├── Reference          → Factual lookup material
├── Marketplace        → External link
└── Disclaimer

Terminology

DiataxisArk TermWhy
ExplanationCore ConceptsMore accessible

The four quadrants

1. Tutorials (learning-oriented)

Purpose: Hands-on lessons for newcomers.

Characteristics:

  • Linear, numbered paths (1, 2, 3...)
  • Single prescribed path - no choices
  • Frequent visible results
  • Ends with "Next step" → How-to Guides

Writing style:

  • Use "we" language
  • Don't explain - link to Core Concepts

Content belongs here if:

  • It teaches a skill through doing
  • Reader is studying, not working
  • Success requires following steps in order

Examples: Quickstart, Running the Dashboard, Starting a New Project, Complete Worked Example


2. How-to guides (task-oriented)

Purpose: Help competent users complete specific tasks.

Organized by persona:

Build with ARK (application developers)

  • Configure models, create agents, coordinate teams, run queries, add tools.

Extend ARK (contributors)

  • Build services locally, implement APIs, build A2A servers, add tests.

Operate ARK (operators / SRE / security)

  • Platform operations: Provisioning, deploying
  • CI/CD and supply chain: Build pipelines
  • Security & assurance: Pen testing, code analysis

Writing style:

  • Goal-oriented: "If you want X, do Y"
  • Assumes competence
  • Don't teach - link to Tutorials or Core Concepts

Content belongs here if:

  • Reader has a specific task to complete
  • Reader is working, not studying

3. Core concepts (understanding-oriented)

Purpose: Explain what ARK is, how it's designed, and why.

Topics:

  • What ARK is and how it works.
  • Design effective agentic systems.
  • Platform architecture concepts.
  • Extensibility concepts.
  • Security and identity concepts.

Writing style:

  • Discursive: "The reason for X is..."
  • Make connections between concepts
  • Provide design decision context

Content belongs here if:

  • It answers "why" or "how does this work"
  • Reader is deciding how to design/extend/operate
  • Content provides context, not procedures

4. Reference (information-oriented)

Purpose: Factual lookup material.

Organized by type:

  • Interfaces: ARK APIs.
  • Kubernetes API: CRDs, resources.
  • Evaluations: Guides, event-based evaluations.
  • System behavior: Query execution, relationships.
  • Operations: Upgrading, troubleshooting.
  • Project: Contributors.

Writing style:

  • Austere, factual, neutral
  • Structure mirrors product
  • No instruction, explanation, or opinion

Content belongs here if:

  • It describes what something IS
  • Reader needs to look up specific details
  • Content is consulted, not read cover-to-cover

Decision guide

Is the reader LEARNING or WORKING?
│
├─ LEARNING (studying)
│   ├─ Hands-on, step-by-step? → TUTORIALS
│   └─ Understanding concepts? → CORE CONCEPTS
│
└─ WORKING (applying)
    ├─ Completing a task? → HOW-TO GUIDES
    └─ Looking up facts? → REFERENCE

Hub pages

Hub pages link to content without moving files:

  • tutorials.mdx - Lists tutorials in order.
  • how-to-guides.mdx - Groups by persona.
  • core-concepts.mdx - Groups by topic.
  • reference/index.mdx - Groups by type.

Hub pages should:

  • Explain purpose in one sentence.
  • Group links logically.
  • Not duplicate content.

Personas

PersonaSections
End usersQuickstart, Tutorials
Agent buildersTutorials, How-to (Build)
Platform engineersHow-to (Operate), Reference
ContributorsHow-to (Extend), Core Concepts

Writing guidelines

Lexicon

  • The product is known as ARK rather than Ark.

General style

  • Be concise and direct.
  • Use simple language.
  • Keep descriptions to 1-2 sentences.
  • Use active voice: "Creates agent" not "Agent is created".
  • Write "ARK" not "Ark".
  • Use US English.
  • Use Oxford commas in lists.

Bullets

  • Capitalize the first word and end with a period.
  • Use numbered lists only for sequences of instructions or when referencing items later.

Capitalization

  • Capitalize only proper nouns (product names, tools, services).
  • Use sentence case for titles: "An introduction to data visualization" not "An Introduction to Data Visualization".
  • Don't capitalize: cloud, internet, machine learning, advanced analytics.

Headings

  • Avoid gerunds: "Get started" not "Getting started," "Customize a layout" not "Customizing a layout".
  • Keep titles short and descriptive for search discoverability.

Instructions

  • Use imperatives: "Complete the configuration steps".
  • Don't use "please".
  • Don't use passive tense: "Complete the steps" not "The steps should be completed".
  • Make hyperlinks descriptive: Learn how to [contribute to ARK](url).
  • Don't write: To contribute, see [here](url).

Avoid

  • Gerunds in headings.
  • Colloquialisms (may not translate across regions/languages).
  • Business speak: "leverage", "utilize", "facilitate".

What not to mix

Don't put in...This content...
TutorialsExplanations, choices.
How-to guidesTeaching, complete reference.
Core conceptsInstructions, reference.
ReferenceInstructions, explanations.

References

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is ark-documentation?

Perfect for AI Agents needing structured documentation for agentic resources, utilizing Diataxis framework. Provider-agnostic operations for agentic resources. ARK codifies patterns and practices developed across dozens of agentic application projects.

How do I install ark-documentation?

Run the command: npx killer-skills add mckinsey/agents-at-scale-ark/ark-documentation. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for ark-documentation?

Key use cases include: Creating new documentation with Introduction, Quickstart, and Tutorials sections, Restructuring existing documentation to fit ARK's Diataxis structure, Reviewing documentation PRs for consistency and accuracy.

Which IDEs are compatible with ark-documentation?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for ark-documentation?

Requires understanding of Diataxis framework. Specific to ARK's documentation needs.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add mckinsey/agents-at-scale-ark/ark-documentation. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use ark-documentation immediately in the current project.

Related Skills

Looking for an alternative to ark-documentation or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI