agentleFS
mckinseymckinsey/agents-at-scale-ark/.claude/skills/architecture/SKILL.md

ark-architecture

Skill439 starsChanged 7 months agoApache-2.0View on GitHub

Design architecture for Ark features following existing patterns and principles. Use when planning new features, extending components, or evaluating technical approaches.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Analyze Current Solution: - Use the ark-analysis skill to examine relevant parts of the codebase

    line 12
  2. Very specific:

    Watch endpoints: Use ?watch=true query param for SSE streaming (Kubernetes-style)

    line 27
  3. Very specific:

    Service ports: Use named ports (e.g., port: mcp) rather than port numbers

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ark Architecture Skill

Design architecture for Ark features following existing patterns and principles.

Process

  1. Analyze Current Solution - Use the ark-analysis skill to examine relevant parts of the codebase
  2. Identify Patterns - Find existing idioms, data models, and service structures to reuse
  3. Design for Reuse - Extend existing components rather than creating new ones
  4. Enable Incremental Updates - Break changes into small, independent pieces
  5. Flag One-Way Decisions - Raise questions on choices that are hard to reverse

Principles

  • Reuse over creation - Extend existing services, models, and patterns
  • Follow existing idioms - Match current code style, naming, and structure
  • Incremental delivery - Design so features can be shipped in stages
  • Reversibility - Identify and question decisions that lock in future options

Conventions

  • Watch endpoints: Use ?watch=true query param for SSE streaming (Kubernetes-style)
  • Service ports: Use named ports (e.g., port: mcp) rather than port numbers

Output

Architecture documents should include:

  • Component diagram showing how new pieces fit with existing ones
  • Data model extending current schemas
  • API design following existing conventions
  • List of one-way decisions requiring team input
  • Implementation phases for incremental delivery

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.