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

Ark Analysis

Skill438 starsChanged 7 months agoApache-2.0View on GitHub

Analyze the Ark codebase by cloning the repository to a temporary location. Use this skill when the user asks questions about how Ark works, wants to understand Ark's implementation, or needs to examine Ark source code.

  • Deletes or force-pushes

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Use this skill when:

    line 12
  2. Very specific:

    Clone to /tmp: Always clone to /tmp/ark-analysis to avoid cluttering the workspace

    line 77
  3. Very specific:

    Use search tools: Prefer rg (ripgrep) or grep for code searches

    line 79
  4. Distinctive:

    Check CLAUDE.md: Look for project-specific guidance in CLAUDE.md files

    line 80

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 Analysis

This skill helps you analyze the Ark codebase by cloning the repository and examining its contents.

When to use this skill

Use this skill when:

  • User asks "how does X work in Ark?"
  • User wants to understand Ark's architecture or implementation
  • User needs to examine Ark source code, CRDs, or controllers
  • User mentions analyzing the Ark repository

Quick start

Clone the Ark repository to a temporary location:

git clone git@github.com:mckinsey/agents-at-scale-ark.git /tmp/ark-analysis
cd /tmp/ark-analysis

Codebase structure

The Ark repository is organized as follows:

  • ark/ - Kubernetes operator and default executor (Go)
    • Controller dispatches queries to executors via A2A protocol
    • CRDs: Agent, Model, Query, Team, MCPServer, ExecutionEngine, A2AServer
    • executors/completions/ - Built-in default execution engine
  • lib/ark-sdk/ - Python SDK (generated + overlay)
    • BaseExecutor ABC and ExecutorApp for pluggable executor interface
  • services/ - Component services
    • ark-api/ - REST API gateway (Python/FastAPI)
    • ark-broker/ - In-memory event bus (Node.js/Express)
    • ark-dashboard/ - Web UI (Next.js/React)
  • samples/ - Example YAML configurations
  • docs/ - Documentation site (Next.js/MDX)

Common analysis tasks

Find controllers

ls ark/internal/controller/
grep -r "Reconcile" ark/internal/controller/

Find CRDs

ls ark/config/crd/bases/
grep -r "kind: Agent" samples/

Find A2A implementations

find . -path "*/a2a*" -type f
grep -r "A2AServer" .

Search for specific features

# Use ripgrep or grep to search
rg "query controller" --type go
grep -r "team coordination" --include="*.go"

Best practices

  1. Clone to /tmp: Always clone to /tmp/ark-analysis to avoid cluttering the workspace
  2. Navigate first: cd /tmp/ark-analysis before running analysis commands
  3. Use search tools: Prefer rg (ripgrep) or grep for code searches
  4. Check CLAUDE.md: Look for project-specific guidance in CLAUDE.md files
  5. Clean up: Optionally remove the temp directory when done: rm -rf /tmp/ark-analysis

Example workflows

Analyzing a controller

git clone git@github.com:mckinsey/agents-at-scale-ark.git /tmp/ark-analysis
cd /tmp/ark-analysis
cat ark/internal/controller/query_controller.go
grep -r "ExecuteQuery" ark/internal/genai/

Understanding A2A integration

cd /tmp/ark-analysis
find samples/a2a -name "*.py"
cat samples/a2a/simple-agent/src/simple_a2a_server/main.py
cat docs/content/developer-guide/building-a2a-servers.mdx

Finding CRD specifications

cd /tmp/ark-analysis
ls ark/api/v1alpha1/
cat ark/api/v1alpha1/agent_types.go

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.