ark-architecture

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

1.11x

Quality

61%

Does it follow best practices?

Impact

95%

1.11x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/architecture/SKILL.md

Evaluation results

100%

23%

Real-Time Agent Execution Status

Watch endpoints and streaming API design

Criteria

Without context

With context

Watch query param

100%

Named port reference

100%

Component diagram present

100%

API design section

100%

One-way decisions listed

100%

Implementation phases

100%

Data model section

100%

Reuse over creation

87%

100%

Incremental breakdown

100%

SSE mechanism explained

100%

99%

-1%

External Tool Provider Integration

Architecture document completeness

Criteria

Without context

With context

Component diagram

100%

Data model section

100%

API design section

100%

One-way decisions section

100%

Implementation phases

100%

Reuse existing components

100%

Naming conventions

100%

Reversibility discussion

100%

Named service ports

100%

Incremental independence

100%

Extension over creation

100%

87%

Agent Activity Audit Trail

Reuse and incremental delivery patterns

Criteria

Without context

With context

Extends existing model

100%

70%

No standalone service

Existing idioms

100%

Watch endpoint if streaming

100%

Named ports

100%

One-way decisions flagged

100%

Implementation phases

100%

Component diagram

100%

API design present

100%

Reversibility noted

100%

Incremental independence

100%

Repository: mckinsey/agents-at-scale-ark
Commit: f4bfd2d

Evaluated: 30 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Real-Time Agent Execution Status External Tool Provider Integration Agent Activity Audit Trail

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.