ark-architecture
Design architecture for Ark features following existing patterns and principles. Use when planning new features, extending components, or evaluating technical approaches.
77
66%
Does it follow best practices?
Impact
95%
1.11xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/architecture/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has good structural completeness with explicit 'what' and 'when' clauses, which is its strongest aspect. However, the capabilities listed are high-level and somewhat vague ('design architecture', 'evaluating technical approaches'), and the trigger terms could be more varied to capture natural user language. The Ark-specific context helps with distinctiveness but the actions described are generic enough to overlap with other planning or architecture skills.
Suggestions
Add more specific concrete actions, e.g., 'Designs module boundaries, defines data flow between components, selects appropriate design patterns for Ark features'
Expand trigger terms with natural variations users might say, e.g., 'Use when discussing system design, module structure, code organization, API design, or making architectural decisions for Ark'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('Ark features') and some actions ('planning new features, extending components, evaluating technical approaches'), but these actions are fairly high-level and not concrete enough to qualify as specific capabilities like 'extract text', 'fill forms', etc. | 2 / 3 |
Completeness | Clearly answers both 'what' ('Design architecture for Ark features following existing patterns and principles') and 'when' ('Use when planning new features, extending components, or evaluating technical approaches') with an explicit 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'architecture', 'features', 'components', and 'technical approaches', but 'Ark' is project-specific and the terms are somewhat generic. Missing more natural trigger phrases users might say like 'design decision', 'system design', 'module structure', or 'code organization'. | 2 / 3 |
Distinctiveness Conflict Risk | The 'Ark' project name provides some distinctiveness, but 'planning new features' and 'evaluating technical approaches' are broad enough to overlap with general coding, code review, or project planning skills. The description doesn't clearly carve out a unique niche beyond being Ark-specific. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise architecture skill that clearly communicates principles and conventions. Its main weakness is the lack of concrete examples—a sample architecture document output or template would significantly improve actionability. The workflow is logical but would benefit from explicit validation checkpoints, particularly around verifying pattern alignment and reviewing one-way decisions.
Suggestions
Add a concrete example of a completed architecture document (even abbreviated) showing the expected output format with component diagram notation, data model extension, and API design sections.
Add a validation checkpoint after step 2 (e.g., 'Confirm identified patterns with existing code references before designing') and a review gate before finalizing one-way decisions.
Link to or provide a template file for architecture documents to improve progressive disclosure and ensure consistent output structure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every section adds value without explaining concepts Claude already knows. No padding or unnecessary context—just principles, conventions, and expected outputs. | 3 / 3 |
Actionability | The skill provides a clear process and principles but lacks concrete examples. There are no sample architecture documents, no example component diagrams, no template for the output format. The conventions section has two specific items (watch endpoints, service ports) which are good, but overall guidance is more directional than executable. | 2 / 3 |
Workflow Clarity | The 5-step process is clearly sequenced and logical, but lacks validation checkpoints. There's no feedback loop for verifying the architecture against existing patterns, no checkpoint for confirming one-way decisions before proceeding, and no explicit review/iteration step. | 2 / 3 |
Progressive Disclosure | The skill references the ark-analysis skill in step 1, which is good cross-referencing. However, the Output section describes what architecture documents should include but doesn't link to templates or examples. For a skill that produces complex multi-section documents, a link to an example output or template file would improve navigation. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- mckinsey/agents-at-scale-ark
- Commit
fc5746e
- Reviewed
Table of Contents
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.