api-design-principles
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.
78
Quality
70%
Does it follow best practices?
Impact
91%
1.03xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/data/02-architect-apidesign/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 a solid structure with an explicit 'Use when' clause that clearly defines trigger scenarios. However, it relies on vague marketing language ('delight developers', 'intuitive, scalable, maintainable') instead of concrete capabilities, and could benefit from more specific trigger terms that users naturally use when discussing API design.
Suggestions
Replace vague qualifiers with concrete actions like 'define resource naming conventions, design pagination strategies, structure error responses, version APIs'
Add more natural trigger terms users would say: 'endpoints', 'routes', 'OpenAPI', 'swagger', 'API documentation', 'request/response format'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (REST and GraphQL API design) and mentions some actions (designing, reviewing, establishing standards), but uses vague qualifiers like 'intuitive, scalable, maintainable' and 'delight developers' which are abstract rather than concrete capabilities. | 2 / 3 |
Completeness | Clearly answers both what (API design principles for REST and GraphQL) and when (designing new APIs, reviewing specifications, establishing standards) with an explicit 'Use when' clause containing specific triggers. | 3 / 3 |
Trigger Term Quality | Includes relevant keywords like 'REST', 'GraphQL', 'API design', 'API specifications', but misses common variations users might say such as 'endpoints', 'routes', 'schema', 'OpenAPI', 'swagger', or 'API documentation'. | 2 / 3 |
Distinctiveness Conflict Risk | Focuses on API design which is somewhat specific, but could overlap with general coding skills, backend development skills, or documentation skills. The REST/GraphQL focus helps but 'API design standards' is broad. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive API design skill with excellent actionable code examples and good progressive disclosure structure. However, it's verbose in places, explaining concepts Claude already knows (HTTP methods, basic GraphQL concepts), and lacks a clear step-by-step design workflow with validation checkpoints that would guide Claude through the API design process.
Suggestions
Remove or significantly condense the 'Core Concepts' section - Claude already knows HTTP method semantics and basic GraphQL concepts
Add an explicit step-by-step API design workflow with validation checkpoints (e.g., 'Design schema → Validate against checklist → Review with stakeholder → Implement')
Trim the 'When to Use This Skill' section to 2-3 key use cases instead of 7
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary explanation (e.g., 'When to Use This Skill' section with 7 bullet points, verbose introductions) and could be tightened. The 'Core Concepts' section explains basic HTTP methods and GraphQL concepts Claude already knows well. | 2 / 3 |
Actionability | Provides fully executable Python/FastAPI code examples, complete GraphQL schemas, and copy-paste ready patterns. Code is concrete with proper imports, type hints, and realistic implementations. | 3 / 3 |
Workflow Clarity | While patterns are well-organized, there's no clear sequential workflow for API design. The 'Interactive Design Process' mentions feedback loops but lacks explicit validation checkpoints or step-by-step design process with verification steps. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from core concepts to patterns to best practices. References to external files (references/, assets/, scripts/) are clearly signaled at the end with one-level-deep navigation. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (534 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- majiayu000/claude-skill-registry
- Commit
6213d1a
- 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.