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.
62
44%
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 covers key scenarios, earning good marks for completeness. However, it relies on aspirational buzzwords ('delight developers', 'intuitive, scalable, and maintainable') instead of listing concrete actions, and it misses many natural trigger terms users would use when seeking API design help. The specificity of capabilities could be significantly improved by enumerating concrete design tasks.
Suggestions
Replace vague aspirational language ('intuitive, scalable, and maintainable APIs that delight developers') with concrete actions like 'define resource naming, design pagination, structure error responses, plan versioning strategies, write OpenAPI/Swagger specs'.
Add more natural trigger terms users would say, such as 'endpoints', 'routes', 'OpenAPI', 'swagger', 'HTTP methods', 'status codes', 'API versioning', 'schema', and file extensions like '.yaml' or '.json'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (REST and GraphQL API design) and mentions some actions ('designing new APIs, reviewing API specifications, establishing API design standards'), but the core description uses vague aspirational language ('intuitive, scalable, and maintainable APIs that delight developers') rather than listing concrete specific actions like 'define resource naming conventions, design pagination schemes, structure error responses'. | 2 / 3 |
Completeness | Clearly answers both 'what' (REST and GraphQL API design principles) and 'when' with an explicit 'Use when...' clause covering three trigger scenarios: designing new APIs, reviewing API specifications, or establishing API design standards. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'REST', 'GraphQL', 'API design', 'API specifications', and 'API design standards', but misses common natural variations users might say such as 'endpoints', 'routes', 'OpenAPI', 'swagger', 'schema design', 'versioning', 'pagination', or 'HTTP methods'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on API design principles for REST and GraphQL provides some distinctiveness, but 'designing new APIs' and 'reviewing API specifications' could overlap with general coding skills, backend development skills, or documentation skills. The phrase 'delight developers' is fluffy and doesn't help differentiation. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a comprehensive but overly verbose API design reference that explains many concepts Claude already knows well. It lacks a clear workflow for the actual task of designing an API, reading more like a textbook chapter than actionable instructions. The massive inline code examples for standard patterns (pagination, error handling, DataLoaders) should either be in referenced files or omitted entirely, as Claude can generate these on demand.
Suggestions
Remove the 'Core Concepts' section entirely—Claude already knows HTTP methods, REST principles, and GraphQL basics. Focus only on project-specific conventions or non-obvious decisions.
Add a clear step-by-step workflow for API design (e.g., 1. Gather requirements → 2. Choose paradigm → 3. Define resources/schema → 4. Review against checklist → 5. Generate OpenAPI spec) with validation checkpoints.
Move the detailed code patterns (pagination, error handling, DataLoaders, HATEOAS) into the referenced files (rest-best-practices.md, graphql-schema-design.md) and keep only a brief summary with links in the main skill.
Replace the lengthy best practices and common pitfalls lists with a concise decision matrix or checklist that Claude can apply during design reviews.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Explains basic concepts Claude already knows (HTTP method semantics, what REST resources are, what GraphQL queries/mutations/subscriptions are). The 'Core Concepts' section is almost entirely redundant knowledge. Massive code examples for standard patterns (pagination, error handling, DataLoaders) that Claude can generate on demand. | 1 / 3 |
Actionability | Code examples are relatively concrete and use real frameworks (FastAPI, Ariadne), but many rely on undefined helper functions (build_query, fetch_users, count_users, etc.) making them not truly executable. The patterns are illustrative rather than copy-paste ready, and the skill reads more like a reference document than actionable instructions for a specific task. | 2 / 3 |
Workflow Clarity | There is no clear workflow or sequenced process for API design. The skill is a collection of patterns and best practices without a defined sequence of steps, validation checkpoints, or decision points. The 'Interactive Design Process' section mentions clarifying requirements but provides no concrete workflow for how to actually design an API from start to finish. | 1 / 3 |
Progressive Disclosure | The Resources section references external files appropriately (rest-best-practices.md, templates, checklists), but the main body contains far too much inline content that should be in those referenced files. The core document should be a concise overview pointing to the detailed patterns, not containing all of them inline. | 2 / 3 |
Total | 6 / 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 | |
632759f
Table of Contents
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.