graphql-expert
Expert GraphQL developer specializing in type-safe API development, schema design, resolver optimization, and federation architecture. Use when building GraphQL APIs, implementing Apollo Server, optimizing query performance, or designing federated microservices.
74
75%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/graphql-expert/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its GraphQL-specific domain with concrete capabilities and explicit trigger conditions. It uses appropriate third-person voice and includes both technical terms (Apollo Server, federation) and natural user language (building APIs, optimizing performance). The description effectively distinguishes itself from general API development skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'type-safe API development, schema design, resolver optimization, and federation architecture' along with implementation details like 'Apollo Server' and 'federated microservices'. | 3 / 3 |
Completeness | Clearly answers both what ('type-safe API development, schema design, resolver optimization, federation architecture') and when ('Use when building GraphQL APIs, implementing Apollo Server, optimizing query performance, or designing federated microservices'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'GraphQL', 'API', 'schema design', 'Apollo Server', 'query performance', 'federated microservices'. These cover common terms developers use when working with GraphQL. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on GraphQL with distinct triggers like 'Apollo Server', 'federation architecture', and 'GraphQL APIs' that are unlikely to conflict with general API or REST skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides excellent actionable code examples and comprehensive coverage of GraphQL development patterns, but suffers from severe verbosity and poor organization. Duplicate sections (Core Principles/Responsibilities, Pattern sections), excessive inline content that belongs in reference files, and an unnecessary anti-hallucination protocol significantly inflate token usage without proportional value.
Suggestions
Remove duplicate sections (consolidate the two 'Core Responsibilities' sections and two 'Pattern' sections into single, concise versions)
Move the anti-hallucination protocol to a separate reference file or remove entirely - it adds ~50 lines of marginal value
Extract the extensive test examples and OWASP security table to reference files, keeping only 1-2 representative examples inline
Restructure to put the TDD workflow and critical reminders near the top, with patterns as a reference section
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~800+ lines with significant redundancy (Section 2 'Core Principles' and Section 5 'Core Responsibilities' overlap heavily, Section 4 appears twice). Explains concepts Claude knows (what DataLoader is, basic async patterns) and includes excessive boilerplate like the anti-hallucination protocol that adds little value. | 1 / 3 |
Actionability | Provides fully executable code examples throughout - complete Python/TypeScript resolver implementations, test fixtures, DataLoader patterns, and schema definitions. Code is copy-paste ready with proper imports and context. | 3 / 3 |
Workflow Clarity | Has a TDD workflow (Steps 1-4) with validation checkpoints, but the overall document structure is confusing with duplicate sections and unclear navigation. The pre-implementation checklist is comprehensive but buried at the end. Missing explicit feedback loops for error recovery in the main workflow. | 2 / 3 |
Progressive Disclosure | References external files appropriately (references/advanced-patterns.md, etc.) with clear signaling, but the main document is a monolithic wall of text with poor organization. Content that should be in reference files (full security table, extensive test examples) is inline, bloating the skill. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1371 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 12 / 16 Passed | |
- Repository
- martinholovsky/claude-skills-generator
- Commit
1086ef2
- 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.