graphql

You're a developer who has built GraphQL APIs at scale. You've seen the N+1 query problem bring down production servers. You've watched clients craft deeply nested queries that took minutes to resolve. You know that GraphQL's power is also its danger.

Quality

18%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/graphql/SKILL.md

Quality

Content

18%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill reads more like a topic outline or table of contents than an actionable skill. It names many important GraphQL concepts and anti-patterns but provides zero executable code, no concrete implementation guidance, and no workflows. The narrative introduction wastes tokens on storytelling that Claude doesn't need, while the areas that matter most—actual patterns, examples, and step-by-step guidance—are empty shells with one-line descriptions.

Suggestions

Add executable code examples for each pattern (DataLoader setup, schema design with proper nullability, Apollo Client cache configuration) — even one concrete example per pattern would dramatically improve actionability.

Create step-by-step workflows for key tasks like 'Setting up DataLoader' or 'Configuring query depth limiting' with validation steps (e.g., test with a nested query to verify depth limiting works).

Remove the narrative intro paragraph and the truncated sentence; replace with a concise purpose statement like '## Purpose\nDesign and implement production-grade GraphQL APIs with proper performance safeguards.'

Split detailed guidance into bundle files (e.g., DATALOADER.md, SCHEMA_DESIGN.md, FEDERATION.md) and reference them from the main skill with clear signposting.

Dimension	Reasoning	Score
Conciseness	The narrative intro ('You've seen the N+1 query problem bring down production servers...') is unnecessary flavor text that Claude doesn't need. The capabilities list is just a bullet list of keywords without actionable content. However, the sharp edges table is reasonably efficient. The content appears truncated ('You've l') which wastes tokens on an incomplete thought.	3 / 5
Actionability	There is no executable code, no concrete commands, no specific examples, and no copy-paste ready guidance anywhere in the skill. The patterns section names concepts ('DataLoader for N+1 Prevention') with one-line descriptions but provides zero implementation details. The sharp edges table gives solutions as imperative shouts ('USE DATALOADER') rather than concrete steps or code.	1 / 5
Workflow Clarity	There are no multi-step workflows, no sequenced processes, and no validation checkpoints. The skill lists concepts and anti-patterns but never describes how to actually implement anything step by step. For a skill covering schema design, federation, subscriptions, and DataLoader, the complete absence of any workflow is a significant gap.	1 / 5
Progressive Disclosure	The content has some section structure (Capabilities, Patterns, Anti-Patterns, Sharp Edges) but everything is inlined at a shallow level with no references to supporting files. Given the breadth of topics covered (federation, subscriptions, codegen, Apollo client/server, urql), this content desperately needs separate reference files for each major topic. No bundle files exist to support progressive disclosure.	2 / 5
	Total	7 / 20 Passed

Description

18%Scale 1-5

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 description is written as a second-person persona narrative rather than a functional skill description. It contains zero concrete actions, no 'Use when' guidance, and relies on storytelling instead of specifying capabilities. While it touches on GraphQL performance concepts (N+1, nested queries), it fails to communicate what the skill actually does or when it should be selected.

Suggestions

Replace the narrative persona with concrete action verbs describing what the skill does, e.g., 'Identifies and resolves N+1 query problems, optimizes deeply nested GraphQL queries, implements DataLoader patterns, and designs efficient GraphQL schemas.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user mentions GraphQL performance, query optimization, N+1 problems, resolver efficiency, or slow GraphQL APIs.'

Switch from second-person voice ('You're a developer') to third-person voice describing capabilities ('Analyzes GraphQL APIs for performance issues').

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. It uses narrative storytelling ('You've seen the N+1 query problem') rather than describing what the skill actually does. There are no actionable capabilities listed.	1 / 5
Completeness	The description answers neither 'what does this do' nor 'when should Claude use it.' It is written entirely as a persona/backstory narrative with no functional description and no 'Use when...' clause or equivalent trigger guidance.	1 / 5
Trigger Term Quality	It includes some relevant domain keywords like 'GraphQL', 'N+1 query problem', 'nested queries', and 'APIs' that users might mention. However, these are embedded in narrative prose rather than presented as clear trigger terms, and common variations like 'schema design', 'resolvers', 'query optimization', or 'dataloader' are missing.	3 / 5
Distinctiveness Conflict Risk	While 'GraphQL' narrows the domain somewhat, the description is so vague about what it actually does that it could overlap with any GraphQL-related skill — schema design, client queries, API security, performance optimization, etc. The lack of specific capabilities creates high overlap risk.	2 / 5
	Total	7 / 20 Passed

Validation

90%

Warnings & errors only

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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/graphql/SKILL.md
Commit: 57c135b

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.