CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

40

Quality

40%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/graphql/SKILL.md

The canonical home for this skill is graphql in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

40%Weight 40%Scale 1-5

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

The body is well-sectioned but content-thin: it provides no executable code or commands, no defined workflow, and a placeholder When-to-Use, relying on terse one-liners and comment-style solutions. Several sections are empty or truncated, which undercuts the otherwise clean structure.

Suggestions

Add concrete, executable examples for the key patterns — a DataLoader batching snippet, a query depth/complexity limit config, and a field-level authorization resolver — instead of one-line descriptions and comment-style solutions.

Define an actual review workflow with validation checkpoints (e.g., check N+1 → check depth/complexity limits → check authorization in resolvers → check nullability design) and replace the generic "When to Use" placeholder with real trigger guidance.

Remove the duplicated persona intro and the truncated "You've l" sentence, and flesh out the empty Anti-Patterns entries with concrete guidance so every section earns its tokens.

DimensionReasoningScore

Conciseness

The body is short overall, but the persona intro is duplicated verbatim from the frontmatter and the "hard-won lessons" anecdote is atmospheric fluff that assumes Claude does not already know these GraphQL pitfalls, so it could be tightened.

3 / 5

Actionability

There is no executable code or commands anywhere; the Sharp Edges "solutions" are comment-style hints ("# USE DATALOADER", "# LIMIT QUERY DEPTH AND COMPLEXITY") and the Patterns are one-liners ("Batch and cache database queries"), giving only high-level hints rather than steps to execute.

2 / 5

Workflow Clarity

No multi-step process or sequence is defined — the body is a collection of lists and a table — and the "When to Use" section is a meaningless placeholder ("This skill is applicable to execute the workflow or actions described in the overview"), leaving rough structure but no actual workflow or checkpoints.

2 / 5

Progressive Disclosure

Sections are clearly headed (## Capabilities, ## Patterns, ## Anti-Patterns, ## Sharp Edges) and no external references are needed for this thin, self-contained content; minor gaps (empty Anti-Patterns entries, the placeholder When-to-Use, and a truncated sentence) keep it just below a 5.

4 / 5

Total

11

/

20

Passed

Description

40%Weight 40%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.

The description is a second-person persona narrative that evokes GraphQL's failure modes but never states what the skill concretely does or when to invoke it. It names a clear niche yet lacks an action list and a "Use when..." trigger clause.

Suggestions

Replace the persona narrative with a direct third-person capability list (e.g., "Designs, implements, and hardens GraphQL APIs: schema design, DataLoader batching, query depth/complexity limits, field-level authorization").

Add an explicit "Use when..." trigger clause with natural user phrases (e.g., "Use when building or debugging GraphQL APIs, or when the user mentions N+1 queries, DataLoader, query depth limiting, Apollo, or urql").

Switch from second-person to third-person voice and add common synonyms/triggers (Apollo, federation, subscriptions, codegen) to lift trigger-term coverage and specificity.

DimensionReasoningScore

Specificity

It names the GraphQL domain and concrete failure modes ("N+1 query problem", "deeply nested queries"), but frames them as persona experience rather than concrete actions the skill performs; the second-person voice ("You're a developer", "You've seen") triggers the rubric's -1 specificity penalty, pulling a base of 3 down to 2.

2 / 5

Completeness

The "what" is only a vague persona framing ("You're a developer who has built GraphQL APIs at scale") rather than a clear capability statement, and there is no "Use when..." clause or equivalent trigger guidance, matching the vague-what/no-when anchor.

2 / 5

Trigger Term Quality

"GraphQL APIs" and "N+1 query problem" are relevant, naturally-said keywords, but coverage is thin and missing common variations users would say (DataLoader, query depth, Apollo, federation, subscriptions, schema design).

3 / 5

Distinctiveness Conflict Risk

"GraphQL APIs at scale" is a clear, distinct niche with minimal conflict risk against related skills like backend or postgres-wizard; the only weakness is the persona framing lacking explicit distinct triggers.

4 / 5

Total

11

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.