CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

graphql-architect

Use when designing GraphQL schemas, implementing Apollo Federation, or building real-time subscriptions. Invoke for schema design, resolvers with DataLoader, query optimization, federation directives.

64

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

73%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.

A strong body: excellent workflow sequencing with validation feedback loops, good executable examples, and a well-organized progressive disclosure structure. The main drags are token padding (keyword list, persona/footer, version pins) and a broken cross-reference inside one bundle file.

Suggestions

Delete the 'Knowledge Reference' section — it only enumerates technologies Claude already knows and adds no actionable value.

Trim the persona intro sentence and author footer, and move version pins like 'Apollo Federation 2.5+' into a dedicated versioning or deprecation note.

Fix the broken cross-reference in migration-from-rest.md: 'federation-guide.md' should be 'federation.md'.

Add the exact composition-check command to workflow step 3 so the validation checkpoint is directly executable.

DimensionReasoningScore

Conciseness

Mostly lean checklists and code, but padded with a 'Knowledge Reference' keyword dump ("Apollo Server, Apollo Federation 2.5+, GraphQL SDL, DataLoader, GraphQL Subscriptions, WebSocket, Redis pub/sub, schema composition...") that names technologies Claude already knows, a persona intro ("Senior GraphQL architect specializing in..."), an author/footer section, and version pins ("Apollo Federation 2.5+" twice) placed outside any deprecation/version note.

3 / 5

Actionability

Concrete, executable examples cover the common cases (federation SDL, DataLoader context setup with ordering comment, createComplexityRule validation config), but "Run schema composition check" names no command (e.g., rover supergraph compose) and the DataLoader example is a fragment without surrounding setup.

4 / 5

Workflow Clarity

Six clearly sequenced steps with explicit validation checkpoints and error-recovery feedback loops: "If composition fails: review entity @key directives, check for missing or mismatched type definitions across subgraphs, resolve any @external field inconsistencies, then re-run composition" and "If complexity threshold is exceeded: identify the highest-cost fields, add pagination limits, restructure nested queries, or raise the threshold with documented justification".

5 / 5

Progressive Disclosure

The body is a clean overview with a reference table pairing each of six real files with a 'Load When' condition, all one level deep. However, migration-from-rest.md cross-references 'graphql-architect/references/federation-guide.md', which does not exist (the actual file is federation.md), creating a minor navigation gap.

4 / 5

Total

16

/

20

Passed

Description

78%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.

A solid description with explicit, concrete trigger guidance and good domain-specific keywords in third-person voice. Its main weaknesses are an implicit 'what' (it never states deliverables such as SDL schemas, subgraph configs, or resolver implementations) and slightly incomplete coverage relative to the skill's body.

Suggestions

After the 'Use when...' clause, state what the skill delivers (e.g., 'Produces SDL schemas, federation-ready subgraphs, and DataLoader-based resolver implementations') to explicitly answer the 'what'.

Add missing natural trigger terms like 'Apollo Server', 'subgraphs', and '.graphql' to broaden keyword coverage.

Mention query complexity/depth limiting and REST-to-GraphQL migration so the description matches the body's actual capability set.

DimensionReasoningScore

Specificity

Names the domain and multiple concrete capabilities ("designing GraphQL schemas, implementing Apollo Federation, or building real-time subscriptions... resolvers with DataLoader, query optimization, federation directives"), but omits security/complexity limiting and REST migration that the body covers, so coverage has gaps rather than being comprehensive.

4 / 5

Completeness

An explicit "Use when designing GraphQL schemas, implementing Apollo Federation, or building real-time subscriptions" clause covers 'when', and "Invoke for schema design, resolvers with DataLoader, query optimization, federation directives" lists capabilities, but the 'what' never states what the skill produces or delivers — it is an invocation list, not an action statement.

4 / 5

Trigger Term Quality

Good natural terms users would say ("GraphQL schemas", "Apollo Federation", "real-time subscriptions", "DataLoader"), but misses common variations like "Apollo Server", "subgraphs", or the ".graphql" file extension.

4 / 5

Distinctiveness Conflict Risk

A clear GraphQL/Apollo Federation niche with distinctive trigger phrases; every term is GraphQL-scoped, so it is unlikely to fire for generic API or database skills despite sharing "schema design" and "query optimization" vocabulary.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Jeffallan/claude-skills

Path

skills/graphql-architect/SKILL.md

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.