CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/graphql-subscription-test-author

Authors GraphQL subscription resolver test suites over graphql-ws (WebSocket) and graphql-sse (Server-Sent Events) transports: subscribe to event streams via the async-iterator API, assert emitted data shape and sequence, verify connection lifecycle and protocol close codes, and validate auth-on-connect (connectionParams / authenticate callback) plus resolver-level pubsub trigger logic. Use for real-time subscription operations; not for queries or mutations - for those use apollo-server-tests, graphql-yoga-tests, or mercurius-tests.

75

Quality

94%

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

Overview
Quality
Evals
Security
Files

Quality

Content

85%

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

A well-structured, highly actionable skill body with executable examples, a clear sequenced workflow, and clean one-level-deep progressive disclosure into verified reference files. Its main weakness is mild verbosity: the spec-overview paragraph and repeated auth/close-code guidance across sections could be consolidated.

Suggestions

Trim the Overview's first paragraph (subscription execution semantics Claude already knows) to a one-line stable-ID citation, keeping the spec pointer without the tutorial.

Consolidate auth-on-connect guidance so it lives primarily in references/auth-on-connect.md with a single summary line in the body, instead of restating connectionParams/authenticate and close code 4403 across 'When to use', 'How to use', the Auth section, the Worked example, and the Anti-patterns table.

Merge the 'Parsing results' section into the basic subscription test example (the check-errors-before-data pattern already appears there) to remove the duplicate snippet.

DimensionReasoningScore

Conciseness

Mostly efficient and actionable, but the Overview explains subscription semantics Claude already knows ('Each emitted result is executed independently against the schema, exactly like a query') and auth-on-connect / close-code 4403 guidance is repeated across 'When to use', 'How to use', the Auth section, the Worked example, and the Anti-patterns table, so it could be tightened.

2 / 3

Actionability

Provides copy-paste-ready, executable code throughout - createClient + client.iterate() loops, jest.config.ts, CI workflow YAML, install commands - with the full server bootstrap delegated to real reference files.

3 / 3

Workflow Clarity

A clear 7-step 'How to use' sequence with explicit verification checkpoints (check errors is undefined before reading data, assert close codes with retryAttempts: 0, dispose/close in afterAll), plus a 5-step worked example and an anti-patterns table acting as a failure-mode checklist.

3 / 3

Progressive Disclosure

The body is an overview pointing to four well-signaled reference files (transport-server-setup, auth-on-connect, lifecycle-and-close-codes, resolver-and-filter-tests); all four exist and are exactly one level deep - they link only to external URLs, not to further reference files - so content is appropriately split and easy to navigate.

3 / 3

Total

11

/

12

Passed

Description

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.

A strong, third-person description that states concrete capabilities, gives explicit use-when guidance, and clearly distinguishes itself from sibling query/mutation skills. No fluff or over-claims; voice is correctly third person.

DimensionReasoningScore

Specificity

Lists multiple concrete actions - 'subscribe to event streams via the async-iterator API, assert emitted data shape and sequence, verify connection lifecycle and protocol close codes, and validate auth-on-connect... plus resolver-level pubsub trigger logic' - matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what (the full action list) and when ('Use for real-time subscription operations; not for queries or mutations - for those use...'), with an explicit 'Use for...' clause.

3 / 3

Trigger Term Quality

Natural terms a user would say are well covered - 'GraphQL subscription', 'subscription resolver test suites', 'graphql-ws', 'graphql-sse', 'WebSocket', 'Server-Sent Events', 'real-time subscription operations' - with good coverage rather than jargon-only.

3 / 3

Distinctiveness Conflict Risk

Carves a clear niche (subscription test authoring over WS/SSE transports) and explicitly disambiguates from apollo-server-tests, graphql-yoga-tests, and mercurius-tests, making wrong-skill triggering unlikely.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents