Content
86%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-structured, actionable skill body with executable examples for both transports and clean one-level-deep progressive disclosure. Slight verbosity in the spec/background sections and absence of an explicit test-failure feedback loop are the only weak spots.
Suggestions
Trim the Overview's restatement of the GraphQL spec subscription execution model and the 'Parsing results' re-explanation of the iterate() result shape — Claude already knows these.
Add a short validate→fix→retry loop in the workflow for when a subscription test hangs or emits an unexpected errors payload (e.g. check errors, inspect close code, adjust retryAttempts).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient with copy-paste code and a tight anti-patterns table, but the Overview/'Parsing results' sections restate the spec execution model and iterate() result shape that Claude largely already knows. | 4 / 5 |
Actionability | Fully executable guidance across both transports — install commands, complete TypeScript test snippets, jest config, and CI YAML — covering the common cases copy-paste ready. | 5 / 5 |
Workflow Clarity | A clear 7-step 'How to use' sequence with checkpoints (check errors before data, dispose/close in afterAll, forceExit in CI), but no explicit validate→fix→retry feedback loop for failing tests. | 4 / 5 |
Progressive Disclosure | SKILL.md is a concise overview with four clearly-signaled, one-level-deep reference files (transport-server-setup, auth-on-connect, lifecycle-and-close-codes, resolver-and-filter-tests), no nested references, content appropriately split. | 5 / 5 |
Total | 18 / 20 Passed |