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.
The content is lean, highly actionable, and well-structured with executable commands and a properly signaled one-level reference file; its only gap is the lack of an explicit validation feedback loop in the discovery workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and code-forward with no padding about what TanStack or libraries are, but a few prose passages (the 'HIGH Tension' meta-section and Common Mistakes explanations) could be trimmed slightly, fitting 'efficient; minor instances of over-explanation'. | 4 / 5 |
Actionability | Commands are fully executable and copy-paste ready ('npx @tanstack/cli libraries --json', 'npx @tanstack/cli doc router framework/react/guide/routing', 'search-docs "server functions" --library start --json') and the Wrong/Correct pairs cover the common cases comprehensively. | 5 / 5 |
Workflow Clarity | The HIGH mistake provides a clear two-step sequence (resolve valid library id, then fetch) where the resolve step acts as the preflight validation checkpoint, but there is no explicit error-recovery feedback loop (e.g. 'if the id is invalid, re-run libraries'), keeping it just below 5. | 4 / 5 |
Progressive Disclosure | The body is a well-organized overview (Setup, Core Patterns, Common Mistakes, References) with a clearly signaled one-level-deep reference to references/discovery-command-output-schemas.md (a real file), keeping bulky output schemas appropriately out of the main skill. | 5 / 5 |
Total | 18 / 20 Passed |