Content
92%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.
Highly actionable, well-structured reference-style skill: executable examples for every mode, clear mode-selection guidance, and explicit boundaries. The only improvement is removing the small amount of duplication between the Modes table and the per-mode sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes competence, but a few facts are stated twice — "verifies each value against the source... returned as null" and "favicons never get promoted" appear in both the Modes table and their dedicated sections, and the structured-over-tables guidance is repeated in Anti-Patterns. Not 5: these duplications could be trimmed. | 4 / 5 |
Actionability | The Quick Reference provides copy-paste-ready JSON tool calls covering structured, schema, selector, metadata, tables, raw-HTML, and named-schema invocations, and the Modes table gives exact selection criteria — specific examples cover the common cases. | 5 / 5 |
Workflow Clarity | This is a single-purpose skill whose one action (choose a mode, call the tool) is unambiguous thanks to the Modes table, Anti-Patterns, and a When-NOT-to-use section; no destructive or batch operations are involved, so no validation cap applies. | 5 / 5 |
Progressive Disclosure | A self-contained ~75-line body with well-organized sections and no bundle files; the only references are one-level-deep, clearly signaled See Also links to sibling skills, making navigation trivial. | 5 / 5 |
Total | 19 / 20 Passed |