Content
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with excellent workflow clarity and concrete executable examples throughout. Its main weakness is length—the document packs a lot of valuable detail inline that could benefit from being split into reference files for progressive disclosure, and some sections could be tightened to reduce token cost. The error handling table and decision matrix are particularly well done.
Suggestions
Trim the 'Before You Start' section to 1-2 sentences since the routing logic is already in the YAML description and decision matrix.
Consider extracting the 'Semantic Query Contract', 'Custom SQL Knobs', and 'Choosing Semantic Objects' sections into a separate REFERENCE.md to reduce the main file's token footprint and improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is thorough and mostly earns its tokens—decision matrices, error tables, and contract details are genuinely useful. However, some sections are verbose (e.g., the 'Choosing Semantic Objects' section re-explains concepts multiple times, and the 'Before You Start' preamble restates what the YAML description already covers). It could be tightened by ~20-30% without losing information. | 2 / 3 |
Actionability | The skill provides fully executable CLI commands with exact JSON payloads, concrete bash examples for each step, specific payload shapes for both typed and legacy forms, and clear good/bad examples for filters. Every major workflow step has copy-paste-ready commands. | 3 / 3 |
Workflow Clarity | The Standard Loop is clearly numbered with validation checkpoints (pilot small query first, inspect returned SQL, confirm workspace context). The 'Fastest Metric Path' provides an explicit step-by-step sequence. Error handling includes a comprehensive diagnostic table with specific recovery actions. The 'Latest Periods' section explicitly warns against a common mistake and provides a clear alternative workflow. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear section headers and a logical flow from decision matrix → standard loop → fastest path → contract details → error handling → reporting. However, with no bundle files, all content is inline in a single long document (~200+ lines). The semantic query contract details, custom SQL knobs, and choosing semantic objects sections could reasonably be split into reference files for better navigation. | 2 / 3 |
Total | 10 / 12 Passed |