Content
82%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 a tight, highly actionable catalog of executable jq/rg queries with clear structure and no padding of concepts Claude already knows; its main weakness is mild intro/trigger redundancy and the lack of an explicit sequenced workflow.
Suggestions
Merge the intro paragraph and the 'Trigger' section to remove redundancy and tighten conciseness toward 5.
Add a short 'Workflow' note (find session via sessions.json → inspect structure → run the matching query) to give the query catalog an explicit sequence for workflow_clarity.
Consider splitting the longer 'Common Queries' catalog into a referenced file if the skill grows, to preserve progressive disclosure at scale.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and mostly code with necessary domain-specific field documentation, but the intro paragraph and the separate 'Trigger' section slightly overlap and could be trimmed. | 4 / 5 |
Actionability | Each common query is copy-paste-ready bash/jq with real syntax, and the examples comprehensively cover listing, finding, extracting, searching, cost, counts, and tool-usage cases. | 5 / 5 |
Workflow Clarity | Location → Structure → Queries → Tips gives a clear, well-organized path; all operations are read-only so the destructive/batch validation cap does not apply, but it is a query catalog rather than a sequenced workflow with checkpoints. | 4 / 5 |
Progressive Disclosure | Clean section headers and a well-organized query catalog make navigation easy with no external references needed; at ~110 lines it exceeds the under-50-line simple-skill exception for a 5. | 4 / 5 |
Total | 17 / 20 Passed |