Content
36%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.
This is an unfilled starter template: structurally clean and concise, but its content is placeholder prompts to the author rather than actionable guidance for the agent. It scores well on conciseness and structure but fails on actionability and workflow clarity because there is nothing concrete to execute.
Suggestions
Replace the placeholder prompts under 'Steps' with concrete, executable instructions (specific files, commands, or code) the agent can follow.
Fill in the 'When to use' section with concrete triggering situations so the workflow is meaningful.
Add an explicit validation/verification step for any destructive or batch operations the real skill performs.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is short and uncluttered, and though it is placeholder scaffolding rather than real content, it does not pad with concepts Claude already knows; it earns slightly above the midpoint for lean efficiency. | 4 / 5 |
Actionability | The body only describes what an author should do ('Describe the situations', 'State the inputs') rather than instructing the agent how to execute; it contains no concrete code, commands, or specific executable guidance. | 1 / 5 |
Workflow Clarity | A rough sequence of three steps is listed, but they are template prompts to fill in, not defined steps with validation checkpoints, so the sequence is poorly defined and validation is absent. | 2 / 5 |
Progressive Disclosure | The body is organized into clear sections (When to use, Steps) with no external references, which is appropriate for a short file; however the section bodies are empty placeholders rather than real overview content. | 3 / 5 |
Total | 10 / 20 Passed |