Content
87%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, well-crafted skill that provides comprehensive, actionable CLI reference for Things 3 management. It's concise, well-organized, and covers both read and write operations with concrete examples. The only notable weakness is the lack of explicit verification steps after write/update operations, which would strengthen the workflow for destructive or state-changing commands.
Suggestions
Add a verification step after write/update operations, e.g., 'After updating, confirm with: things search "<title>" --limit 1' to close the feedback loop.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It assumes Claude knows what a URL scheme is, what UUIDs are, and how CLI tools work. Every section provides only the information needed to use the tool, with no unnecessary explanations or padding. | 3 / 3 |
Actionability | Every operation is demonstrated with concrete, copy-paste-ready CLI commands. The examples cover a wide range of use cases (basic add, with notes, into projects, with tags, checklists, STDIN, update operations) with specific flags and arguments. | 3 / 3 |
Workflow Clarity | The modify workflow has a clear sequence (search for ID → set auth → update), and dry-run is mentioned for safe preview. However, there are no explicit validation checkpoints or feedback loops — e.g., no step to verify the update succeeded or to check the result after adding a todo. For write operations that modify a task database, this is a gap. | 2 / 3 |
Progressive Disclosure | For a standalone skill with no bundle files, the content is well-organized into logical sections (Setup, Read-only, Write, Examples for add, Examples for modify, Delete, Notes). The structure is flat and easy to scan, with no need for external references given the scope. | 3 / 3 |
Total | 11 / 12 Passed |