ssong-skills/things-skill
Manage Things 3 tasks on macOS via AppleScript. Full CRUD: view, create, complete, move, and delete tasks and projects across all Things 3 lists.
98
100%
Does it follow best practices?
Impact
96%
2.04xAverage score across 5 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that excels across all dimensions. It provides specific concrete actions, includes abundant natural trigger terms and example user phrases, explicitly addresses both what the skill does and when to use it, and is clearly scoped to the Things 3 application on macOS. The description is comprehensive without being unnecessarily verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: view lists, create tasks with deadlines and tags, complete tasks, move between projects, set due dates, search, and organize. These are clearly defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (manage Things 3 tasks with specific actions listed) and 'when' (explicit trigger guidance with 'This skill should be used when...' followed by detailed trigger scenarios and example phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural user phrases: 'Things 3', 'tasks', 'to-dos', 'inbox', 'today', 'upcoming', 'someday', 'add a task', 'show my inbox', 'what do I need to do today', 'mark it done', 'my to-do list'. These are highly natural terms users would actually say. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to 'Things 3 on macOS' which is a specific application, making it highly distinguishable from generic task management or other to-do app skills. The app name and platform provide a clear niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that is concise, highly actionable, and well-structured. It provides complete executable examples for all common operations, enforces a robust validation workflow (show-before-modify, check return values, verify with follow-up queries), and appropriately delegates the full AppleScript API to a reference file. The guidance on building reports from query output rather than creation arguments is a particularly thoughtful safety measure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No unnecessary explanations of what Things 3 is, what AppleScript is, or how JSON works. The content is dense with actionable information and assumes Claude's competence throughout. | 3 / 3 |
Actionability | Provides fully executable shell commands with concrete examples for every operation (query, create, complete, move, delete). The error-checking pattern is copy-paste ready, and the jq-based report generation pattern is specific and executable. | 3 / 3 |
Workflow Clarity | Excellent workflow with explicit validation checkpoints: show before modifying, capture and check every return value for errors, verify mutations with follow-up queries, and build reports from verified query output rather than creation args. The error recovery path for ambiguous matches is clearly specified. | 3 / 3 |
Progressive Disclosure | Clean structure with quick-reference command tables in the main file and a clear one-level-deep reference to the full AppleScript API in references/applescript-api.md. The main file covers all common operations while appropriately deferring the full API reference. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents