things-mac
Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks OpenClaw to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
92
93%
Does it follow best practices?
Impact
96%
3.55xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
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 clearly identifies the target application (Things 3), the mechanism (CLI + URL scheme + local database), and provides explicit trigger guidance with natural user terms like 'add a task', 'list inbox/today/upcoming', and 'search tasks'. The only minor oddity is the reference to 'OpenClaw' which appears to be a specific agent name rather than a generic reference, but this doesn't materially harm the description's quality.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: add/update projects+todos via URL scheme, read/search/list from the local Things database. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (manage Things 3 via CLI, add/update projects+todos, read/search/list from database) and when ('Use when a user asks to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'add a task to Things', 'list inbox/today/upcoming', 'search tasks', 'inspect projects/areas/tags', 'Things 3'. The term 'OpenClaw' is unusual but the rest covers natural user language well. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific application (Things 3), a specific platform (macOS), and a specific CLI tool. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
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, covers both read and write operations with concrete examples, and handles edge cases (delete not supported, Full Disk Access). The only notable weakness is that the modify/complete workflow could benefit from explicit sequencing with validation checkpoints, especially given that --completed and --canceled are semi-destructive operations.
Suggestions
Add an explicit numbered workflow for update operations (1. Search for ID → 2. Dry-run preview → 3. Execute) to make the validation checkpoint mandatory before destructive actions like --completed/--canceled.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose—setup, read commands, write commands, examples, and edge cases are all tightly written. No unnecessary explanations of what Things 3 is or how URL schemes work. Claude's intelligence is respected throughout. | 3 / 3 |
Actionability | All commands are concrete, copy-paste ready, and cover a wide range of use cases (add, update, search, read). Examples include specific flags, realistic values, and even STDIN multi-line input. The auth token workflow is clearly spelled out. | 3 / 3 |
Workflow Clarity | The update workflow (search for ID → set auth token → update) is present but implicit rather than explicitly sequenced with numbered steps. The --dry-run safe preview is mentioned but not positioned as a mandatory validation checkpoint before destructive operations like --completed/--canceled. | 2 / 3 |
Progressive Disclosure | For a single-purpose CLI skill under 80 lines with no need for external references, the content is well-organized into logical sections (Setup, Read, Write, Examples, Notes) with clear headers. No bundle files are needed and none are referenced. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Repository
- trpc-group/trpc-agent-go
- Commit
9f4b734
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.