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 Bitterbot to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

86%Weight 40%Scale 1-5

Reviews 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, executable command catalog with clear sectioning and safety-preview checkpoints on write operations. The chief trim opportunity is the repeated auth-token literal across update commands.

Suggestions

Factor the repeated `--auth-token <TOKEN>` pattern out of the update examples into a one-line note (e.g. 'All update commands require `--auth-token <TOKEN>` or `THINGS_AUTH_TOKEN`') to reduce padding.

Add an explicit validate-fix-retry note for write operations (e.g. run `--dry-run` first, confirm the printed URL, then run for real) to push workflow clarity toward a full feedback loop.

Consider collapsing near-duplicate 'safe preview' mentions into a single callout in the Write section.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept over-explanation, but the `--auth-token <TOKEN>` literal is repeated verbatim across seven update commands and could be factored into a note, fitting anchor 4 (minor trimmable padding).	4 / 5
Actionability	Fully executable, copy-paste-ready commands throughout — e.g. `things add "Buy milk" --notes "..."`, `things update --id <UUID> --auth-token <TOKEN> --completed`, and a heredoc STDIN example — covering the common cases per anchor 5.	5 / 5
Workflow Clarity	Read/write/modify sections are clearly organized and write ops include a `--dry-run` validation checkpoint ('prints the URL and does not open Things'), with the modify section sequencing ID retrieval, auth, then the update; only a minor validate-fix-retry loop is missing, fitting anchor 4.	4 / 5
Progressive Disclosure	No bundle files exist and none are needed for this single-CLI skill; the body is a well-organized self-contained reference with clear sections (Setup, Read-only, Write, Examples, Delete, Notes), satisfying the simple-skill exception for anchor 5.	5 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: it concisely conveys concrete capabilities and provides explicit 'Use when' trigger guidance tied to specific user requests. The only minor gap is keyword synonym breadth, leaving trigger term quality just below maximum.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'add/update projects+todos via URL scheme', 'read/search/list from the local Things database', 'list inbox/today/upcoming', 'inspect projects/areas/tags' — with comprehensive coverage matching the anchor 5 example.	5 / 5
Completeness	Explicitly states both what ('Manage Things 3 via the things CLI... add/update... read/search/list') and when ('Use when a user asks Bitterbot to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags') with concrete triggers, matching anchor 5.	5 / 5
Trigger Term Quality	Natural user phrases like 'add a task to Things', 'list inbox/today/upcoming', and 'search tasks' give good keyword coverage, but a few common synonyms (e.g. 'to-do', 'reminders') are absent, fitting anchor 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche (Things 3 task manager via the things CLI on macOS, tied to Bitterbot) with distinct triggers and minimal overlap with other skills, matching anchor 5.	5 / 5
	Total	19 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 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	13 / 16 Passed

Repository: Bitterbot-AI/bitterbot-desktop
Path: skills/things-mac/SKILL.md
Commit: 017761f

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.