CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

73

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

93%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.

Excellent CLI skill content: entirely executable commands organized into clean sections (setup, read, write, add examples, modify examples, limitations), with dry-run previews and an auth-token workflow making write operations safe. The only gap is the absence of an explicit post-update verification step in the modify workflow.

DimensionReasoningScore

Conciseness

The body is command-list style with zero concept explanation — it never explains what Things 3 or a URL scheme is, jumps straight to executable commands (e.g., "`things add "Buy milk" --notes "2% + bananas"`"). Every line is a command, flag, or operational note, matching the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

All guidance is copy-paste-ready: read commands ("`things inbox --limit 50`", "`things search "query"`"), write examples covering notes, when/deadline, list, heading, tags, checklist items, and a full update workflow with concrete flag combinations ("`things update --id <UUID> --auth-token <TOKEN> --completed`"). Specific examples cover the common cases, matching the top anchor.

5 / 5

Workflow Clarity

The modify workflow is well sequenced with an explicit safety checkpoint ("Prefer safe preview: `things --dry-run add`"; "First: get the ID (UUID column): `things search "milk" --limit 5`") plus error-recovery guidance ("If DB reads fail: grant Full Disk Access"), but there is no post-write verification step (e.g., re-running search to confirm the change), so it fits 'clear sequence with most checkpoints' rather than the full validate-feedback-loop anchor at 5.

4 / 5

Progressive Disclosure

This is a single-purpose, ~60-line skill with no bundle files; all content (setup, read ops, write ops, examples, limitations) appropriately lives inline under clear section headers with nothing that belongs in a separate file, and navigation is trivial. It matches the simple-skill pattern where well-organized sections in one file score full marks; the 4 anchor would require misplaced or poorly-split content, which is absent.

5 / 5

Total

19

/

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.

A strong description: it states concrete capabilities (add/update via URL scheme, read/search/list from the local database) and gives an explicit 'Use when' clause with concrete trigger phrases. The only room for improvement is broader synonym coverage (todos, reminders, mark complete) in the trigger terms.

DimensionReasoningScore

Specificity

The description enumerates concrete actions across the tool's full surface: "add/update projects+todos via URL scheme; read/search/list from the local Things database" — matching the comprehensive multi-action anchor rather than the 'minor gaps' anchor at 4, since add, update, read, search, and list cover the CLI's operations.

5 / 5

Completeness

It explicitly answers both parts: what ("Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database)") 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 trigger phrases, matching the top anchor; the 4 anchor applies only when the 'when' is less explicit.

5 / 5

Trigger Term Quality

Natural phrases like "add a task to Things", "list inbox/today/upcoming", "search tasks", and "inspect projects/areas/tags" give good keyword coverage, but common synonyms such as "todos/to-dos", "reminders", or "mark complete" are absent — fitting the 'good coverage, a few natural terms missing' anchor rather than the comprehensive-synonyms anchor at 5.

4 / 5

Distinctiveness Conflict Risk

"Things 3", "things CLI", "macOS", and Things-specific terms (inbox/today/upcoming, projects/areas/tags) define a clear niche with distinct triggers and minimal overlap with any generic task-management or database skill.

5 / 5

Total

19

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

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
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.