things-todo

Things 3 via things CLI: add, list, search, update, delete, verify.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

100%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 well-structured, executable, and concise CLI skill with strong validation feedback loops around destructive and batch operations. No bundle files are present or needed, and nothing warrants splitting out.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout: executable commands, a flag list, and gotchas with no padding or explanation of concepts Claude already knows, fitting the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	Commands are fully executable and copy-paste ready (e.g. 'things add "..." --when tomorrow --tags travel', 'things delete --id <uuid> --confirm <uuid>'), with concrete examples covering add, read, update, and delete cases.	5 / 5
Workflow Clarity	Workflows are explicitly sequenced with validation feedback loops: add-then-read-back, find-UUID-then-mutate, '--dry-run' before bulk updates/deletes, and trash verification after delete, satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	The skill is a single self-contained SKILL.md with clearly organized sections (Tool, Start, Add, Update/Delete, Conventions, Gotchas); no content needs splitting into bundle files and navigation is easy.	5 / 5
	Total	20 / 20 Passed

Description

75%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 specific, distinct, and action-rich, but omits an explicit 'when to use' trigger clause, which limits its completeness. Adding a 'Use when...' phrase naming user intents (e.g. managing todos/tasks in Things 3) would raise it.

Suggestions

Append a 'Use when...' clause stating when Claude should invoke this skill (e.g. 'Use when the user asks to manage Things 3 to-dos or tasks on macOS').

Add natural synonyms like 'todo', 'task', or 'to-do' alongside 'Things 3' to broaden trigger-term coverage.

Keep the concise action list as-is; it is the strongest part of the description.

Dimension	Reasoning	Score
Specificity	Lists six concrete actions ('add, list, search, update, delete, verify') against a named domain (Things 3 via things CLI), matching the 'multiple specific concrete actions; comprehensive coverage' anchor.	5 / 5
Completeness	The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guideline.	3 / 5
Trigger Term Quality	'Things 3' and 'things CLI' plus the action verbs are natural user terms, but common synonyms like 'todo', 'task', or 'to-do' are missing, so it sits above the midpoint rather than at full coverage.	4 / 5
Distinctiveness Conflict Risk	'Things 3 via things CLI' targets a specific application with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: steipete/agent-scripts
Path: skills/things-todo/SKILL.md
Commit: dc4f583

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.