things-todo

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

Quality

85%

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 body is an exemplary lean CLI skill: concrete executable commands, explicit read-back verification after every write, dry-run guards for destructive operations, and a gotchas section capturing real operational pitfalls. No changes are needed.

Dimension	Reasoning	Score
Conciseness	The body is entirely operational content — install command, auth handling, flag tables, gotchas — with no explanation of concepts Claude already knows; every line (e.g. "`--tags` is plural for add/update; `tasks --tag` is singular for filtering") earns its place.	5 / 5
Actionability	All guidance is copy-paste-ready: a real `things add "Book LHR-SFO..."` example with flags, concrete JSON read-back commands, UUID-based update/delete sequences, and a dry-run flag — fully executable with specific examples covering the common cases.	5 / 5
Workflow Clarity	Destructive and batch operations have explicit validation loops: "Always read back after writes", "Prefer `--dry-run` before bulk updates/deletes", and post-delete verification against both normal and trash search — exceeding the feedback-loop requirement rather than merely meeting it.	5 / 5
Progressive Disclosure	This is a single-file skill with no bundle directories; the content is well-organized into clear sections (Tool, Start, Add, Update/Delete, Conventions, Gotchas) and nothing that belongs in a separate reference file is inlined.	5 / 5
	Total	20 / 20 Passed

Description

71%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 concise and specific, enumerating six concrete operations for a clearly named domain tool. Its main weakness is the absence of an explicit 'Use when...' trigger clause and of natural synonyms like 'to-dos' or 'tasks' that users would say.

Suggestions

Add an explicit trigger clause, e.g. "Use when managing to-dos or tasks in Things 3 on macOS."

Include natural synonyms users would say — "to-dos", "tasks", "todo list" — to improve trigger-term coverage.

Briefly disambiguate from Apple Reminders in the description (e.g. "not Apple Reminders") to reduce overlap risk, since that distinction currently lives only in the body.

Dimension	Reasoning	Score
Specificity	"Things 3 via things CLI: add, list, search, update, delete, verify" lists six specific concrete actions covering the full CRUD lifecycle plus verification, matching the comprehensive-coverage anchor rather than the score-4 anchor with 'minor gaps'.	5 / 5
Completeness	The 'what' is explicit (the six CLI operations), but there is no "Use when..." clause or equivalent trigger guidance — usage is only weakly implied by naming the app, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	"Things 3", "things CLI", and the action verbs (add, list, search, update, delete) are terms a user of this app would naturally say, but common synonyms and variations like "to-dos", "tasks", "todo list", or "Reminders" are missing, fitting anchor 4 rather than 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	Naming the niche Things 3 app and its CLI gives a clear niche with mostly distinct triggers, but "things" is also an extremely common English noun and generic todo apps are closely related, leaving minor overlap risk rather than minimal.	4 / 5
	Total	16 / 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: 3f8c6a3

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.