Content
76%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A tight, highly actionable CLI reference that respects the reader's intelligence and covers the command surface thoroughly. The main gaps are the missing safety validation around destructive delete operations and a slightly over-inline due-vs-alarm section that could be split out.
Suggestions
Add a validation step before destructive commands, e.g. "Run `remindctl list <name>` or `remindctl today --json` to confirm the ID/list before `delete`/`--delete --force`, and confirm with the user for irreversible deletions" — this would lift workflow_clarity above the cap.
Move the extended due-vs-alarm explanation (EKCalendarItem/EKReminder docs note) into a small references/ file to tighten the main body.
Trim the restated iCloud-sync sentence in the intro, which duplicates the 'When to Use' section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is a lean command reference with almost no concept-explanation padding; the only trimmable bits are the "Apple's public EKReminder docs list only reminder-specific properties" aside and the Reminders.app/iCloud restatement, which is 'efficient with minor instances of over-explanation' rather than the every-token-earns-its-place level 5. | 4 / 5 |
Actionability | Every section is copy-paste-ready `remindctl` syntax with realistic values ("Buy milk", "2026-05-15 14:00"), covering viewing, list management, creating, editing, completing, deleting, and output formats — fully executable guidance for the common cases. | 5 / 5 |
Workflow Clarity | Sequences are unambiguous per command and there is a verify-with-JSON check after edits, but destructive operations are shown without validation — "remindctl delete 4A83 --force" and "remindctl list Work --delete" appear with no check-first or confirm-before-delete step, so the destructive-operations cap of 3 applies. Not score 2 because the per-command guidance itself is clear and rule 2 does mandate confirming content before creating. | 3 / 5 |
Progressive Disclosure | The skill is self-contained (no references/scripts/assets bundle exists) with well-organized sections that keep everything appropriately inline for a CLI quick reference; this is 'good structure with minor organization gaps' rather than a 5, since the ~117-line body with the due-vs-alarm deep dive could plausibly live in a separate reference file. | 4 / 5 |
Total | 16 / 20 Passed |