using-cron

Manage scheduled tasks — create, query, update, and delete. CRITICAL - When user message contains any future time intent (e.g. "in 2 days", "tomorrow at 8am", "every morning"), you MUST load this skill first. NEVER write custom scheduler scripts.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable commands and complete parameter/output documentation, and is well organized. It loses points for bilingual duplication and redundant examples (conciseness) and for lacking explicit validation/feedback loops around destructive operations (workflow_clarity), plus a monolithic single-file structure (progressive_disclosure).

Suggestions

Remove the  Chinese mirror blocks (or move them to a separate localized reference) and drop the standalone "Usage Examples" section that duplicates commands already shown per-script, to tighten conciseness.

Add an explicit validation checkpoint after create (e.g. confirm the returned schedule_id with get.py before further operations) and a verify-before-delete step, plus an error-recovery note, to raise workflow_clarity.

Move the per-script SYNOPSIS/OPTIONS/OUTPUT reference into separate files under references/ (e.g. REFERENCE.md) and keep SKILL.md as a concise overview pointing to them, improving progressive_disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient API reference, but the bilingual <!--zh--> mirroring and a "Usage Examples" section that restates commands already shown in each script section add padding Claude does not need, so it is not fully lean.	2 / 3
Actionability	Provides full executable synopses, parameter tables with types/required flags, a --type/--day mapping table, JSON output shapes, and copy-paste-ready examples — concrete and complete rather than pseudocode.	3 / 3
Workflow Clarity	A clear numbered Typical Workflow sequence exists, but there are no explicit validation checkpoints or error-recovery feedback loops, and destructive operations (permanent delete) lack verify steps, capping it at 2.	2 / 3
Progressive Disclosure	Scripts are correctly signaled and all referenced files exist, with well-organized per-script sections, but the full per-script API reference is inlined in a single ~420-line SKILL.md with no separate reference files, fitting the "some structure, content that should be separate is inline" anchor.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 names concrete CRUD actions, includes natural user-facing temporal trigger phrases, and explicitly pairs capability with a clear use-when clause and anti-conflict steering. It fully satisfies the what/when/which-skill criteria.

Dimension	Reasoning	Score
Specificity	Lists four concrete CRUD actions — "create, query, update, and delete" — matching the anchor for multiple specific concrete actions, not just naming a domain.	3 / 3
Completeness	Explicitly states what ("Manage scheduled tasks — create, query, update, and delete") and when ("When user message contains any future time intent ... you MUST load this skill first"), satisfying both halves with an explicit trigger.	3 / 3
Trigger Term Quality	Includes natural temporal phrases users would say ("in 2 days", "tomorrow at 8am", "every morning") plus "future time intent", giving good coverage rather than just some relevant keywords.	3 / 3
Distinctiveness Conflict Risk	A clear scheduled-tasks niche with distinct future-time triggers and an explicit anti-conflict directive ("NEVER write custom scheduler scripts"), making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: dtyq/magic
Path: backend/super-magic/agents/skills/using-cron/SKILL.md
Commit: 41d7ef4

Reviewed: about 13 hours 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.