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. Use the Code Mode tools described by this skill.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./backend/super-magic/agents/skills/using-cron/SKILL.md

Quality

Content

71%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.

Highly actionable CRUD skill with executable copy-paste examples and a clear rules/checklist section, weakened by repeated invocation boilerplate and a monolithic inline body that ignores the available scripts/ bundle. Tightening the scaffolding and either splitting reference material into files or documenting the scripts/ usage would raise the score.

Suggestions

Collapse the repeated run_sdk_snippet/tool.call scaffolding into one canonical pattern and show only the differing tool.call arguments per operation to reduce token cost.

Document a path to the existing scripts/*.py bundle (or move the per-operation detail tables/examples into reference files) so SKILL.md becomes a lean overview with one-level-deep references.

Add explicit per-step feedback loops for the destructive delete/update operations (e.g., 'if result.ok is false, surface result.content and stop — do not retry with a guessed id') to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of padding about concepts Claude already knows, but the same run_sdk_snippet/tool.call scaffolding is repeated across 7+ near-identical code blocks, which could be tightened; sits below the lean score-4 anchor.	3 / 5
Actionability	Fully copy-paste-ready run_sdk_snippet blocks for all five CRUD operations with real parameter values, plus custom-employee and long-content variants, covering the common cases comprehensively.	5 / 5
Workflow Clarity	Operations are clearly sequenced (create -> keep id -> get/update/delete) with a Rules checklist including validation (check result.ok, surface errors, never retry with guessed IDs); not 5 because validation is listed globally rather than woven as explicit per-step feedback loops.	4 / 5
Progressive Disclosure	Section headers provide some structure, but all CRUD examples and reference tables are inlined in a 217-line body and the provided scripts/ bundle files are never referenced or navigated to from the documented run_sdk_snippet pattern.	3 / 5
	Total	15 / 20 Passed

Description

88%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 names concrete CRUD actions and pairs them with explicit, natural future-time-intent trigger phrases so Claude knows both what it does and when to load it. Minor improvements could broaden trigger synonyms (e.g., 'remind me', 'schedule', 'every weekday').

Dimension	Reasoning	Score
Specificity	Names the domain and four concrete CRUD actions ("create, query, update, and delete"), matching the comprehensive-coverage anchor; not 4 because the full lifecycle of actions is covered rather than having minor gaps.	5 / 5
Completeness	Explicitly states what ("Manage scheduled tasks — create, query, update, and delete") and when (concrete future-time-intent trigger phrases), matching the both-answered-with-concrete-triggers anchor.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ("in 2 days", "tomorrow at 8am", "every morning") but is not exhaustive of synonyms (e.g., "remind me", "schedule", "every weekday"), so it sits just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	The future-time-intent trigger carves a fairly distinct niche, but "scheduled tasks" still overlaps with generic reminder/calendar skills, so it is mostly distinct with minor overlap risk rather than minimal conflict risk.	4 / 5
	Total	18 / 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: dtyq/magic
Path: backend/super-magic/agents/skills/using-cron/SKILL.md
Commit: f9973c5

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.