cron

Use this skill only for scheduled or recurring tasks. Manage jobs with qwenpaw cron list/create/get/state/update/pause/resume/delete/run, and always pass --agent-id explicitly.

Quality

83%

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

75%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 content with complete, executable command examples and a clear workflow. The main weakness is redundancy across Decision Rules, Common Mistakes, and Usage Tips, which inflates length without adding guidance.

Suggestions

Consolidate the repeated --agent-id, one-time-immediate, confirm-info, and list-before-modify points so they appear once (e.g. in Decision Rules) rather than being restated across Common Mistakes and Usage Tips.

Move the full Cron Expression Examples and Help Information listings into a reference file linked from SKILL.md to reduce the overview length and improve progressive disclosure.

Add an explicit validate-then-retry feedback loop (e.g. run qwenpaw cron state after a failed create/update and act on the reported error) to strengthen workflow clarity for destructive/batch operations.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with code blocks and lists instead of concept explanations, but Decision Rules, Common Mistakes, and Usage Tips restate the same handful of points (--agent-id, one-time-immediate, confirm missing info, list-before-modify), so it could be tightened.	3 / 5
Actionability	Provides copy-pasteable, fully executable commands for every subcommand plus multiple complete create examples covering cron, scheduled one-time, and scheduled repeating cases.	5 / 5
Workflow Clarity	A clear Minimal Workflow sequence is supported by a Minimum-Information checklist and validation checkpoints (confirm missing info, list before modify/delete, state to troubleshoot), with only minor gaps in explicit error-recovery feedback loops.	4 / 5
Progressive Disclosure	Single well-organized file with clear section headers and easy navigation; no external references are needed for this contained CLI reference, though the length and repeated content could be externalized for a cleaner overview.	4 / 5
	Total	16 / 20 Passed

Description

92%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, specific description that clearly states the trigger conditions and enumerates the concrete actions available. Adding common synonyms (reminder, daily/weekly/hourly, cron) would round out trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the scheduling domain and lists nine concrete subcommands (list/create/get/state/update/pause/resume/delete/run) plus an explicit --agent-id instruction, matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly states both what (manage jobs via the enumerated subcommands) and when (only for scheduled or recurring tasks) with a concrete trigger phrase.	5 / 5
Trigger Term Quality	'scheduled or recurring tasks' are natural trigger phrases, but common user variations such as reminder, daily/weekly/hourly, and cron are absent from the description, leaving good-but-not-comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	Scoped narrowly to cron/scheduled task management with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: agentscope-ai/QwenPaw
Path: src/qwenpaw/agents/skills/cron-en/SKILL.md
Commit: f6dbc1d

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.