loop

Create a loop that runs a prompt now and follows up either on a fixed schedule or through self-paced wakeups. Usage - /loop check the build, /loop 5m check the build, /loop check the PR every 30m. /loop list to show jobs, /loop clear to cancel all.

Quality

83%

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

Quality

Content

85%

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

A highly actionable, well-sequenced skill body with concrete tool calls, cron mappings, and validation feedback loops, only slightly limited by a few verbose passages that could be condensed.

Suggestions

Factor the repeated "don't re-arm if complete/blocked" rules into a single shared note referenced by each path to reduce duplication and tighten conciseness.

Break the long monitor auto-stop bullet in the prompt-only path into a short decision table or sub-list for faster scanning.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and operational with no concept-explanation fluff, but several long compound bullets (monitor auto-stop handling) and the repeated "don't re-arm if complete/blocked" rules across sections could be tightened, so it falls short of the lean score-3 anchor.	2 / 3
Actionability	Provides fully executable guidance: a concrete interval-to-cron table, exact sentinels, and named tool calls with specific parameters (delaySeconds, recurring, durable), matching the copy-paste-ready anchor.	3 / 3
Workflow Clarity	Each path is a numbered sequence with explicit decision checkpoints and feedback loops (three-tick ambiguous-signal termination, monitor restart-once-then-end on repeated auto-stop), satisfying the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	No bundle files exist; the single cohesive skill is organized into clearly headed sections with no nested-reference anti-pattern, so well-organized inline content earns the top score.	3 / 3
	Total	11 / 12 Passed

Description

82%

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 specific, well-triggered description with concrete actions and a distinct niche, weakened only by the absence of an explicit "Use when..." condition that would lift completeness to the top level.

Suggestions

Add an explicit trigger condition such as "Use when the user wants to repeatedly check or advance something on a schedule or while away" to raise completeness from 2 to 3.

Optionally state the natural-language trigger (e.g. "Use when the user says 'loop', 'keep checking', or 'run this every N minutes'") alongside the existing usage examples.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "runs a prompt now", "follows up either on a fixed schedule or through self-paced wakeups", "list to show jobs", "clear to cancel all" — matching the multiple-specific-actions anchor rather than the partial score-2 anchor.	3 / 3
Completeness	Clearly states what the skill does but lacks an explicit "Use when..." clause; the "Usage -" examples show invocation rather than a triggering condition, so per the guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Embeds natural phrasings a user would actually say ("check the build", "5m check the build", "check the PR every 30m", "list", "clear"), giving good coverage rather than only jargon.	3 / 3
Distinctiveness Conflict Risk	The /loop, cron, and wakeup scheduling niche is distinct with unique triggers, making conflict with other skills unlikely.	3 / 3
	Total	11 / 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: QwenLM/qwen-code
Path: packages/core/src/skills/bundled/loop/SKILL.md
Commit: 8878264

Reviewed: 5 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.