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

77%

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 ./packages/core/src/skills/bundled/loop/SKILL.md

Quality

Content

76%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.

A highly actionable, well-structured instruction-only skill with concrete parsing rules, cron mappings, and explicit re-arm logic. Its main weakness is the missing pre-confirmation validation on the batch '/loop clear' subcommand, which caps workflow clarity.

Suggestions

Add a pre-deletion confirmation step to '/loop clear' (e.g., list jobs and confirm with the user before calling CronDelete on every job) to satisfy batch-operation validation and lift the workflow_clarity cap.

Tighten the prompt-only path's edge-case prose (monitor restart counts, ambiguous-signal handling) into terser rules to improve conciseness.

Consider splitting the loop.md task-file mode and Autonomous mode into a short reference file if the body grows further, to keep the overview scannable.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes Claude's competence (no explaining of cron basics), but some edge-case prose around monitor restart counts and ambiguous-signal handling could be trimmed; mostly efficient with minor over-explanation.	4 / 5
Actionability	Guidance is fully concrete and executable: exact regex ('^\d+[smhd]$'), a copy-paste cron conversion table, exact sentinel strings, and exact tool-call parameters with explicit re-arm rules.	5 / 5
Workflow Clarity	Paths are clearly sequenced with feedback loops (monitor restart-once-then-stop, three-tick ambiguity escalation), but the '/loop clear' batch delete lacks a pre-deletion validation checkpoint, which caps workflow clarity at 3 per the batch-operation guidance.	3 / 5
Progressive Disclosure	A single self-contained file organized into clearly labeled sections (Subcommands, Parsing, each path, Autonomous mode) with no nested references; good structure, though at ~100 lines a couple of mode-specific sections could conceivably be split out.	4 / 5
	Total	16 / 20 Passed

Description

78%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 covers what the skill does and gives concrete usage triggers, with a clear distinct niche. It could be marginally stronger with a direct 'Use when...' phrasing and a few more synonyms, but is well above average.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities ('runs a prompt now and follows up either on a fixed schedule or through self-paced wakeups', 'list to show jobs', 'clear to cancel all'), with only minor gaps in describing the follow-up mechanics.	4 / 5
Completeness	Clearly states what the skill does and provides equivalent explicit trigger guidance through 'Usage -' examples; scored 4 rather than 5 because the 'when' is conveyed via invocation examples rather than a direct declarative 'Use when...' clause.	4 / 5
Trigger Term Quality	Natural invocation phrases appear via usage examples ('check the build', 'check the PR every 30m', '5m', 'list', 'clear'), giving good keyword coverage, though synonyms like 'remind', 'repeat', or 'schedule' are absent.	4 / 5
Distinctiveness Conflict Risk	The '/loop' command niche with its distinctive cron/wakeup scheduling domain and explicit syntax has minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 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: 054eabb

Reviewed: 1 day 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.