Tessl • The management layer for AI agent skills

SkillPublic

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

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

88%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.

Excellent procedural content: concrete, executable, and clearly sequenced with explicit error-recovery rules, and no padding of known concepts. The only real flaws are a dangling empty "## Input" section and slightly verbose monitor edge-case handling.

Suggestions

Remove or complete the dangling "## Input" heading that ends the body with no content.

Tighten the monitor auto-stop and ambiguous-signal bullets in the prompt-only path, which repeat conditions across multiple sentences.

Consider moving the autonomous-mode and loop.md task-file-mode sections into a reference file if the skill grows, keeping SKILL.md as a routing overview.

Dimension	Reasoning	Score
Conciseness	Dense, harness-specific instructions with essentially no explanation of concepts Claude already knows; only the monitor auto-stop and ambiguity-handling bullets run slightly long and could be tightened.	4 / 5
Actionability	Fully executable guidance: exact regex ("^\d+[smhd]$"), an interval-to-cron conversion table, concrete CronCreate/LoopWakeup parameter specifications, and seven worked input examples covering the common cases.	5 / 5
Workflow Clarity	The parsing section is an unambiguous decision tree, each path is fully sequenced with numbered steps and explicit tool-call parameters, and error-recovery loops are spelled out (restart a monitor once with a counter, end after repeated auto-stop, end after three ambiguous ticks).	5 / 5
Progressive Disclosure	Well-organized sections per path with no bundle files to reference, but a dangling empty "## Input" heading ends the document and the autonomous/loop.md modes remain fully inline; overall good structure with minor organization gaps.	4 / 5
	Total	18 / 20 Passed

Description

75%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: concrete actions, natural trigger phrasing via usage examples, and a distinct command niche. It would score higher with an explicit "Use when…" clause and coverage of the autonomous and task-file modes.

Suggestions

Add an explicit trigger clause such as "Use when the user wants to repeat or re-run a prompt on a schedule or keep checking something".

Mention the autonomous mode briefly (e.g., "or keep working autonomously when no prompt is given") to close the coverage gap.

Include a few natural synonyms ("recurring", "repeat", "on a schedule") alongside "loop" for broader trigger matching.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("Create a loop that runs a prompt now", "follows up either on a fixed schedule or through self-paced wakeups", "list to show jobs", "clear to cancel all"), but coverage has minor gaps — autonomous mode and the loop.md task-file mode are not mentioned.	4 / 5
Completeness	The "what" is clear (runs a prompt now and follows up on a fixed schedule or via self-paced wakeups) and the usage examples act as explicit trigger guidance, so the missing-Use-when cap does not apply; however, there is no explicit "Use when…" phrasing and the "when" could be more directly stated.	4 / 5
Trigger Term Quality	Natural phrases users would actually say ("check the build", "check the PR every 30m", "show jobs", "cancel") plus the /loop usage examples give good keyword coverage, though common synonyms like "repeat", "recurring", or "on a schedule" are missing.	4 / 5
Distinctiveness Conflict Risk	The /loop command syntax and list/clear subcommands form a clear niche with distinct triggers and minimal conflict risk; minor overlap remains with generic scheduling/recurring language that could match related skills.	4 / 5
	Total	16 / 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
Revision: e5db764

Reviewed: 7 hours ago

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.

loop

Table of Contents

Is this your skill?