CtrlK
BlogDocsLog inGet started
Tessl Logo

loop

Schedule a prompt to fire on a fixed cadence (recurring loop). Use when the user asks to "run X every N minutes/hours/days", "loop X", "babysit Y", "be proactive about Y every N", or invokes `/loop` directly. Parses `[interval] <prompt>`, picks a clean cron expression, registers the job via the `cron` tool, and executes the prompt once immediately so the user sees activity without waiting for the first cron tick.

75

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 well-structured, actionable instruction skill that turns free-form input into a concrete cron call with clear parse rules, mapping tables, and worked examples. It assumes Claude's competence and stays tight, with only minor redundancy and a small validation gap around cron-call failure.

Suggestions

Trim the closing rationale in section 5 ('This is the don't-make-the-user-wait rule...') since the heading and first bullet already convey it.

Add a brief fallback in section 4 for when the cron tool call fails (e.g., surface the error and do not attempt the immediate run), giving the workflow an explicit recovery checkpoint.

DimensionReasoningScore

Conciseness

Mostly lean — it assumes Claude knows cron and regex rather than explaining them, and uses compact tables — but a few lines (e.g. the closing rationale in section 5) restate what the heading and first bullet already convey.

4 / 5

Actionability

Provides fully executable guidance: an explicit parse regex, an exact interval→cron mapping table, a worked examples table covering edge cases (7m rounding, 30s, empty, autonomous), and concrete default/rounding values.

5 / 5

Workflow Clarity

A clear 7-step numbered sequence with a guard in step 1 (empty input → usage hint, stop) and a rounding-communication checkpoint in step 3, but lacks an explicit recovery path if the cron call itself fails.

4 / 5

Progressive Disclosure

A self-contained, single-purpose skill with no external bundle files; content is organized into well-labeled numbered sections with no nesting or buried references, so the well-organized-sections exception applies.

5 / 5

Total

18

/

20

Passed

Description

100%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 high-quality description that concisely states concrete capabilities, provides explicit 'Use when' trigger guidance with natural phrasings, and carves out a distinct scheduling niche. Uses third-person voice throughout with no padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Schedule a prompt to fire', 'Parses [interval] <prompt>', 'picks a clean cron expression', 'registers the job via the cron tool', 'executes the prompt once immediately' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (schedule/parse/map/register/execute) and 'when' via a 'Use when...' clause with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Covers natural phrasings users would actually say — "run X every N minutes/hours/days", "loop X", "babysit Y", "be proactive about Y every N", and "/loop directly" — with synonym variation across the domain.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (recurring prompt scheduling via cron) with distinct triggers tied to /loop and 'every N' phrasings, minimizing overlap with other skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
XiaomiMiMo/MiMo-Code
Reviewed

Table of Contents

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.