CtrlK
BlogDocsLog inGet started
Tessl Logo

schedule-tasks

定时任务注册、管理、能力指南。支持周期任务和一次性延迟任务。 ⚠️ ROUTING: 定时/schedule/cron 需求优先用本 skill(Cat Café 本地定时任务), 不要用另一个叫 `schedule` 的 skill(那是云端 remote-agent,用途不同)。 Use when: 用户想设定时任务、定期提醒、周期巡检、定时发送内容、延迟执行一次性操作。 Not for: 已有 builtin 任务的手动触发。 Output: 注册/管理定时任务,任务到点唤醒猫执行。

79

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%Weight 40%Scale 1-3

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

A dense, table-driven body that gives concrete tool calls and trigger JSON, clear multi-step registration/deletion flows with explicit confirmation checkpoints, and clean section organization with no concept over-explanation. It is appropriately self-contained for its scope.

DimensionReasoningScore

Conciseness

The body is table-driven and dense (trigger JSON, template/error tables) with no explanation of concepts Claude already knows; the capability table is system-specific (rich-block types) and earns its place, matching the lean anchor rather than the padded level-2 case.

3 / 3

Actionability

Provides concrete tool names (cat_cafe_list_schedule_templates, cat_cafe_preview_scheduled_task, cat_cafe_register_scheduled_task, cat_cafe_remove_scheduled_task) and copy-paste-ready trigger JSON like {"type":"cron","expression":"0 9 * * *"}, meeting the fully-executable anchor.

3 / 3

Workflow Clarity

Both flows are explicitly sequenced — 注册流程 (4 steps: 识别意图→匹配模板→预览确认→注册) and 删除流程 (3 steps with confirm-target→user-confirm→delete), each with an explicit user-confirmation checkpoint, so the destructive delete is not capped at 2.

3 / 3

Progressive Disclosure

Single self-contained SKILL.md with no bundle files and no nested references; content is organized into clearly headed sections (能力, 注册流程, Trigger 语法速查, 管理, 常见错误) that navigate easily, satisfying the well-organized-sections allowance for reference-free skills.

3 / 3

Total

12

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 well-structured description that concretely states capabilities, supplies an explicit Use-when/Not-for/Output trigger structure, and proactively disambiguates a same-named sibling skill. It uses third-person declarative voice with no fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "定时任务注册、管理", "支持周期任务和一次性延迟任务", and the Use-when clause enumerates 设定时任务、定期提醒、周期巡检、定时发送内容、延迟执行一次性操作, matching the anchor for multiple specific concrete actions rather than the single-domain level 2.

3 / 3

Completeness

Explicitly answers both what ("定时任务注册、管理...支持周期任务和一次性延迟任务" + "Output: 注册/管理定时任务") and when (an explicit "Use when:" clause plus "Not for:"), so it is not capped at 2 by the missing-trigger-guidance rule.

3 / 3

Trigger Term Quality

The triggers list covers natural terms a user would actually say in both languages — "每天", "提醒我", "remind me", "in 5 minutes", "schedule", plus management verbs 删除/取消/cancel/delete — giving good coverage rather than the partial level-2 set.

3 / 3

Distinctiveness Conflict Risk

The explicit ROUTING note ("不要用另一个叫 `schedule` 的 skill,那是云端 remote-agent") plus "Not for:" carves a clear niche and proactively disambiguates a same-named conflicting skill, exceeding the level-2 overlap case.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
zts212653/clowder-ai
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.