CtrlK
BlogDocsLog inGet started
Tessl Logo

schedule-ops-skill

当用户要把任务交给后台异步执行、按 cron / 周期性重复、委派给项目 Agent 长时间跑,或查看/审批/取消看板任务时触发。典型说法"每天 9 点帮我 X"、"让 coder agent 跑这个"、"有哪些待审批"。**不用于**:一次性即时答复(→直接用工具)、真实日历会议 / 约会(→calendar-ops-skill)、一次性计划审批(→`SubmitPlan`)。

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 detailed, actionable reference for scheduled-task operations with strong workflow sequencing and validation for destructive/batch operations. Its main weakness is redundancy: the ScheduledTaskWait rationale is reinforced across several sections, adding token cost without new information.

Suggestions

Consolidate the ScheduledTaskWait guidance into one authoritative section and reference it from elsewhere rather than re-explaining the rationale in both '什么时候用哪个工具' and '常见错误与防范'.

Tighten or remove the repeated '原因:' rationale sentences in the common-errors section, keeping the rule and example but dropping the explanatory padding Claude can infer.

Replace the '...' and '{...}' placeholders in the create examples with minimal concrete parameter sets so the guidance is fully copy-paste ready.

DimensionReasoningScore

Conciseness

Mostly efficient and well-organized, but the ScheduledTaskWait guidance is repeated across the dedicated section, the tool-selection list, and the common-errors section, and the repeated '原因' rationale lines add tokens that could be trimmed.

3 / 5

Actionability

Provides concrete tool calls with parameters (e.g. the complete resolve example and exact cron expressions with intervalMs values), though a few create examples use '...' / '{...}' placeholders leaving minor gaps.

4 / 5

Workflow Clarity

Multi-step processes are clearly sequenced with validation checkpoints — '先查后删' for batch cleanup, 'date' time checks before scheduling — and timeout handling offers a retry→handoff feedback loop; minor validation gaps remain around schedule-parameter verification.

4 / 5

Progressive Disclosure

Single-file skill (no bundle files exist) with clear section headers and horizontal-rule structure; well-organized for navigation, though the ~180-line body keeps some reference-like material (detailed cron table, common-errors catalog) inline that could be externalized.

4 / 5

Total

15

/

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 strong, specific description with concrete capability actions, natural trigger phrases, and explicit boundary guidance that cleanly separates it from neighboring skills. It answers both 'what' and 'when' without padding.

DimensionReasoningScore

Specificity

Names the domain and lists multiple concrete actions — '后台异步执行', '按 cron / 周期性重复', '委派给项目 Agent 长时间跑', '查看/审批/取消看板任务' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both what (async/background/cron task scheduling and management) and when (trigger conditions with concrete example phrases), plus a clear '不用于' exclusion clause.

5 / 5

Trigger Term Quality

Includes natural user utterances across the main use cases — '每天 9 点帮我 X', '让 coder agent 跑这个', '有哪些待审批' — phrases a user would genuinely say when needing this skill.

5 / 5

Distinctiveness Conflict Risk

Clear niche (scheduled/async task ops) with explicit disambiguation against calendar-ops-skill and SubmitPlan via the '不用于' clause, minimizing wrong-skill triggering.

5 / 5

Total

20

/

20

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
itsablabla/openloaf-web
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.