Agent skill

QwenPaw Scheduled Tasks

by agentscope-ai in agentscope-ai/QwenPaw

Chinese-language guide to creating and managing scheduled or recurring tasks with the qwenpaw cron commands, always with an explicit agent id.

Apache-2.0Auto-check passedProductivity & Automation

SKILL.md written in Chinese; this summary is our English description.

Install QwenPaw Scheduled Tasks

skills CLI
$ npx skills add agentscope-ai/QwenPaw --skill cron -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install agentscope-ai/QwenPaw cron --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/qwenpaw/agents/skills/cron-zh .claude/skills/cron && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cron
GitHub stars
36k
Token cost
~1.4k tokens
SKILL.md length
247 words
Files
1
Skills in repo
20
Repo updated
First seen
Licence
Apache-2.0

At a glance

Chinese-language guide to creating and managing scheduled or recurring tasks with the qwenpaw cron commands, always with an explicit agent id.

  • Works in 7 steps: 只有在未来定时执行或周期执行时才使用 cron → 如果只是立即做一次,通常不要创建 cron → 创建前必须确认执行时间/周期、目标… → …
  • Setting a daily or weekly reminder through an agent
  • SKILL.md covers 什么时候用, 决策规则, 硬规则 and 常用命令, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Use only when something must run at a future time or repeatedly; a one-off action now, a normal reply, an unspecified time or an unclear target channel are not reasons to create a cron job. The qwenpaw cron commands cover list, create, get, state, update, pause, resume, delete and run, and every command must pass --agent-id explicitly, since leaning on the default agent can send tasks to the default workspace.

Two task types exist: text, which sends a fixed message, and agent, which asks an agent and delivers the reply to a channel. Two schedule types exist: cron for classic periodic schedules, and scheduled for tasks starting at a run-at time, one-off or repeating by day with count, until or never end types. The default timeout is 120 seconds; raise it for longer agent tasks but keep it below the schedule interval, within 80 percent for intervals of 10 minutes or less.

When your agent uses it

  • Setting a daily or weekly reminder through an agent
  • Scheduling a one-time task for a specific future time
  • Pausing, resuming or deleting an existing scheduled task
  • Running a recurring check that reports to a chat channel

Example prompts

  • “Create a daily task that asks my agent for a news summary every morning.”
  • “Pause the weekly report job and list the remaining tasks.”
  • “Schedule a one-off reminder for next Monday morning in my team channel.”

Requirements

  • The qwenpaw CLI
  • Your agent id, shown in the system prompt

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. 只有在未来定时执行或周期执行时才使用 cron
  2. 如果只是立即做一次,通常不要创建 cron
  3. 创建前必须确认执行时间/周期、目标 channel、target-user、target-session
  4. 所有 cron 命令都必须显式传 --agent-id
  5. 不要依赖默认 agent,否则任务可能落到 default workspace
  6. 如果 agent 任务只需后台执行、不向渠道输出,添加 --silent;执行、会话历史、追踪和可选收件箱记录仍会继续
  7. 迁入任务的 requires_review 未清除时,不得运行或恢复;必须先在 Console 中完成人工复核和批准

What it can do on your machine

Read from SKILL.md and the folder at commit d7a0f50. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

QwenPaw Scheduled Tasks loads about 1.4k tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 247 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from agentscope-ai/QwenPaw at commit d7a0f50, republished under its Apache-2.0 licence (© agentscope-ai). 247 words, ~1,422 tokens.

Download SKILL.mdSave it as .claude/skills/cron/SKILL.md (or your agent's skills folder).
name
cron
description
仅在需要未来定时执行或周期执行任务时,使用本 skill。使用 qwenpaw cron list/create/get/state/update/pause/resume/delete/run 管理任务,并始终显式传入 --agent-id。
metadata.builtin_skill_version
1.8

定时任务管理

什么时候用

只有在需要未来某个时间自动执行,或按周期重复执行时,使用本 skill。

应该使用
  • 用户要求"每天 / 每周 / 每小时"执行某事
  • 用户要求"明天 9 点 / 下周一 / 某个时间"自动提醒或执行
  • 需要长期周期性通知、检查、汇报
不应使用
  • 只是要现在立即执行一次
  • 只是当前会话中的正常回复
  • 用户没有明确执行时间或周期
  • 目标 channel / user / session 还不明确

决策规则

  1. 只有在未来定时执行或周期执行时才使用 cron
  2. 如果只是立即做一次,通常不要创建 cron
  3. 创建前必须确认执行时间/周期、目标 channel、target-user、target-session
  4. 所有 cron 命令都必须显式传 --agent-id
  5. 不要依赖默认 agent,否则任务可能落到 default workspace
  6. 如果 agent 任务只需后台执行、不向渠道输出,添加 --silent;执行、会话历史、追踪和可选收件箱记录仍会继续
  7. 迁入任务的 requires_review 未清除时,不得运行或恢复;必须先在 Console 中完成人工复核和批准

硬规则

必须显式指定 --agent-id

所有 qwenpaw cron 命令都必须传:

bash
--agent-id <your_agent_id>

你的 agent_id 在系统提示中的 Agent Identity 部分(Your agent id is ...)。 不得省略,否则任务可能错误创建到 default agent 的 workspace。


常用命令

bash
# 列出任务
qwenpaw cron list --agent-id <agent_id>

# 查看任务详情
qwenpaw cron get <job_id> --agent-id <agent_id>

# 查看任务状态
qwenpaw cron state <job_id> --agent-id <agent_id>

# 创建任务
qwenpaw cron create --agent-id <agent_id> ...

# 删除任务
qwenpaw cron delete <job_id> --agent-id <agent_id>

# 暂停 / 恢复任务
qwenpaw cron pause <job_id> --agent-id <agent_id>
qwenpaw cron resume <job_id> --agent-id <agent_id>

# 立即执行一次已有任务
qwenpaw cron run <job_id> --agent-id <agent_id>

# 更新已有任务
qwenpaw cron update <job_id> --agent-id <agent_id> ...

创建任务

支持两种类型:

  • text:定时发送固定消息
  • agent:定时向 agent 提问,并把回复发送到目标 channel

支持两种调度形态:

  • cron(--schedule-type cron):经典 cron 周期(如每天 9 点、每 2 小时),与循环任务相对应
  • scheduled(--schedule-type scheduled):日程任务(从 --run-at 开始,可一次性或按天重复)
调度选择规则(必须遵守)
  • 用户表达“每小时/每天/每周”且不强调具体起始日时,优先用 cron
  • 用户表达“明天/下周一/从某天开始/未来两周/有明确截止时间”时,优先用 scheduled
  • scheduled 不重复时(即一次性任务):只传 --run-at,不要传 --repeat-*
  • scheduled 重复时:传 --repeat-every-days,并根据结束条件传:
    • 限定次数:--repeat-end-type count --repeat-count N
    • 限定结束时间:--repeat-end-type until --repeat-until <ISO8601>
    • 不设结束:--repeat-end-type never
超时设置

默认超时 120 秒(2 分钟)。对于较长的 agent 任务,应显式设置更大的超时时间,避免任务被提前取消:

bash
--timeout 600   # 10 分钟
--timeout 3600   # 1 小时

核心规则:

  1. 如果 agent 任务涉及联网搜索、代码执行或多步工具调用,建议设置 --timeout 600 或更高
  2. timeout 必须小于调度周期,避免前一次执行未完成时下一次已触发,导致任务重叠运行。例如:
    • 每 15 分钟执行:--timeout 不应超过 900 秒
    • 每 10 分钟执行:--timeout 建议不超过间隔的 80%(即 480 秒)
    • 每天执行:--timeout 可以设置较大,不需要特别限制
  3. 对于高频任务(间隔 ≤ 10 分钟),遵循 timeout ≤ 调度间隔的 80%;低频任务(每小时及以上)按实际需要设置即可
创建前最少要确认
  • --type
  • --name
  • --schedule-type
  • --cron(当 --schedule-type cron)
  • --run-at(当 --schedule-type scheduled)
  • --channel
  • --target-user
  • --target-session
  • --text
  • --agent-id
  • --timeout(对于 agent 类型任务,根据预期执行时间设置合适的超时)

如果缺少这些信息,应先向用户确认,再创建任务。

创建示例
bash
# 循环任务(对应 --schedule-type cron)
qwenpaw cron create \
  --agent-id <agent_id> \
  --type text \
  --schedule-type cron \
  --name "每日早安" \
  --cron "0 9 * * *" \
  --channel imessage \
  --target-user "CHANGEME" \
  --target-session "CHANGEME" \
  --text "早上好!"
bash
# 循环任务(对应 --schedule-type cron)
qwenpaw cron create \
  --agent-id <agent_id> \
  --type agent \
  --schedule-type cron \
  --name "检查待办" \
  --cron "0 */2 * * *" \
  --channel dingtalk \
  --target-user "CHANGEME" \
  --target-session "CHANGEME" \
  --text "我有什么待办事项?" \
  --timeout 600

如果是后台 agent 任务,可在上面的命令中添加 --silent。text 任务不能使用该参数。

bash
# 日程一次性:明天 9 点提醒(不重复)
qwenpaw cron create \
  --agent-id <agent_id> \
  --type text \
  --schedule-type scheduled \
  --name "明早提醒" \
  --run-at "2026-05-13T09:00:00+08:00" \
  --channel dingtalk \
  --target-user "CHANGEME" \
  --target-session "CHANGEME" \
  --text "9 点开组会" \
  --save-result-to-inbox
bash
# 日程重复:未来两周每天 9 点(共 14 次)
qwenpaw cron create \
  --agent-id <agent_id> \
  --type text \
  --schedule-type scheduled \
  --name "未来两周组会提醒" \
  --run-at "2026-05-13T09:00:00+08:00" \
  --repeat-every-days 1 \
  --repeat-end-type count \
  --repeat-count 14 \
  --channel dingtalk \
  --target-user "CHANGEME" \
  --target-session "CHANGEME" \
  --text "9 点开组会" \
  --save-result-to-inbox
从 JSON 创建
bash
qwenpaw cron create --agent-id <agent_id> -f job_spec.json

最小工作流

1. 判断是否真的是"未来定时"或"周期执行"
2. 确认执行时间/周期
3. 确认 channel、target-user、target-session
4. 显式带上 --agent-id
5. qwenpaw cron create 创建任务
6. 后续用 list / state / pause / resume / delete 管理
迁入任务的复核流程

通过 PawPort 导入的定时任务默认禁用,并带有不可绕过的审核门。

请在 Console 的定时任务页面中检查并批准迁入任务。批准只记录审核结果,任务仍保持禁用;仅在用户明确要求时,再在该页面中单独启用。


Cron 表达式示例

0 9 * * *      每天 9:00
0 */2 * * *    每 2 小时
30 8 * * 1-5   工作日 8:30
0 0 * * 0      每周日零点
*/15 * * * *   每 15 分钟

常见错误

错误 1:把一次性立即执行当成 cron

如果只是现在执行一次,通常不要创建 cron。

错误 2:没传 --agent-id

这会导致任务落到错误的 agent / workspace。所有 cron 命令都必须显式传 --agent-id。

错误 3:信息没补全就创建

如果用户没说明时间、周期、目标 channel 或目标 session,应先追问。

错误 4:操作已有任务前不先查

暂停、恢复、删除前,先用:

bash
qwenpaw cron list --agent-id <agent_id>

找到正确的 job_id。


使用建议

  • 缺少参数时,先问用户再创建
  • 修改/暂停/删除前,先 qwenpaw cron list --agent-id <agent_id>
  • 排查问题时,用 qwenpaw cron state <job_id> --agent-id <agent_id>
  • 给用户展示命令时,提供完整、可直接复制的版本
  • 用户提到“结果进收件箱/不进收件箱”时,显式加 --save-result-to-inbox 或 --no-save-result-to-inbox,否则不要添加该项。
  • 用户要求后台或静默执行且不向渠道回复时,对 agent 任务添加 --silent。

帮助信息

bash
qwenpaw cron -h
qwenpaw cron list -h
qwenpaw cron create -h
qwenpaw cron get -h
qwenpaw cron state -h
qwenpaw cron pause -h
qwenpaw cron resume -h
qwenpaw cron delete -h
qwenpaw cron run -h

© agentscope-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in src/qwenpaw/agents/skills/cron-zh of agentscope-ai/QwenPaw.

Open the folder on GitHubat commit d7a0f50

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in agentscope-ai/QwenPaw, which our catalogue first saw on October 7, 2026.

Compare with similar skills

QwenPaw Scheduled Tasks next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

QwenPaw Scheduled Tasks compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
QwenPaw Scheduled Tasks this skillagentscope-ai/QwenPaw36k—~1.4kAutomated safety check: PassApache-2.0
ScheduleTinyAGI/tinyagi3.6k—~1.4kAutomated safety check: PassMIT
OpenObserve PR Briefopenobserve/openobserve22k—~1.8kAutomated safety check: PassAGPL-3.0
Send User MessageTinyAGI/tinyagi3.6k—~829Automated safety check: PassMIT
Vexa Scheduler RoutinesVexa-ai/vexa2.9k—~901Automated safety check: PassApache-2.0
OpenClaw to NanoClaw Migrationnanocoai/nanoclaw31k—~6kAutomated safety check: NotesMIT

Similar skills

  • Schedule

    TinyAGI/tinyagi

    Create, list, and delete scheduled tasks (recurring or one-time) that send messages to agents.

    3.6k GitHub stars~1.4k tokensUpdated 6 mo ago
    Productivity & AutomationAuto-check passed
  • OpenObserve PR Brief

    openobserve/openobserve

    Produces a read-only morning brief of your open pull requests across the openobserve GitHub org, with a next step for each and a reminder for idle ones.

    22k GitHub stars~1.8k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Send User Message

    TinyAGI/tinyagi

    Send a proactive message to a paired user via their channel (Discord, Telegram, or WhatsApp).

    3.6k GitHub stars~829 tokensUpdated 6 mo ago
    Productivity & AutomationAuto-check passed
  • Writes durable recurring or future-dated jobs for a Vexa workspace as routine files, replacing OS cron, timers and session-only reminders.

    2.9k GitHub stars~901 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Guides a conversational migration from an OpenClaw install to NanoClaw v2, carrying over identity, channel credentials, scheduled tasks and workspace files.

    31k GitHub stars~6k tokensUpdated 3 days ago
    Productivity & AutomationAuto-check: notes
  • Cron Ops

    czl9707/build-your-own-openclaw

    Create, list, and delete scheduled cron jobs. An agent skill from czl9707/build-your-own-openclaw.

    1.9k GitHub stars~593 tokensUpdated 3 mo ago
    Productivity & AutomationAuto-check passed

More from agentscope-ai/QwenPaw

All 20 skills in this repo
  • Terraform and OpenTofu Guide

    agentscope-ai/QwenPaw

    Guidance for writing and testing Terraform and OpenTofu code: module structure, naming, test approaches, CI/CD workflows, state handling and security scanning.

    36k GitHub starsUsed in 6 repos~4.2k tokens
    Auto-check passed
  • Make Skill

    agentscope-ai/QwenPaw

    Turns reusable decisions, templates or workflows from the current conversation into a new workspace skill through plan, approval, draft, validation and publication.

    36k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • QwenPaw Make Skill

    agentscope-ai/QwenPaw

    Creates a focused workspace skill from the current conversation in QwenPaw, moving through a planning, approval, drafting, validation and publishing script pipeline.

    36k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • QwenPaw Scheduled Tasks

    agentscope-ai/QwenPaw

    Creates and manages scheduled or recurring jobs with the qwenpaw cron commands, always tied to an explicit agent ID and a confirmed target channel.

    36k GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • DOCX Creation and Editing

    agentscope-ai/QwenPaw

    Creates, reads and edits Word .docx files, including tracked changes and comments, using docx-js for new files and XML editing for existing ones.

    36k GitHub stars~3.3k tokensUpdated today
    Auto-check passed
  • Mailbox Operations Hub

    agentscope-ai/QwenPaw

    Connects, registers, and operates a personal mailbox, reading, searching, sending, and organizing, through a managed mail server for nine domains.

    36k GitHub stars~2.6k tokensUpdated today
    Auto-check passed

Questions about QwenPaw Scheduled Tasks

What does QwenPaw Scheduled Tasks do?

Chinese-language guide to creating and managing scheduled or recurring tasks with the qwenpaw cron commands, always with an explicit agent id. Use only when something must run at a future time or repeatedly; a one-off action now, a normal reply, an unspecified time or an unclear target channel are not reasons to create a cron job. The qwenpaw cron commands cover list, create, get, state, update, pause, resume, delete and run, and every command must pass --agent-id explicitly, since leaning on the default agent can send tasks to the default workspace.

When should I use QwenPaw Scheduled Tasks?

QwenPaw Scheduled Tasks fits situations like: setting a daily or weekly reminder through an agent; scheduling a one-time task for a specific future time; pausing, resuming or deleting an existing scheduled task; running a recurring check that reports to a chat channel.

How do I install QwenPaw Scheduled Tasks in Claude Code?

Run `npx skills add agentscope-ai/QwenPaw --skill cron -a claude-code`. Or copy the skill folder (src/qwenpaw/agents/skills/cron-zh in agentscope-ai/QwenPaw) into .claude/skills/cron in your project. Claude Code loads it when a task matches its description.

How do I install QwenPaw Scheduled Tasks in Codex?

Run `npx skills add agentscope-ai/QwenPaw --skill cron -a codex`. Or copy the skill folder (src/qwenpaw/agents/skills/cron-zh in agentscope-ai/QwenPaw) into .agents/skills/cron in your project. Codex loads it when a task matches its description.

Can I use QwenPaw Scheduled Tasks in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agentscope-ai/QwenPaw --skill cron -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cron, .gemini/skills/cron, .github/skills/cron and .opencode/skills/cron in your project.

What does QwenPaw Scheduled Tasks need to run?

SKILL.md names no scripts, command-line tools or credentials: QwenPaw Scheduled Tasks is instructions for the agent only. Our summary lists: The qwenpaw CLI; Your agent id, shown in the system prompt.

Does QwenPaw Scheduled Tasks access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is QwenPaw Scheduled Tasks safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does QwenPaw Scheduled Tasks use?

QwenPaw Scheduled Tasks is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does QwenPaw Scheduled Tasks use?

About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to QwenPaw Scheduled Tasks?

Skills that share tags, products or a category with QwenPaw Scheduled Tasks: Schedule (TinyAGI/tinyagi, 3.6k stars), OpenObserve PR Brief (openobserve/openobserve, 22k stars), Send User Message (TinyAGI/tinyagi, 3.6k stars) and Vexa Scheduler Routines (Vexa-ai/vexa, 2.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains QwenPaw Scheduled Tasks?

agentscope-ai (a GitHub organization) maintains it in agentscope-ai/QwenPaw, which has 35,521 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 9, 2026.

Source: agentscope-ai/QwenPaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.