Agent skill

QwenPaw Scheduled Tasks

by agentscope-ai in 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.

Apache-2.0Auto-check passedProductivity & Automation

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-en .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
~2.3k tokens
SKILL.md length
841 words
Files
1
Skills in repo
20
Repo updated
First seen
Licence
Apache-2.0

At a glance

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

  • Works in 7 steps: Only use cron for future scheduled or… → If it only needs to be done once… → Before creating, confirm execution… → …
  • Setting up a daily or weekly automatic message or report
  • SKILL.md covers When to Use, Decision Rules, Hard Rules and Common Commands, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Cron is for work that must happen later or repeatedly: daily, weekly or hourly jobs, reminders at a set time, and periodic checks or reports. It is not for something to do once right now, an ordinary reply, or a request with no schedule or an unclear target channel, user or session. The subcommands are list, create, get, state, update, pause, resume, delete and run.

Every command must include `--agent-id`, otherwise the job may land in the default agent's workspace; the ID comes from the agent identity section of the system prompt. Jobs are either text (a fixed message) or agent (a scheduled question whose reply goes to the target channel), with `--silent` for agent jobs that should run without channel output. Schedules use `--schedule-type cron` for classic recurrence or `scheduled` with `--run-at` for calendar-style runs, and imported jobs flagged `requires_review` must be approved in the Console first.

When your agent uses it

  • Setting up a daily or weekly automatic message or report
  • Scheduling a reminder for a specific future time
  • Pausing, resuming or deleting an existing scheduled job

Example prompts

  • “Send the team a standup reminder every weekday at 9 AM in the ops channel.”
  • “Pause the weekly report job until next Monday.”
  • “List my scheduled jobs and show the state of the nightly backup check.”

Requirements

  • The `qwenpaw` CLI
  • The agent ID of the agent that owns the job

Workflow steps

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

  1. Only use cron for future scheduled or periodic execution
  2. If it only needs to be done once immediately, do not create a cron job
  3. Before creating, confirm execution time/schedule, target channel, target-user, and target-session
  4. All cron commands must explicitly include --agent-id
  5. Do not rely on the default agent, or the task may end up in the default workspace
  6. For an agent task that should run without channel output, add --silent; execution, session history, trace, and optional Inbox recording…
  7. Never run or resume an imported job while requires_review is set; review and approve it in Console first

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 2.3k tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 841 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~45
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

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). 841 words, ~2,323 tokens.

Download SKILL.mdSave it as .claude/skills/cron/SKILL.md (or your agent's skills folder).
name
cron
description
Use this skill only for scheduled or recurring tasks. Manage jobs with qwenpaw cron list/create/get/state/update/pause/resume/delete/run, and always pass --agent-id explicitly.
metadata.builtin_skill_version
1.8

Cron (Scheduled Task Management)

When to Use

Use this skill only when you need to automatically execute something at a future time or repeat execution on a schedule.

Should Use
  • User asks to do something "daily / weekly / hourly"
  • User asks for automatic reminders or execution "tomorrow at 9 AM / next Monday / at a specific time"
  • Long-term periodic notifications, checks, or reports are needed
Should Not Use
  • The task only needs to be executed once right now
  • It is just a normal reply within the current session
  • The user has not specified an execution time or schedule
  • The target channel / user / session is still unclear

Decision Rules

  1. Only use cron for future scheduled or periodic execution
  2. If it only needs to be done once immediately, do not create a cron job
  3. Before creating, confirm execution time/schedule, target channel, target-user, and target-session
  4. All cron commands must explicitly include --agent-id
  5. Do not rely on the default agent, or the task may end up in the default workspace
  6. For an agent task that should run without channel output, add --silent; execution, session history, trace, and optional Inbox recording still continue
  7. Never run or resume an imported job while requires_review is set; review and approve it in Console first

Hard Rules

Must Explicitly Specify --agent-id

All qwenpaw cron commands must include:

bash
--agent-id <your_agent_id>

Your agent_id is found in the Agent Identity section of the system prompt (Your agent id is ...). Do not omit it, or the task may be incorrectly created in the default agent's workspace.


Common Commands

bash
# List tasks
qwenpaw cron list --agent-id <agent_id>

# View task details
qwenpaw cron get <job_id> --agent-id <agent_id>

# View task status
qwenpaw cron state <job_id> --agent-id <agent_id>

# Create a task
qwenpaw cron create --agent-id <agent_id> ...

# Delete a task
qwenpaw cron delete <job_id> --agent-id <agent_id>

# Pause / Resume a task
qwenpaw cron pause <job_id> --agent-id <agent_id>
qwenpaw cron resume <job_id> --agent-id <agent_id>

# Run an existing task once immediately
qwenpaw cron run <job_id> --agent-id <agent_id>

# Update an existing task
qwenpaw cron update <job_id> --agent-id <agent_id> ...

Creating Tasks

Two types are supported:

  • text: Send a fixed message on a schedule
  • agent: Ask an agent a question on a schedule and send the reply to the target channel

Two schedule modes are supported:

  • cron (--schedule-type cron): classic cron recurrence (for example, daily 09:00 or every 2 hours)
  • scheduled (--schedule-type scheduled): calendar-style schedule starting from --run-at, either one-time or repeating by day
Schedule Selection Rules (Must Follow)
  • If user intent is generic recurrence ("hourly/daily/weekly") without a specific start date, prefer cron
  • If user intent includes a concrete start date ("tomorrow", "next Monday", "starting from <date>", "for the next two weeks"), prefer scheduled
  • For one-time scheduled tasks: pass only --run-at and do not pass any --repeat-* options
  • For repeating scheduled tasks: pass --repeat-every-days and choose an end condition:
    • fixed count: --repeat-end-type count --repeat-count N
    • end datetime: --repeat-end-type until --repeat-until <ISO8601>
    • no end: --repeat-end-type never
Timeout Settings

Default timeout is 120 seconds (2 minutes). For longer agent tasks, you must explicitly set a larger timeout to prevent premature cancellation:

bash
--timeout 600   # 10 minutes
--timeout 3600   # 1 hour

Core Rules:

  1. If the agent task involves web search, code execution, or multi-step tool calls, set --timeout 600 or higher
  2. Timeout must be less than the scheduling interval to prevent overlap (a new run firing while the previous one is still executing). Examples:
    • Every 15 minutes: --timeout should not exceed 900 seconds
    • Every 10 minutes: --timeout recommend no more than 80% of interval (i.e. 480 seconds)
    • Daily: --timeout can be larger, no special restriction needed
  3. For frequent tasks (interval ≤ 10 minutes), follow timeout ≤ 80% of interval; for infrequent tasks (hourly or above), set based on actual needs
Show full SKILL.md (314 more words)Show less
Minimum Information Required Before Creating
  • --type
  • --name
  • --schedule-type
  • --cron (when --schedule-type cron)
  • --run-at (when --schedule-type scheduled)
  • --channel
  • --target-user
  • --target-session
  • --text
  • --agent-id
  • --timeout (for agent-type tasks, set an appropriate timeout based on expected execution time)

If any of this information is missing, confirm with the user before creating the task.

Creation Examples
bash
# Recurring task (--schedule-type cron)
qwenpaw cron create \
  --agent-id <agent_id> \
  --type text \
  --schedule-type cron \
  --name "Daily Greeting" \
  --cron "0 9 * * *" \
  --channel imessage \
  --target-user "CHANGEME" \
  --target-session "CHANGEME" \
  --text "Good morning!"
bash
# Recurring task (--schedule-type cron)
qwenpaw cron create \
  --agent-id <agent_id> \
  --type agent \
  --schedule-type cron \
  --name "Check Todos" \
  --cron "0 */2 * * *" \
  --channel dingtalk \
  --target-user "CHANGEME" \
  --target-session "CHANGEME" \
  --text "What are my pending tasks?" \
  --timeout 600

For a background agent task, add --silent to the command above. Do not use it for text tasks.

bash
# Scheduled one-time: remind at 9 AM tomorrow (no repeat)
qwenpaw cron create \
  --agent-id <agent_id> \
  --type text \
  --schedule-type scheduled \
  --name "Tomorrow Morning Reminder" \
  --run-at "2026-05-13T09:00:00+08:00" \
  --channel dingtalk \
  --target-user "CHANGEME" \
  --target-session "CHANGEME" \
  --text "Standup starts at 9:00." \
  --save-result-to-inbox
bash
# Scheduled repeating: next two weeks, every day at 9 AM (14 runs)
qwenpaw cron create \
  --agent-id <agent_id> \
  --type text \
  --schedule-type scheduled \
  --name "Two-week Standup Reminder" \
  --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 "Standup starts at 9:00." \
  --save-result-to-inbox
Create from JSON
bash
qwenpaw cron create --agent-id <agent_id> -f job_spec.json

Minimal Workflow

1. Determine whether this truly requires "future scheduling" or "periodic execution"
2. Confirm execution time/schedule
3. Confirm channel, target-user, target-session
4. Explicitly include --agent-id
5. Create the task with qwenpaw cron create
6. Manage tasks afterwards with list / state / pause / resume / delete
Reviewing Imported Jobs

Jobs imported by PawPort are disabled and protected by a non-bypassable review gate.

Review and approve imported jobs in the Console Cron Jobs page. Approval records the review but leaves the job disabled. Enable it there separately only if the user explicitly asks.


Cron Expression Examples

0 9 * * *      Every day at 9:00
0 */2 * * *    Every 2 hours
30 8 * * 1-5   Weekdays at 8:30
0 0 * * 0      Every Sunday at midnight
*/15 * * * *   Every 15 minutes

Common Mistakes

Mistake 1: Creating a cron job for a one-time immediate execution

If the task only needs to be done once right now, do not create a cron job.

Mistake 2: Not passing --agent-id

This causes the task to be assigned to the wrong agent / workspace. All cron commands must explicitly include --agent-id.

Mistake 3: Creating a task without complete information

If the user has not specified the time, schedule, target channel, or target session, ask for clarification first.

Mistake 4: Modifying existing tasks without checking first

Before pausing, resuming, or deleting, first run:

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

to find the correct job_id.


Usage Tips

  • When parameters are missing, ask the user before creating
  • Before modifying/pausing/deleting, run qwenpaw cron list --agent-id <agent_id> first
  • To troubleshoot issues, use qwenpaw cron state <job_id> --agent-id <agent_id>
  • When showing commands to the user, provide complete, copy-pasteable versions
  • If the user mentions "save to inbox" (or not), explicitly include --save-result-to-inbox or --no-save-result-to-inbox
  • If the user asks for background or silent execution with no channel reply, use --silent on an agent task
  • Before creating, you can run qwenpaw chats list --agent-id <agent_id> to get valid target-user and target-session

Help Information

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-en 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—~2.3kAutomated 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 2 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
  • 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
  • OMP Sub-Agent Role Presets

    agentscope-ai/QwenPaw

    Gives the allowed_tools and skills preset for each OMP sub-agent role, to apply when calling spawn_subagent.

    36k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

Questions about QwenPaw Scheduled Tasks

What does QwenPaw Scheduled Tasks do?

Creates and manages scheduled or recurring jobs with the qwenpaw cron commands, always tied to an explicit agent ID and a confirmed target channel. Cron is for work that must happen later or repeatedly: daily, weekly or hourly jobs, reminders at a set time, and periodic checks or reports. It is not for something to do once right now, an ordinary reply, or a request with no schedule or an unclear target channel, user or session.

When should I use QwenPaw Scheduled Tasks?

QwenPaw Scheduled Tasks fits situations like: setting up a daily or weekly automatic message or report; scheduling a reminder for a specific future time; pausing, resuming or deleting an existing scheduled job.

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-en 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-en 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; The agent ID of the agent that owns the job.

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 2.3k tokens (SKILL.md is roughly 9.3k 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.