automation
Create, inspect, update, delete, and run Kun scheduled tasks or saved workflows.
64
Quality
75%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Securityby
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./resources/bundled-skills/automation/SKILL.mdKun Automation
Copyright (c) 2026 KunAgent. Licensed under the MIT License.
Purpose
Create, inspect, update, delete, and run Kun scheduled tasks or saved workflows.
Tool routing
| Tool or skill | Use |
|---|---|
mcp_gui_schedule_gui_schedule_list | List current schedules before a mutation. |
mcp_gui_schedule_gui_schedule_create | Create one-time, daily, or interval schedules. |
mcp_gui_schedule_gui_schedule_update | Update a schedule by returned task id. |
mcp_gui_schedule_gui_schedule_delete | Delete only the explicitly selected task. |
mcp_gui_schedule_list_workflows | Discover user-saved workflows. |
mcp_gui_schedule_run_workflow | Run a named saved workflow. |
task_graph | Model dependencies inside the current thread. |
Workflow
- Determine whether the user needs a schedule, a saved workflow, or an in-thread dependency graph.
- Read existing state before updating or deleting.
- For schedules, choose exactly one kind: at, daily, or interval.
- Preserve the conversation execution settings when available.
- Read back the resulting schedule or workflow output.
Completion gates
- Persistent create/update/delete actions require explicit user intent.
- Report the returned task id and effective timing.
- Never claim a scheduled run has executed before observing its result.
Boundaries
- Do not infer recurring intent from a one-time request.
- Do not bypass schedule APIs with OS cron or background shell processes.
Delivery
Lead with the outcome, name the evidence used for verification, and disclose any real limitation that remains.
- Repository
- KunAgent/Kun
- Commit
e67f656
- Last updated
- First committed
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.