dsh-cron-job
Run the following command in DeepSeek Harness:
dsh plugin install upJiang/dsh-cron-job
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install upJiang/dsh-cron-job in your terminal, then restart DSH and refresh your browser to start using it; the source code is at https://github.com/upJiang/dsh-cron-job
About this plugin
The hardest part of a scheduled job is rarely whether it runs — it is whether anyone sees the result once it does. dsh-cron-job closes that gap: it lets your DeepSeek Harness model execute a scheduled task and pushes the output straight into the messaging tools you already open every day — WeChat, Feishu, DingTalk, WeCom, QQ, Slack, Telegram, Discord, or WhatsApp.
Describe what you want in plain language and the plugin drafts a complete task covering schedule, timezone, prompt, tool permissions, and delivery targets. Before anything is committed it live-tests the workspace, model, agent, data sources, and every notification channel; if any single check fails the task is never created. After activation you can search, pause, resume, trigger on demand, or review run history from one screen, with each execution isolated in its own session so jobs never block each other.
It is built for developers and technical operators who already use DSH models for data collection, monitoring, or report generation and want the output delivered to their daily IM clients. If you came from the older dsh-im plugin, your existing channel configs and credential references are carried over automatically, making the upgrade low-friction.
Use Cases
- Daily digest of Product Hunt and GitHub Trending delivered to a Feishu group
- Weekly monitoring reports automatically sent to a Slack channel
- Scheduled service health checks with alerts pushed to DingTalk or WeChat
Best For
- Developers leveraging DSH models for data collection and report generation
- Ops engineers who need automated results synced to team IM channels
- Tech leads who want to build scheduled tasks with natural language prompts
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.