Cursor introduces /automate skill for automating repetitive tasks
TL;DR
Cursor's new /automate skill creates automations from plain language. Workflows trigger via Slack emojis or GitHub events while cloud agents access virtual computers.
What changed
Cursor introduced the /automate skill so Vibe Builders and Developers can describe automations in plain language. Basic Users gain triggers through Slack emojis or GitHub events while cloud agents run on their own virtual computers.
Why it matters
Basic Users complete routine Slack tasks faster when emojis start workflows without extra steps. Developers link GitHub events directly into projects for consistent automation compared to manual checks in VS Code.
What to watch for
Test the skill against manual scripting in VS Code and verify by creating one emoji trigger in a Slack channel to confirm the workflow executes.
Who this matters for
- Vibe Builders: Use the /automate skill to build complex workflows by describing the logic in plain language.
Harsh’s take
Cursor is moving beyond code completion into full agentic orchestration. The /automate skill effectively turns the editor into a control center for external services. By allowing cloud agents to operate on their own virtual machines, Cursor solves the local environment bottleneck that usually kills complex agentic workflows.
This update signals a shift where the IDE is no longer just for writing text, it is for managing state across Slack and GitHub. Operators should stop thinking about manual scripts and start treating their editor as a deployment hub. If you are still manually checking GitHub PRs or Slack for task updates, you are falling behind the current speed of development.
by Harsh Desai
About Cursor
View the full Cursor page →All Cursor updatesGo deeper
More AI news
- Daily RoundupVercel-Origin beta and GPT-5.6 Sol discount, plus agent tools for builders
Vercel rolled out Origin repository deployments and a month-long GPT-5.6 Sol discount on AI Gateway while Product Hunt featured new agent layers and Hugging Face highlighted an uncensored Qwen model, with industry moves around data use and automation exits.
- Weekly DigestHermes Agent v0.20 voice and A2A protocol, OpenClaw mobile updates, and multi-agent tools to test now
Hermes Agent rolled out v0.20 releases with voice streaming, A2A interoperability, desktop artifacts, and self-recovery tools while OpenClaw added Android switching, iOS caching, and plugin provenance checks across the week.
- Daily Roundupbeenga-image-1 on Replicate, Qwen3.8-27B on HF, and the AI trust debate
Fresh image and text models appeared on Replicate and Hugging Face while industry voices highlighted trust as the core barrier to wider AI adoption.