Robin

I help you make money with AI l AI Tech Tools | Robotics Engineering | AI Videos | Sharing Insights of AI l ✉️ [email protected]

[Robin @heyrobinx]

🚨 This feels unfair. 🚨

Claude can do the Excel work that used to take analysts hours.

Here are 8 prompts that make it happen 👇🧵

[Robin @heyrobinx]

@heyemilyx Agent Skills plus powerful image models creates a strong foundation for automated design workflows.

[Robin @heyrobinx]

@atulkumarzz #1 on the open-weight leaderboard shows how quickly open creative models are advancing.

[Robin @heyrobinx]

@andersyab The combination of UI design and editable outputs makes this ecosystem especially interesting.

[Robin @heyrobinx]

@Alifkhanzxx This is exactly how open models can push creative tooling forward.

[Robin @heyrobinx]

This release quietly packs a lot into 6B parameters.

UI generation.
Layer separation.
Transparent assets.
Visual coding.
Browser validation.
Image-to-editable-PPT.

And the models are open source.

The bigger story isn't better AI images. It's AI producing design outputs that can actually enter a real workflow.

[Robin @heyrobinx]

This release quietly packs a lot into 6B parameters.

UI generation.
Layer separation.
Transparent assets.
Visual coding.
Browser validation.
Image-to-editable-PPT.

And the models are open source.

The bigger story isn't better AI images. It's AI producing design outputs that can actually enter a real workflow.

[Ant Ling @AntLingAGI]

We’re open-sourcing the Ming-Image-0.1-Design family:
• Ming-Image-0.1-Design, 6B
• Ming-Image-0.1-Design-Layer, 6B
• Two open-source Agent Skills: the Ling UI Design Skill and the Image-to-Editable-PPT Skill

Ming-Image-0.1-Design ranks #1 among open-weight models on Artificial Analysis’s UI/UX Design leaderboard. 🧵

[Ant Ling @AntLingAGI]

We’re open-sourcing the Ming-Image-0.1-Design family:
• Ming-Image-0.1-Design, 6B
• Ming-Image-0.1-Design-Layer, 6B
• Two open-source Agent Skills: the Ling UI Design Skill and the Image-to-Editable-PPT Skill

Ming-Image-0.1-Design ranks #1 among open-weight models on Artificial Analysis’s UI/UX Design leaderboard. 🧵

[Robin @heyrobinx]

@univerHQ A runtime that spans a spreadsheet and a deck could be useful for workflows that cross both.

[Univer @univerHQ]

We made it to the Top 3 on GitHub Trending.

Univer is the open-source Office Harness for AI Agents—spreadsheets, docs, slides, canvas, relational tables, and PDFs in one runtime.

Thank you to everyone who starred, shared, and contributed.

Try it and tell us what we should build next:https://t.co/mB1aJorYG8

[Robin @heyrobinx]

@LeonUniver The gratitude toward people who simply tried the project is a good open-source instinct.

[Leon LY @LeonUniver]

Univer is now Top 3 on GitHub Trending.🚀

We’ve spent years building an open-source Office runtime where AI agents can work with spreadsheets, docs, slides, canvas, tables, and PDFs—not just generate text around them.

Seeing the developer community respond like this means a lot.

Thank you to everyone who starred, shared, contributed, or simply gave Univer a try.

We’re just getting started.

https://t.co/jfFpUZp3NV

[Robin @heyrobinx]

@atulkumarzz A canvas gives creators control, direction, and freedom beyond simple prompt generation.

[Robin @heyrobinx]

@LeonUniver Most teams have the calculation in one place and the rationale in another; connecting them is a meaningful shift.

[Leon LY @LeonUniver]

Thanks for sharing this, Robert.

A lot of a company’s thinking lives in spreadsheets, documents, and slides. The assumptions behind a deal, the calculations, the recommendation, the presentation to the board. They belong to the same decision, but we usually manage them as separate files. Someone has to keep the numbers and the story in sync.

That’s why I think Univer Workspace can become a System of Decision. Bring those pieces together around a decision, and keep the connections from source data through analysis to the final presentation.

Spreadsheets are central to this. A cell gives you a precise place to reference, and formulas let business experts express their own logic. People can see an assumption, change it, follow the calculation, and question the result. There’s something reassuring about being able to open a sheet and see how a number was arrived at. For many business users, that’s much more approachable than logic living somewhere behind an application.

We see the spreadsheet as the working model for a decision, with connections to the company’s underlying data. Univer’s shared runtime lets documents, slides, and the decision app work with that same model. Formulas connect them back to the cells, so the relationships can stay intact as assumptions change.

Agents can help build and update all of this. People can inspect the model and review the changes before accepting them.

That’s the direction we’re working toward: keeping the reasoning behind a decision connected, visible, and open to revision.

[Zoya Zen @heyzoyax]

STOP TELLING CHATGPT “WRITE ME AN EMAIL”

BAD REQUEST = BAD RESULT.

USE THESE COMMANDS INSTEAD AND WATCH THE MAGIC HAPPEN:

[Robin @heyrobinx]

@atulkumarzz Turning raw ideas into complete business cases in one workflow is powerful.

[Robin @heyrobinx]

@atulkumarzz Precise action sequencing could completely change how creators approach cinematic storytelling.

[Atul Kumar @atulkumarzz]

I used Pippit's 3D Director Studio to build a cinematic battlefield sequence, with every step already decided before anything got generated.

→ she throws a grenade, ducks as it detonates
→ throws a second grenade, another blast further out
→ rises and advances with her rifle raised
→ grabs more ammo from a nearby crate
→ throws a third grenade, one final blast in the distance

five separate actions, all picked from the Action Library and stacked on the timeline in exact order, and Seedance 2.5 generated the sequence beat for beat.

you're not hoping the model gets five moving parts right anymore. You're the one directing all of them

Try 3D Director Studio on Pippit @pippitofficial → https://t.co/NrE2BSGI9q

#3DDirectorStudio #PippitAI #Seedance25 #PippitPartner

[Robin @heyrobinx]

@LeonUniver The four usage paths matter. Different teams will want a CLI, an embedded plugin, or a workspace rather than one prescribed agent surface.

[Leon LY @LeonUniver]

Today we’re shipping Univer Office Harness — our approach to making Office work native to AI agents.

Agents can reason. But hand one a spreadsheet, a doc, and a deck, and too much of the job is still parsing formats, moving data between files, and rebuilding context.

Univer is an open-source Office engine with 30k+ GitHub stars across Univer and Luckysheet, bringing spreadsheets, docs, slides, canvases, and relational tables into one runtime.

Office Harness adds what agentic work needs on top: connected data, validation, isolated worktrees, and human review.

The Univer Office SDK is the foundation. CLI, plugins, and Workspace are experiences built on top of it.

Below: what it does, four ways to use it today, and how it performs on our benchmark 🧵