Carbone Skill for AI - Teach your AI to build document templates
by•
Carbone is a universal document-generation engine: feed it a template file and JSON file, and it produces pixel-perfect documents at scale. The Carbone Skill teaches AI assistants like Claude or ChatGPT the entire Carbone templating language. Describe what you want in plain language and your AI writes correct Carbone syntax, builds templates in DOCX, XLSX, PPTX, HTML or PDF, and validates tags before you render automatically at scale.
Replies
Carbone
@steevep Congrats on the launch team. Very cool, can I upload brand CI etc and have it extract the details and apply to new docs?
Carbone
Bonjour @zolani_matebese 👋
The Skill itself teaches the AI the Carbone templating language rather than doing brand extraction directly, but in practice, yes, you can absolutely achieve this.
You can give the AI your brand details (colors, fonts, logo) as context, paste your guidelines, a hex palette, or even an existing PDF brand document, and ask it to build templates that match. It'll apply your styling to the generated DOCX/XLSX/PPTX/HTML templates. If you have a structured brand kit, the cleaner the input, the more consistent the output.
Happy to walk through an example if you'd like, I'm available for a demo!
great work! How does the validator catch a formatter that doesn't exist in Carbone? I am thinking if the AI invents a name that's syntactically clean but unknown, is the skill parsing against an actual grammar pre-render?
Carbone
Merci @artstavenka1! To answer your question: The Skill is a knowledge layer that grounds the AI in Carbone's complete documented formatter set, with a core rule: "never invent syntax, anything not documented doesn't exist." So a clean-looking but unknown formatter gets flagged against the real reference list instead of accepted. The actual grammar enforcement happens at render time in Carbone's engine; the Skill's job is to catch the invented ones before you get there.
Carbone
Hey Product Hunt! 👋
Carbone was born from a simple frustration: why do developers have to get involved every time a business needs to tweak a document? An invoice layout, a new field on a contract, a translated report — small changes that would eat up hours of dev time.
So we built Carbone around one idea: anyone should be able to design and own their document templates. No code required. Just open Word, Excel, or LibreOffice, drop in some tags, and the engine handles the rest. Business teams got their autonomy back. Developers got their afternoons back.
That was already a big step. But there was still a learning curve — the templating syntax, the JSON structure, the API calls. Nothing insurmountable, but still a door that not everyone would push open.
Today, that door is wide open.
With our new AI Skill, you don't need to know Carbone's syntax. You don't need to think about JSON. You just describe what you want — and the AI figures out the rest, feeds Carbone, and hands you back a polished document in seconds.
From "no code required" to "no friction at all". That's the journey we've been on since day one.
We can't wait to see what you build with it. 🚀🇫🇷
Carbone
I am very happy to see that AI-assisted template design is becoming a reality after two years of research and internal experimentation in a field where everything changes every two months!
The Skill seems to address the needs of many customers who want to keep their own AI while giving it additional capabilities.
We will closely monitor user feedback to determine whether we should also launch our own sovereign AI solution that can be installed On-Premise in the coming months. We have many things to unveil in this area this year!
Carbone has been great for no-code setups, but handling complex loops and formatters always required a bit of developer hand-holding. This completely changes things for growth ops teams. Excited to plug this into our Make workflows.. good work team
Document templates as a skill layer for AI is a powerful pattern — especially for structured financial documents where the same template logic needs to run across hundreds of variations.
I publish project finance and valuation model templates on Eloquens (eloquens.com/channel/samir-asadov-cfa) and the templates are Excel-heavy with formula interdependencies that go beyond text placeholders. The XLSX support in Carbone is what makes this interesting — does the AI understand Excel formula syntax and named ranges, or is it treating the .xlsx primarily as a tabular structure to fill rather than a live calculation engine?
Carbone
Thanks @samir_asadov ! you're asking exactly the right question.
Good news for your use case: Carbone keeps the XLSX as a real, working workbook. The formulas, the inter-dependencies, the named ranges you've built in Excel: they all stay intact. Carbone just drops the dynamic data into the cells your formulas point to, and everything recalculates normally when the file opens. So your model stays a model, and it's not getting flattened into static numbers.
The Skill's role is teaching the AI to place Carbone tags correctly within that structure, including inside formula contexts and across ranges without breaking the formula references.
If you'd like to stress-test it against one of your valuation models, happy to help you try it. I'm available for a live demo :)
Stripo.email
Love the practical approach here. Teaching AI the actual templating language, rather than relying on guesswork, feels much more reliable for production workflows.
Carbone
Merci @marianna_tymchuk!! That's exactly the thinking, without the Skill, AI tends to invent syntax, or borrow it from other templating libraries or programming language, so you get tags that look plausible but the syntax is not supported and rejected by Carbone. The Skill grounds it in Carbone's real documentation, plus production template examples, patterns and logic: so you get correct, elegant tags every time ✅.
Very interesting launch. How well does the Skill handle large multi-page reports with nested loops and conditional sections?
Carbone
Thanks @starkturtle ! Really well, actually. Nested loops and conditional sections are core Carbone features, and the Skill knows them in depth, including the tricky parts like keeping loop blocks from interleaving and pairing show/hide conditions correctly.
Multi-page reports work great across all the template formats, so you can pick whatever fits your case, DOCX, HTML, PPTX and the rest. Just describe the structure and the logic in plain language, and the AI builds the template with the right nested loops and conditionals in place.
Happy to help you try it on a real report if you want to put it to the test!
Mailwarm
Can it handle complex tables and conditional sections in DOCX without breaking formatting when data varies a lot?
Carbone
Bonjour @othman_katim 👋 to answer your question: that's exactly what Carbone is built for. The data can vary a lot from one render to the next and the DOCX formatting holds up, because your template stays a real Word document. Loops expand rows, conditional sections show or hide, and the styling you set stays intact.
The Skill helps you get there cleanly. It knows the patterns that keep formatting safe, like keeping loop blocks from interleaving, pairing show/hide conditions properly, and handling tables that grow with the data.
If you're interested, I'm available for a demo call :D
WeWeb.io
Nice, this is game changer for me, I'll test it right now! Can I give a file to re-create it in another format?
Carbone
Bonjour @alexy_carlier1 ! Glad to see you there!
And yes, exactly. Give the AI your existing file and ask it to recreate the template in another format. It rebuilds the structure and the Carbone tags in the target format (DOCX, XLSX, PPTX, HTML, and so on). Just keep in mind each format has its own strengths, so the layout may adapt a little to fit the new one.
Let me know how the test goes, curious to hear what you build! ;)