Who it is forA developer or analyst who already works in a coding agent and wants it to produce real Office files from a prompt.
The problemCoding agents can write text, but producing a finished .pptx or .xlsx file that opens cleanly in Office usually takes manual work.
The outcomeThe agent creates, converts or edits real Office files on your machine and returns them for review, without opening a window.
What you need first
- A computer running macOS, Windows or Linux, with the GenOffice app downloaded from the releases page
- Either a Genspark sign-in or an API key from a supported provider such as Claude, OpenAI or Gemini, or a local OpenAI-compatible server
- For the agent use cases: Claude Code, Codex, Cursor, Gemini CLI or another supported coding agent installed on the same computer
Steps
- Run
npx skills add genspark-ai/genofficeto install the skill, or open GenOffice Settings → Integrations and install it into the agents it finds. - Start your coding agent in a project folder where the output should go.
- Ask the agent for a specific file, for example a short eight-slide deck on a topic you choose.
- Let the agent use
genofficecommands to check and assemble the file, then review the rendered output it returns. - Open the saved .pptx or .xlsx in Office or GenOffice and check the content and layout.
Prompt for your agent
Install the genoffice skill from the genspark-ai/genoffice repo, then build an eight-slide deck about <topic> in <output folder> as a .pptx file. Expected output: one .pptx file and a rendered preview of each slide. Verify that the deck opens and that no slide text overflows or overlaps.
Caveat. Image generation and any other AI-backed steps send content to the AI provider you configured, so check that provider before running the agent on private material.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page