SenseNova Skills

SenseNova Skills is a skills collection published by SenseNova (GitHub: OpenSenseNova). The README says the skills extend SenseNova models with "concrete, end-to-end office capabilities." The repo is grouped by office task: image and infographic generation, slide decks, Excel data analysis, deep research, academic and social search, HTML reports, team collaboration and long-running project tracking. Each skill lives in its own folder and follows the Agent Skills convention, so you can use one alone or chain several. One README example starts from a raw price-quote CSV, analyses the data, runs deep research on the findings and ends with a slide deck. The authors recommend running it in an agent such as OpenClaw or hermes-agent, with the SenseNova platform API as the model. What sets it apart is that one repo covers a whole office workflow, from data analysis and research to the finished deck.

Who it's for:Office workers and teams who regularly produce analysis reports, presentation decks and industry research. It's smoother for people comfortable setting up their own agent tools.

Before you start: You need an agent that supports Agent Skills (the README recommends OpenClaw or hermes-agent), then install and configure from INSTALL.md; each group of skills needs its own Python dependencies and API keys. The SenseNova API has separate international and mainland China regions, and the docs page, API key, base URL and model name must all come from the same region. The install examples include downloading a script with curl and piping it straight into bash. AI Inspiration World does not recommend installing that way: it runs a script from the internet without you seeing it first. Zhihu and Douyin search ask you to copy cookies from your browser by hand, and the docs say this part uses the platforms' internal interfaces. AI Inspiration World does not recommend it: it uses your login credentials to access those platforms. The proactive project-tracking skill keeps long-term records, and when you accept a suggestion it resumes the original session. The docs are in English and Chinese. The code is free under the MIT license; the model API may cost extra.

Based on the project's public documentation. Not tested by AI Inspiration World.