Project overview
SenseNova-Skills is a repository of modular skills for AI office assistants. Each skill has its own directory and a SKILL.md file describing its triggers, capabilities, and execution flow, following the Agent Skills convention. The skills require a compatible agent runtime; the README recommends OpenClaw or hermes-agent and the SenseNova Platform API.
Use cases
The project suits tasks such as generating infographics, creating presentations, organizing and analyzing Excel data, conducting research, turning reports into web pages, coordinating teamwork, and tracking ongoing projects. Skills can run individually or work together—for example, analyzing quotation data, researching the reasons behind changes, and producing a presentation.
What it does and problems it solves
The project divides office tasks into composable skills that give AI assistants concrete processing workflows. Data analysis skills cover reading multiple worksheets, cleaning, filtering, cross-sheet aggregation, and Excel/CSV export. Presentation skills cover requirement collection, outlines, page creation, and PPTX export in certain modes. Research skills cover planning, search, report writing, and citation preparation. Other skills support image processing, web content creation, shared team workspaces, and project progress records.
These capabilities connect the stages from source materials to analysis, research, and deliverables. This listing includes only the repository link; runnable packages and core workflows have not been validated.
How to use
1. Open the original repository through the entry below this page and browse the README's Skills List. Choose a skill by category: image and visualization, presentations, data analysis, deep research, search, web content, team collaboration, or project tracking.
2. Open the selected skill's directory and read its SKILL.md to understand its purpose. Then read the category's full guide for configuration requirements, dependencies, and invocation examples. The README's skill list itself needs no installation; running a skill requires installing it and configuring a compatible runtime.
3. Follow the relevant guide to invoke the skill in an Agent Skills-compatible assistant. Prepare the materials needed for the task, such as Excel files, report text, or a presentation brief specifying the topic, audience, and page count. Follow each skill's guide for its exact input method.
4. For connected workflows, consult the examples/ directory. The README includes an example that combines quotation data analysis, deep research, and presentation generation. Consult docs/faq.md for setup or runtime questions.
Installation
1. Read INSTALL.md and the selected skill's category guide in the original repository first. Their contents were not included in the supplied material, so complete dependency versions, API configuration commands, and all skill-specific installation steps cannot be listed here.
2. Prepare an Agent Skills-compatible runtime. The README recommends OpenClaw or hermes-agent, but the supplied content does not explain how to install those tools themselves; consult their original repositories.
3. The README recommends asking your AI assistant to install the skills. Obtain the clone address from the original repository below this page, give it to the assistant, and ask it to clone the repository and place the skills in its skills directory. The target is `~/.openclaw/skills/` for OpenClaw or `~/.hermes/skills/` for hermes-agent.
4. For manual installation, obtain the repository using its original clone address, then copy the subdirectories under `SenseNova-Skills/skills/` into your assistant's skills directory. The README provides `mkdir -p ~/.openclaw/skills` to create the OpenClaw directory and `cp -r SenseNova-Skills/skills/* ~/.openclaw/skills/` to copy the skills. For hermes-agent, change the target directory to `~/.hermes/skills/`.
5. Follow INSTALL.md and the category guides to configure Python dependencies, API keys, and other requirements. For SenseNova API access, the documentation, key, base address, and model name must all belong to the same region. You may need to restart the agent service manually before it recognizes the installed skills.
Source and usage notes
- Original repository: https://github.com/OpenSenseNova/SenseNova-Skills
- Source revision: 7838651111ef2dc3ac0293f08008730f1a022694
This listing links to the upstream repository. It does not provide a verified download package, and the complete workflow has not been independently validated.
This description was organized and translated with AI from public upstream material. Refer to the original repository for capabilities, setup requirements, costs, and license terms. 
