SenseNova-Skills  by OpenSenseNova

Agent skills enabling end-to-end office productivity and deep research

Created 1 month ago
2,401 stars

Top 18.6% on SourcePulse

GitHubView on GitHub
Project Summary

Summary

This repository provides a suite of "skills" designed to extend agent runtimes like OpenClaw and hermes-agent with concrete, end-to-end office automation capabilities. Targeting engineers, researchers, and power users, these skills enable complex tasks such as image generation, slide deck creation, data analysis, and deep research, offering significant benefits through standalone use or composition into sophisticated workflows. The project also offers Raccoon, a bundled solution for a zero-setup, enterprise-grade experience.

How It Works

The SenseNova-Skills architecture organizes each capability into a distinct directory, defining its triggers, functionalities, and execution flow via a SKILL.md file, adhering to the Agent Skills convention. It leverages the SenseNova model family, including SenseNova 6.7 Flash and the U1 model for infographic generation. Skills can be chained together to form end-to-end processes, such as transforming raw data into a comprehensive research report and then into a presentation. The system integrates with agent runtimes and offers a local Agent OS for enhanced privacy and personalization.

Quick Start & Requirements

  • Primary install / run command: Recommended installation involves instructing an agent runtime (e.g., OpenClaw, hermes-agent) to clone the repository URL (https://github.com/OpenSenseNova/SenseNova-Skills). Manual installation requires git clone followed by copying skill subdirectories to the agent's skills directory (e.g., ~/.openclaw/skills/).
  • Non-default prerequisites and dependencies: Requires an Agent Skills-compatible runtime (OpenClaw or hermes-agent), SenseNova Platform API access (free token plan available), and potentially specific Python versions/packages per skill category. Node runtime is needed for PPT skills. API keys are necessary for SenseNova and some external services.
  • Links: Full walkthrough in INSTALL.md; detailed guides for image generation (docs/sn-image-generate_en.md), PPT generation (docs/sn-ppt-generate.md), data analysis (docs/sn-data-analysis.md), and deep research (docs/sn-deep-research.md). Raccoon trial available at xiaohuanxiong.com.

Highlighted Details

  • Comprehensive Skill Suite: Covers image generation & visualization, slide-deck (PPT) generation, Excel data analysis, and deep research.
  • Infographic Generation: A novel capability built on the SenseNova U1 model, designed to condense complex data and insights into digestible, structured visual infographics.
  • Raccoon Integration: Offers a bundled, enterprise-grade solution with zero-setup, providing immediate access to SenseNova models and the Cowork-Skill suite.
  • Proven Scalability: The underlying SenseNova technology has been adopted by over 15 million individual users and thousands of enterprise customers.
  • End-to-End Workflow Example: Demonstrates a full pipeline from data analysis to deep research and finally PPT generation, showcasing integrated capabilities.

Maintenance & Community

The project encourages community contribution by offering skills as templates for users' own OpenClaw skills. Users are invited to join a community chat (QR code mentioned in README) for feedback, support, and updates.

Licensing & Compatibility

  • License type: MIT License.
  • Compatibility notes: The MIT license is permissive and generally compatible with commercial use and linking within closed-source projects.

Limitations & Caveats

Some social media search skills may require cookie authentication for access. While Raccoon provides a zero-setup experience, manual installation and configuration of specific dependencies (Python packages, Node runtime) may be necessary for individual skills. API keys are required for core SenseNova functionalities.

Health Check
Last Commit

1 day ago

Responsiveness

Inactive

Pull Requests (30d)
21
Issues (30d)
6
Star History
2,423 stars in the last 30 days

Explore Similar Projects

Feedback? Help us improve.