SenseNova-Skills
SenseNova office skills: infographics, slide decks, Excel analysis and deep research for Agent Skills runtimes
- 5,970 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Runs Python scripts and calls external APIs
- Sends document contents to cloud models
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/sensenova-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Runs Python scripts and calls external APIs
- Sends document contents to cloud models
This is third-party code. Review the repository files before installing.
What it does
The repository holds Agent Skills-format skills in tiers: base tools for image generation, editing and recognition, and scenario skills on top. Scenarios generate infographics with layout and style selection and vision model review, build slide decks in fast, standard and creative modes with PPTX export, and analyse large Excel tables with Parquet conversion. There is also a deep research orchestrator with report writing and citation rendering, plus team collaboration skills.
Who it is for. For people building an office AI assistant on OpenClaw or hermes-agent who are willing to use SenseNova models.
Good fit when
- You need an infographic or deck from a report
- You need to analyse a large Excel file and export results
- You need a research report with sources
Not a fit when
- You cannot get a SenseNova API key
- You work in Claude Code or Cursor and do not want to adapt the skills
Example request
Make a vertical infographic from this quarterly reportLimitations
The skills target OpenClaw and hermes-agent with SenseNova models via an OpenAI-compatible API, so you need a platform key for the international or mainland China region. Some scenarios require Python dependencies, Node.js and third-party keys such as image search. Access from Russia without VPN is unverified. The README promotes the commercial Raccoon product.
How to disable. Remove the sn-* folders from ~/.openclaw/skills/ or ~/.hermes/skills/ and restart the agent.
FAQ
Can I use another model instead of SenseNova?
The README recommends SenseNova and the image base tools call its API, so switching needs rework.
How do I check the environment?
The sn-image-doctor and sn-ppt-doctor skills check dependencies and fill missing variables into .env.
Discussion
No questions or reviews yet.
Related
SkillsA set of three research skills: paper writing, academic Word and PowerPoint documents, scientific computing and figures
A set of Codex skills for research work: image to editable Office shapes and VBA, and paper to a PPTX deck
A set of 14 skills that teach the agent to build diagrams and visualizations right inside Markdown: UML, cloud and network schemes, charts, maps and cards
Anthropic skills
Skills
Anthropic's official skill examples: docx, pdf, pptx and xlsx documents, design, MCP builder and the Agent Skills spec
A skill set for research work in the style of Nature journals: finding and reading papers, writing, statistics, figures, reviewer responses
Three skills for academic writing: a paper schema for image generation, rewriting text to sound less machine-made, and drafting from scratch
README in short
The README recommends running the skills in OpenClaw or hermes-agent with the SenseNova API and points to a detailed INSTALL.md. You can let the agent install them or copy folders from skills manually. The skills are then listed by section: images, slide decks, data analysis, deep research, HTML and teamwork, each with its own guide.
README badge
Original SKILL.md
--- name: sn-infographic description: | Generates professional infographics with various layout types and visual styles. Analyzes content, recommends layout and style, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", or "可视化". metadata: project: SenseNova-Skills tier: 1 category: scene priority: 9 user_visible: true triggers: - "infographic" - "information graphic" - "infographics generation" - "visual summary" - "data visualization" - "visual explanation" - "diagram" --- # sn-infographic Info graphic generation scene skill (tier 1), relying on the `sn-image-generate`, `sn-image-recognize`, and `sn-text-optimize` tools provided by `sn-image-base` (tier 0). Features: - Evaluation of prompt quality (auto mode) - Prompt expansion (force/auto mode) - Multiple rounds of image generation and VLM review - Output the best result based on quality ranking