Modular SenseNova skills for building AI-powered office assistants and productivity workflows
# Add to your Claude Code skills
git clone https://github.com/OpenSenseNova/SenseNova-SkillsGuides for using ai agents skills like SenseNova-Skills.
Last scanned: 5/15/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-15T06:56:35.061Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": true
}See how SenseNova-Skills compares with popular alternatives.
SenseNova-Skills is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by OpenSenseNova. Modular SenseNova skills for building AI-powered office assistants and productivity workflows. It has 5,710 GitHub stars.
Yes. SenseNova-Skills passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/OpenSenseNova/SenseNova-Skills" and add it to your Claude Code skills directory (see the Installation section above).
SenseNova-Skills is primarily written in JavaScript. It is open-source under OpenSenseNova on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh SenseNova-Skills against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
See comparison
English | 简体中文
The SenseNova model family plugs directly into agent runtimes such as OpenClaw and hermes-agent, with the skills in this repository extending the models with concrete, end-to-end office capabilities.
In this repository each skill lives in its own directory and declares triggers, capabilities, and execution flow through a SKILL.md file, following the Agent Skills convention.
The skills cover image generation & visualization, slide-deck (PPT) generation, Excel data analysis, deep research, HTML experiences, team collaboration, and proactive project tracking — usable standalone or composed into end-to-end workflows.
🎨 Want to see what it can do? Check out our sn-infographic Gallery to explore nearly 100 stunning generation cases and steal their prompt designs !
The latest SenseNova models and the full Cowork-Skill suite in this repo are bundled into Raccoon, with enterprise-grade security and a zero-setup experience — if you'd rather not provision env, API keys, and runtimes yourself, you can use these capabilities directly through Raccoon. Free trial available — no payment required to get started.
Raccoon now ships a full upgrade across product capability and client experience:
👉 Try it: xiaohuanxiong.com
These skills are designed to run inside an Agent Skills-compatible agent.
https://token.sensenova.ai/v1
Mainland China: platform.sensenova.cn/token-plan, Base URL https://token.sensenova.cn/v1INSTALL.md.This repo documents both the international and mainland China SenseNova API flows. Make sure the docs page, API key, base URL, and model name all come from the same region.
Recommended: let the agent install the skills for you. Hand it the repo URL and ask it to clone and drop the skills into the right directory — for example:
"Please install SenseNova-Skills from https://github.com/OpenSenseNova/SenseNova-Skills into your skills directory."
After it finishes, you may need to manually restart the agent service before the new skills are picked up.
| Agent | Target directory |
|---|---|
| OpenClaw | ~/.openclaw/skills/ |
| hermes-agent | ~/.hermes/skills/ |
Clone this repository, then copy the subdirectories under skills/ into the target directory yourself:
git clone https://github.com/OpenSenseNova/SenseNova-Skills.git --depth=1
mkdir -p ~/.openclaw/skills
cp -r SenseNova-Skills/skills/* ~/.openclaw/skills/
For Hermes, swap the target to ~/.hermes/skills/.
Per-category Python dependencies, API keys, and invocation examples are documented in the 📖 Full guide for each section.
📖 Full guide: docs/sn-image-generate_en.md (prerequisites, Quick Start, API config, and invocation samples).
| Name | Label | Description |
|---|---|---|
sn-image-doctor |
Environment Doctor | Validates the SenseNova-Skills environment — checks sn-image-base install, Python deps, and required env vars; interactively fills missing values into .env. |
sn-image-base |
Image Base Layer (Tier 0) | Low-level tools — text-to-image (sn-image-generate), image editing (sn-image-edit), image recognition (sn-image-recognize), and text optimization (sn-text-optimize) — exposed through a unified sn_agent_runner.py, designed to be called by upper-layer skills. |
sn-infographic |
Infographic Generation (Tier 1) | Auto prompt-quality scoring, layout/style selection (87 layouts / 66 styles), multi-round generation with VLM review and quality ranking, producing publication-ready infographics. Supports SenseNova U1.5 Lite, including native 4K output. |
sn-image-imitate |
Image Imitation (Tier 1) | Given one reference image and a target content prompt, generates a new image that imitates the reference. |
sn-image-resume |
Resume Image Generation (Tier 1) | Given resume information, generates a resume image. |
📖 Full guide: docs/sn-ppt-generate.md (prerequisites, Quick Start, API config, and invocation samples).
| Name | Label | Description |
|---|---|---|
sn-ppt-entry |
PPT Entry Point | Unified entry point for PPT generation. Collects role / audience / scene / page count / mode (standard, dazzle, or creative), parses pdf / docx / md / txt inputs, emits task_pack.json + info_pack.json, and dispatches to the downstream mode. |
sn-ppt-story |
PPT Outline (Story) | Mandatory mid-stage between the entry and the exit modes: turns the query, user materials, and completed research into the single editable outline.md; must not be skipped or written by hand. |
sn-ppt-standard |
PPT Standard Mode | style spec → outline → asset plan + per-slot images + VLM QA → per-page HTML → per-page review → build present.html; exports PPTX via its own HTML→PPTX exporter. |
sn-ppt-dazzle |
PPT Dynamic Mode | Turns a prepared outline.md into a single-file 1280×720 dynamic HTML deck (motion, page transitions, keyboard navigation) for animated/interactive presentations. |
sn-ppt-creative |
PPT Creative Mode | One full-page 16:9 PNG per slide generated from a per-page composed prompt; exports PPTX. |
sn-ppt-doctor |
PPT Environment Doctor | Checks local rendering/export dependencies (Python/Node Playwright, Chromium, PPTX exporter) and Bundled media config; reports only — never writes .env or modifies the task directory. |
sn-ppt-tools |
Bundled Tool Fallback | Provides the fallback (web search, image search, image generation, image download) when the host's native search/image tools are absent or fail; reads SN_PPT_* config fr |