mirror of
https://github.com/QianWen-AI/qianwen-ai.git
synced 2026-09-14 19:59:40 +08:00
main
QianWen AI Skills
Fold QianWen's AI skills into your agent. Just talk.
Highlights
- 🤖 Agent-native — Your agent picks the model, tunes the call, and handles errors. You just talk.
- ⚡ One-line install — One command and you're ready. No SDK, no boilerplate.
- 🧠 10 skills, one interface — Text, image, video, voice, vision, model selection, auth, usage, payment, and skill discovery — all built in.
- 🌐 Works across many agents — Plug into many Agent Skills-compatible agents instantly.
Quick Start
Manual Install
Requires Node.js 18+.
npx skills add QianWen-AI/qianwen-ai
When prompted, press a to select all skills, then Enter to confirm.
Let Your Agent Handle It (Recommended)
Paste this into your AI Agent and let it handle everything:
Please install QianWen AI Skills for me:
1. Check if Node.js is installed, install it if not
2. Run: npx skills add QianWen-AI/qianwen-ai
3. If a skill selection prompt appears, select all skills and confirm
4. Once installed, start with "Skills acquired." then list what skills I got and walk me through what I can do with them
Once installed, the qianwen-ops-auth skill will guide you and your agent through API Key setup automatically.
What You Can Do
Tell your agent what you need — it writes the code, picks the right QianWen model, and runs the job.
| Capability | Try saying... |
|---|---|
| Text at Scale | "Write a script to call Qwen-Plus and polish the language in these 10,000 docs" · "Batch-summarize every PDF in this folder using the cheapest text model" |
| Image Generation | "Generate 20 product posters in different styles — try ink wash, flat, and 3D" · "Write a pipeline to add watermarks and expand the background of all images in /assets" |
| Video Generation | "Turn each of these 5 product shots into a 5-second showcase clip" · "Generate a cinematic intro video from this script and key frame" |
| Voice | "Convert all 30 chapters of this audiobook to speech, use a warm female voice" · "Generate bilingual audio intros for each episode in this podcast list" |
| Vision | "Write a script to extract text from every screenshot in this folder and save to an Excel" · "Batch-analyze these 200 floor plan images and output a room-by-room breakdown" |
| Model Selection | "Pick the cheapest model that can handle this translation batch" · "Choose a stronger reasoning model for this problem" |
| Usage & Billing | "Check my remaining free tier quota for qwen3.6-plus" · "Show me the cost breakdown for last month" · "Am I close to hitting my coding plan limits?" |
Skills
| Skill | What it does |
|---|---|
qianwen-text |
Text generation, chat, code, reasoning, function calling |
qianwen-vision |
Image & video understanding, OCR, chart analysis |
qianwen-image-generation |
Text-to-image, image editing, style transfer |
qianwen-video-generation |
Text-to-video, image-to-video, video editing |
qianwen-audio-tts |
Text-to-speech with multiple voice profiles |
qianwen-model-selector |
Recommends the right model for your use case |
qianwen-ops-auth |
API key and authentication management |
qianwen-usage |
Usage queries, free tier checks, subscriptions, billing |
qianwen-payment |
Payment center — account balance, account balance recharge, recharge guidance |
qianwen-find-skills |
Discover, compare, and install QianWen Agent Skills for a task |
Contributing
We'd love your help! Here are a few ways to get involved:
- Report bugs — Something broke? Open an issue with steps to reproduce.
- Suggest features — Have an idea for a new skill or improvement? File a feature request.
- Submit PRs — Fork the repo, create a branch, make your changes, and open a pull request.
- Improve docs — Typos, unclear wording, better examples — all welcome.
Disclaimer — This skill calls QianWen APIs on your behalf; usage costs are billed to your account. AI-generated content may not always be accurate — review before relying on it. Keep your API Key secure. This project is provided as-is, without warranties of any kind.
License
Description
qianwen-image-generation: Generate and edit images using Wan and Qwen Image models. Supports text-to-image, image editing (style transfer, subject consistency, text rendering), and…; qianwen-vision: Understand images and videos with Qwen vision models. TRIGGER when: user wants to analyze, describe, or extract information from images or videos, OCR text…; qianwen-update-check: Check for qianwen-ai updates and notify the user when a new version is available. TRIGGER when: user asks to check for u…
Readme
563 KiB
Languages
Python
87.5%
JavaScript
12.5%