Maintainer of this skill?
# Add to your Claude Code skills
git clone https://github.com/CCharlie-xiu/wuch-aiSee how wuch-ai compares with popular alternatives.
wuch-ai is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by CCharlie-xiu. 说一句，界面在画布上长出来 · https://wuch-ai.net. It has 53 GitHub stars.
wuch-ai's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/CCharlie-xiu/wuch-ai" and add it to your Claude Code skills directory (see the Installation section above).
wuch-ai is primarily written in JavaScript. It is open-source under CCharlie-xiu 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 wuch-ai against similar tools.
No comments yet. Be the first to share your thoughts!
Available after the catalog security scan passes.
⚠️ 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.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
English | 中文
Say what you want — the UI grows on the canvas.
No drag-and-drop builder, no hand-written frontend. One message in the chat pane; the left canvas streams and renders as it goes. Sliders, checkboxes, and options update in place—no extra model round-trip. Sessions, memory, and knowledge stay on your side.
Try it → https://wuch-ai.net · Demo replay (no model key required) · Intro
| You get | Meaning |
|---|---|
| Natural language → interactive UI | Say “build a Q3 sales page” and charts, tables, and controls appear on the left |
| Edit in place, no extra model call | Sliders, checks, and options update locally; send another message when you need the next turn |
| Isolated cloud trial accounts | Sign up and use; sessions / memory / knowledge are per account |
| Self-hostable | bun run dev locally, or deploy to your own Workers |
Login. Dedicated auth page; register or sign in before the canvas. Keep several accounts and switch anytime.
Main UI. Canvas on the left, chat on the right. One sentence on the right; the left streams as it renders. The top bar shows source, compile output, and diagnostics.
Product analytics dashboard. Ask for a product dashboard and get metrics, trend charts, and insight cards—then refine in chat.
Maps & routes. Demo replay works without a model: store pins, trunk lines, region highlights—same pipeline as live chat.
Tables & Excel. Editable sales grids; import your own sheet, then ask the chat about targets and budget.
| Entry | What it does |
|---|---|
| wuch-ai.net | Hosted app: register, sign in, use |
/login |
Sign up / sign in, then enter the main UI |
/ |
Live UI left, chat right; set model base URL and key in Settings |
/demos.html |
Canned UI replay without a model (maps, tables, …) |
Say something simple (e.g. “make a Q3 sales page”); the left pane streams and renders. Controls are clickable on the canvas; send another message when you need a new turn.
bun install
bun run dev # http://127.0.0.1:8788
bun run mock # optional fake upstream when you have no key: http://127.0.0.1:8789/v1
http://127.0.0.1:8788/proxy?url=https://api.openai.com/v1bun run mock, then use http://127.0.0.1:8789/v1/demos.html and try map or table demosHosted app: https://wuch-ai.net. Cloudflare deploy notes: apps/cloudflare/README.md.
Deeper design notes live in DESIGN.md, DESIGN-KB.md, and docs/—you don’t need them to start.