Wanwu is an enterprise platform for building AI agents, workflows, retrieval-augmented applications, and managing models in multi-tenant environments. It is designed for developers and enterprise teams delivering AI applications and integrations. The catalogue entries provide skills and agents for using the platform.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add UnicomAI/wanwu --skill frontend-devgit clone --depth 1 https://github.com/UnicomAI/wanwuWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/unicomai/wanwu/frontend-dev)<a href="https://agentmods.dev/skills/unicomai/wanwu/frontend-dev"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/frontend-dev.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00087 | $0.05691 |
| Opus 5 | $0.00044 | $0.02846 |
| Sonnet 5 | $0.00017 | $0.01138 |
| Haiku 4.5 | $0.00009 | $0.00569 |
Grade B, and why
frontend-dev scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
3. **Execute:** Show prompt to user, **MUST confirm before generating**, then run script This is a copy
97% identical to frontend-dev — 276 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 599 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Studio
Build complete, production-ready frontend pages by orchestrating 5 specialized capabilities: design engineering, motion systems, AI-generated assets, persuasive copy, and generative art.
Invocation
/frontend-dev <request>
The user provides their request as natural language (e.g. "build a landing page for a music streaming app").
Skill Structure
frontend-dev/
├── SKILL.md # Core skill (this file)
├── scripts/ # Asset generation scripts
│ ├── minimax_tts.py # Text-to-speech
│ ├── minimax_music.py # Music generation
│ ├── minimax_video.py # Video generation (async)
│ └── minimax_image.py # Image generation
├── references/ # Detailed guides (read as needed)
│ ├── minimax-cli-reference.md # CLI flags quick reference
│ ├── asset-prompt-guide.md # Asset prompt engineering rules
│ ├── minimax-tts-guide.md # TTS usage & voices
│ ├── minimax-music-guide.md # Music prompts & lyrics format
│ ├── minimax-video-guide.md # Camera commands & models
│ ├── minimax-image-guide.md # Ratios & batch generation
│ ├── minimax-voice-catalog.md # All voice IDs
│ ├── motion-recipes.md # Animation code snippets
│ ├── env-setup.md # Environment setup
│ └── troubleshooting.md # Common issues
├── templates/ # Visual art templates
│ ├── viewer.html # p5.js interactive art base
│ └── generator_template.js # p5.js code reference
└── canvas-fonts/ # Static art fonts (TTF + licenses)
Project Structure
Assets (Universal)
All frameworks use the same asset organization:
assets/
├── images/
│ ├── hero-landing-1710xxx.webp
│ ├── icon-feature-01.webp
│ └── bg-pattern.svg
├── videos/
│ ├── hero-bg-1710xxx.mp4
│ └── demo-preview.mp4
└── audio/
├── bgm-ambient-1710xxx.mp3
└── tts-intro-1710xxx.mp3
Asset naming: {type}-{descriptor}-{timestamp}.{ext}
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- canvas-fonts/ArsenalSC-OFL.txt 4.4 KB
- canvas-fonts/ArsenalSC-Regular.ttf 162 KB
- canvas-fonts/BigShoulders-Bold.ttf 92 KB
- canvas-fonts/BigShoulders-OFL.txt 4.4 KB
- canvas-fonts/BigShoulders-Regular.ttf 92 KB
- canvas-fonts/Boldonse-OFL.txt 4.4 KB
- canvas-fonts/Boldonse-Regular.ttf 75 KB
- canvas-fonts/BricolageGrotesque-Bold.ttf 89 KB
- canvas-fonts/BricolageGrotesque-OFL.txt 4.4 KB
- canvas-fonts/BricolageGrotesque-Regular.ttf 89 KB
- canvas-fonts/CrimsonPro-Bold.ttf 105 KB
- canvas-fonts/CrimsonPro-Italic.ttf 106 KB
- canvas-fonts/CrimsonPro-OFL.txt 4.4 KB
- canvas-fonts/CrimsonPro-Regular.ttf 104 KB
- canvas-fonts/DMMono-OFL.txt 4.4 KB
- canvas-fonts/DMMono-Regular.ttf 48 KB
- canvas-fonts/EricaOne-OFL.txt 4.4 KB
- canvas-fonts/EricaOne-Regular.ttf 24 KB
- canvas-fonts/GeistMono-Bold.ttf 76 KB
- canvas-fonts/GeistMono-OFL.txt 4.4 KB
- canvas-fonts/GeistMono-Regular.ttf 76 KB
- canvas-fonts/Gloock-OFL.txt 4.4 KB
- canvas-fonts/Gloock-Regular.ttf 93 KB
- canvas-fonts/IBMPlexMono-Bold.ttf 133 KB
- canvas-fonts/IBMPlexMono-OFL.txt 4.4 KB
- canvas-fonts/IBMPlexMono-Regular.ttf 131 KB
- canvas-fonts/IBMPlexSerif-Bold.ttf 157 KB
- canvas-fonts/IBMPlexSerif-BoldItalic.ttf 166 KB
- canvas-fonts/IBMPlexSerif-Italic.ttf 166 KB
- canvas-fonts/IBMPlexSerif-Regular.ttf 157 KB
- canvas-fonts/InstrumentSans-Bold.ttf 66 KB
- canvas-fonts/InstrumentSans-BoldItalic.ttf 68 KB
- canvas-fonts/InstrumentSans-Italic.ttf 68 KB
- canvas-fonts/InstrumentSans-OFL.txt 4.4 KB
- canvas-fonts/InstrumentSans-Regular.ttf 66 KB
- canvas-fonts/InstrumentSerif-Italic.ttf 69 KB
- canvas-fonts/InstrumentSerif-Regular.ttf 68 KB
- canvas-fonts/Italiana-OFL.txt 4.4 KB
- canvas-fonts/Italiana-Regular.ttf 27 KB
- canvas-fonts/JetBrainsMono-Bold.ttf 112 KB
- canvas-fonts/JetBrainsMono-OFL.txt 4.4 KB
- canvas-fonts/JetBrainsMono-Regular.ttf 112 KB
- canvas-fonts/Jura-Light.ttf 151 KB
- canvas-fonts/Jura-Medium.ttf 151 KB
- canvas-fonts/Jura-OFL.txt 4.4 KB
- canvas-fonts/LibreBaskerville-OFL.txt 4.4 KB
- canvas-fonts/LibreBaskerville-Regular.ttf 144 KB
- canvas-fonts/Lora-Bold.ttf 131 KB
- canvas-fonts/Lora-BoldItalic.ttf 137 KB
- canvas-fonts/Lora-Italic.ttf 136 KB
- canvas-fonts/Lora-OFL.txt 4.4 KB
- canvas-fonts/Lora-Regular.ttf 131 KB
- canvas-fonts/NationalPark-Bold.ttf 77 KB
- canvas-fonts/NationalPark-OFL.txt 4.4 KB
- canvas-fonts/NationalPark-Regular.ttf 75 KB
- canvas-fonts/NothingYouCouldDo-OFL.txt 4.4 KB
- canvas-fonts/NothingYouCouldDo-Regular.ttf 31 KB
- canvas-fonts/Outfit-Bold.ttf 54 KB
- canvas-fonts/Outfit-OFL.txt 4.4 KB
- canvas-fonts/Outfit-Regular.ttf 54 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 599 lines · 87 tokens per session scan B de95c2bc6852
frontend-dev is a skill published in the GitHub repository UnicomAI/wanwu (2,460 stars, last pushed 2d ago), licensed Apache-2.0. It adds 87 tokens to every session and 5,691 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). It is 97% identical to frontend-dev, differing in 276 lines, and is treated as a copy.
Other skills, from other repositories
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
sketch
Throwaway HTML mockups: 2-3 design variants to compare.
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
impeccable
Frontend design guidance, upstream-maintained (impeccable).
glassmorphism
Glassmorphism design system skill. Use when building frosted-glass UI components with blur, transparency, and layered depth effects.
liquid-glass
Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.