agentmods.dev

huashu-design

huashu-design is a skill for Claude Code, Codex from pc-software-org/huashu-design-en. It costs 535 tokens per session (17,217 once invoked), scanned C, original, MIT.

A design skill that creates high-fidelity visual work with HTML as its production tool. It supports interactive prototypes, design variations, presentations, animations, infographics, and visualizations, with the output shaped for the chosen medium.

In plain words
What is it for?
Use it for product mockups, interactive demos, side-by-side design directions, 1920×1080 slide decks, motion concepts, and print-quality data visuals.
Why use it?
It helps turn a design idea into something people can click through, compare, present, or watch. The result is not limited to a conventional webpage layout.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

not rated 24repo 2mo ago C scan 535 tokens original MIT

Good fit Use it for product mockups, interactive demos, side-by-side design directions, 1920×1080 slide decks, motion concepts, and print-quality data visuals.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pc-software-org/huashu-design-en/huashu-design-en
View source ↗ pc-software-org/huashu-design-en
Install

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.

Any agent
npx skills add pc-software-org/huashu-design-en --skill huashu-design-en
Clone the repo
git clone --depth 1 https://github.com/pc-software-org/huashu-design-en

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for huashu-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/pc-software-org/huashu-design-en/huashu-design-en/github.svg)](https://agentmods.dev/skills/pc-software-org/huashu-design-en/huashu-design-en)
Your own site
<a href="https://agentmods.dev/skills/pc-software-org/huashu-design-en/huashu-design-en"><img src="https://agentmods.dev/badge/skills/pc-software-org/huashu-design-en/huashu-design-en/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for huashu-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/pc-software-org/huashu-design-en/huashu-design-en"><img src="https://agentmods.dev/badge/skills/pc-software-org/huashu-design-en/huashu-design-en.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 535 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 17,217 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00535 $0.17217
Opus 5.5 $0.00214 $0.06887
Sonnet 5.5 $0.00107 $0.03443
Haiku 4.5 $0.00053 $0.01722

Measured 2mo ago against content hash a365c3a011be, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

huashu-design scanned grade C with 2 findings 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (assets/deck_stage.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

- 🛑 **Checkpoint 2·Asset self-inspection**: Confirm that core assets are in place before starting work - physical products must have product pictures (not CSS silhouettes), digital products must have logo+UI screenshots

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -o assets/<brand>-brand/logo.svg https://<brand>.com/logo.svg
SKILL.md · 815 lines

How it starts

The opening of the file, as written. The whole thing — 815 lines — stays where its author put it; the contents beside it link to each section on GitHub.

#HuashuDesign · Huashu-Design

You are a designer working with HTML, not a programmer. The user is your manager, and you produce thoughtful, well-crafted design work.

HTML is a tool, but your medium and output format will change - don't be like a webpage when making slides, don't be like a Dashboard when making animations, don't be like an instruction manual when making app prototypes. Experts in the corresponding fields according to the task embody: animator/UX designer/slideshow designer/prototyper.

Prerequisites for use

This skill is designed specifically for "using HTML for visual output"; it is not a general-purpose magic wand for every HTML task. Applicable scenarios:

  • Interactive prototype: high-fidelity product mockup, users can click, switch, and feel the process
  • Design variation exploration: Compare multiple design directions side by side, or adjust parameters in real time with Tweaks
  • Presentation Slides: 1920×1080 HTML deck, can be used as PPT
  • Animation Demo: timeline-driven motion design, making video materials or concept demonstrations
  • Infographics/Visualizations: Precise layout, data-driven, print-grade quality

Unsuitable scenarios: Production-level Web Apps, SEO websites, and dynamic systems that require backends - use frontend-design skill for these.

Core Principle #0 · Facts come before hypotheses (highest priority, overriding all other processes)

**Any factual assertion involving the existence, release status, version number, and specification parameters of a specific product/technology/event/person must be verified by WebSearch in the first step. It is prohibited to make assertions based on training corpus. **

Trigger conditions (meet any one):

  • The user mentioned a specific product name that you are not familiar with or are unsure about (such as "DJI Pocket 4", "Nano Banana Pro", "Gemini 3 Pro", a new version of SDK)
  • Involving release timelines, version numbers, and specifications in 2024 and beyond
  • Sentences like "I remember...", "It probably hasn't been released yet", "Probably around...", "Maybe it doesn't exist" come up in your mind
  • User requests design materials for a specific product/company

Read the full file on GitHub · 815 lines

Files

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.

Changes

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.

  1. 2mo ago First seen · 815 lines · 535 tokens per session scan C a365c3a011be

Subscribe to this mod's changes

huashu-design is a skill published in the GitHub repository pc-software-org/huashu-design-en (24 stars, last pushed 2mo ago), licensed MIT. It adds 535 tokens to every session and 17,217 once invoked, about $0.0021 per session on Opus 5.5. A static security scan graded it C with 2 findings (hidden instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Creative and mediaDesign and UX
Related

huashu-design compared with skills from other repositories

huashu-design next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
huashu-designpc-software-org/huashu-design-enSkill242mo agoMITC535Claude Code, Codex
webgl-holographic-foilnexu-io/open-designSkill106kyesterdayApache-2.0A41Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-designSkill106kyesterdayApache-2.0A53Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-designSkill106kyesterdayApache-2.0A78Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codexSkill34k4d agoMITA52Codex
glance-canonical-layoutsandroid/skillsSkill10kyesterdayApache-2.0A56Claude Code
accessibilitymicrosoft/hve-coreSkill1.6kyesterdayMITA47Claude Code