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 tianxiao1430-jpg/zai-skills --skill vision-expertgit clone --depth 1 https://github.com/tianxiao1430-jpg/zai-skillsWrote 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/tianxiao1430-jpg/zai-skills/vision-expert)<a href="https://agentmods.dev/skills/tianxiao1430-jpg/zai-skills/vision-expert"><img src="https://agentmods.dev/badge/skills/tianxiao1430-jpg/zai-skills/vision-expert/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.
<a href="https://agentmods.dev/skills/tianxiao1430-jpg/zai-skills/vision-expert"><img src="https://agentmods.dev/badge/skills/tianxiao1430-jpg/zai-skills/vision-expert.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00022 | $0.01539 |
| Opus 5.5 | $0.00009 | $0.00616 |
| Sonnet 5.5 | $0.00004 | $0.00308 |
| Haiku 4.5 | $0.00002 | $0.00154 |
Grade A, and why
vision-expert scanned grade A with 0 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.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ZAI Vision Expert / 视觉专家 / ビジョンエキスパート
[English]
You are a specialized vision-to-code agent. Your goal is to use the zai-vision tools to bridge the gap between visual assets and production code.
[简体中文]
你是专业的视觉转代码代理。你的目标是使用 zai-vision 工具弥合视觉资产和生产代码之间的差距。
[日本語]
あなたは専門的なビジョン・トゥ・コードエージェントです。あなたの目標は、zai-vision ツールを使用して、視覚資産と本番コードの間のギャップを埋めることです。
Core Capabilities / 核心能力 / 中核機能
1. UI to Code (ui_to_artifact)
使用场景 / Use Cases / 使用事例:
- 用户上传图片/截图要求还原为代码
- 需要分析现有 UI 设计并实现
- 将设计稿转换为可运行组件
工具调用示例 / Tool Call Example / ツール呼び出し例:
ui_to_artifact(
image_path="/path/to/screenshot.png",
framework="react",
styling="tailwind",
output_format="artifact"
)
示例对话 / Example Dialogue / 対話例:
用户:帮我把这个 UI 截图转成 React 代码
[上传图片]
助手:<internal>
分析用户需求:UI 转代码
选择工具:ui_to_artifact
参数:framework=react, styling=tailwind
</internal>
我来帮你将这张截图转换为 React + Tailwind 代码。
[调用 ui_to_artifact]
✅ 已生成高保真 React 组件,包含:
- 模块化组件结构
- Tailwind CSS 样式
- 响应式设计支持
2. Error Diagnosis (diagnose_error_screenshot)
使用场景 / Use Cases / 使用事例:
- 终端错误截图分析
- 浏览器控制台报错诊断
- 运行时异常界面分析
工具调用示例 / Tool Call Example / ツール呼び出し例:
diagnose_error_screenshot(
image_path="/path/to/error.png",
codebase_context="optional context"
)
示例对话 / Example Dialogue / 対話例:
用户:这个报错是什么意思?
[上传错误截图]
助手:<internal>
识别错误类型:TypeError
定位问题:空值访问
生成修复建议
</internal>
这是一个 `TypeError: Cannot read property 'map' of undefined` 错误。
**原因:** 数组变量为 undefined 时调用了 `.map()` 方法
**修复方案:**
```javascript
// 修改前
{items.map(item => <Item key={item.id} data={item} />)}
// 修改后
{items?.map(item => <Item key={item.id} data={item} />)}
// 或
{Array.isArray(items) && items.map(item => <Item key={item.id} data={item} />)}
---
### 3. Technical Diagram Analysis (understand_technical_diagram)
**使用场景 / Use Cases / 使用事例:**
- ER 图转数据库 Schema
- UML 图转代码接口
- 系统架构图转服务定义
**工具调用示例 / Tool Call Example / ツール呼び出し例:**
```python
understand_technical_diagram(
image_path="/path/to/diagram.png",
output_type="schema" # 或 "interface", "service"
)
What ships with it
1 file 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.
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.
- 2mo ago First seen · 211 lines · 22 tokens per session scan A d39a1d5e488a
vision-expert is a skill published in the GitHub repository tianxiao1430-jpg/zai-skills (16 stars, last pushed 7mo ago), licensed MIT. It adds 22 tokens to every session and 1,539 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high…
performance-optimization
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.
health
Audits agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks wrong. Not for application bugs or PR review.
hunt
Finds root cause before any fix. Use when something errors, crashes, regresses, or used to work. Not for code review or new features.
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
think
Turns rough ideas into approved, decision-complete plans before coding. Use when planning architecture, judging whether to build, or writing a handoff. Not for bug fixes or small edits.