diff --git a/packages/website/src/pages/docs/introduction/limitations/page.tsx b/packages/website/src/pages/docs/introduction/limitations/page.tsx
index 665091d..ac6ebf2 100644
--- a/packages/website/src/pages/docs/introduction/limitations/page.tsx
+++ b/packages/website/src/pages/docs/introduction/limitations/page.tsx
@@ -1,3 +1,5 @@
+import { Link } from 'wouter'
+
import { useLanguage } from '@/i18n/context'
export default function LimitationsPage() {
@@ -11,184 +13,144 @@ export default function LimitationsPage() {
{isZh
- ? '了解 page-agent 当前的功能边界和技术限制'
- : "Understand page-agent's current capabilities and technical constraints"}
+ ? 'Page Agent 基于 DOM 理解网页并执行操作。这决定了它的能力边界。'
+ : 'Page Agent understands web pages via DOM and performs actions accordingly. This defines its capability boundary.'}
+ {/* PageAgent.js vs PageAgentExt */}
- {isZh ? '页面支持限制' : 'Page Support Limitations'}
+ {isZh ? 'PageAgent.js vs PageAgentExt' : 'PageAgent.js vs PageAgentExt'}
- {isZh
- ? '• 无法操作未接入该能力的网站:需要目标网站主动集成 page-agent'
- : '• Requires integration: Cannot operate on sites without page-agent'}
-
-
+
+ {isZh
+ ? 'PageAgent.js 是核心库,运行在页面内。PageAgentExt 是可选的浏览器扩展,提供额外的浏览器级控制能力。'
+ : 'PageAgent.js is the core library running inside a page. PageAgentExt is an optional browser extension that adds browser-level control.'}
+
- {isZh
- ? 'page-agent 基于 DOM 结构进行理解和操作,没有视觉识别能力,无法理解以下内容:'
- : 'page-agent operates based on DOM structure with no visual recognition. Cannot understand:'}
-
-
-
- {isZh
- ? '• 图片内容:无法识别图片中的文字、图标或视觉元素'
- : '• Image content: Cannot recognize text, icons, or visual elements in images'}
-
- {isZh
- ? '所有操作都基于 DOM 元素的语义化标签和属性。如果页面结构不够语义化,或者没有任何 accessibility 特性,可能影响 AI 的理解准确性。'
- : 'All operations rely on semantic tags and attributes. Poor semantic structure or lack of accessibility features may affect AI understanding accuracy.'}
-
- {isZh
- ? '反常识的交互规则、基于视觉的操作提示、复杂的鼠标交互、快速出现快速消失的元素等,都会影响 AI 的理解和操作。'
- : 'Counter-intuitive interaction rules, visual-only operation hints, complex mouse interactions, or rapidly appearing/disappearing elements can affect AI understanding and operation.'}
-
+ {isZh
+ ? 'Page Agent 不使用多模态模型,不截图,没有视觉能力。仅通过 DOM 结构理解页面。'
+ : 'Page Agent does not use multimodal models, does not take screenshots, and has no visual capability. It reads pages through DOM structure only.'}
+
+
+ {isZh
+ ? '图片、Canvas、WebGL、SVG 等视觉内容无法被识别。页面的语义化程度和可访问性直接影响 AI 的理解准确性。'
+ : 'Images, Canvas, WebGL, SVG and other visual content cannot be recognized. Page semantic quality and accessibility directly affect AI accuracy.'}
+
+
+
+ {/* Website Quality */}
+
+ {isZh ? '网页质量影响' : 'Page Quality Matters'}
+
+
+
+ {isZh
+ ? '反常识的交互逻辑、纯视觉的操作提示、快速出现消失的元素等都会降低自动化成功率。语义化的 HTML 和良好的可访问性会显著提升效果。'
+ : 'Counter-intuitive interactions, visual-only cues, and rapidly appearing/disappearing elements reduce automation success. Semantic HTML and good accessibility significantly improve results.'}
+