원클릭으로
image-recognition
图片识别与图文理解,基于 PaddleOCR-VL 模型,支持识别图片中的文字、场景、物体等信息。支持109种语言,可输出JSON或Markdown格式。
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
图片识别与图文理解,基于 PaddleOCR-VL 模型,支持识别图片中的文字、场景、物体等信息。支持109种语言,可输出JSON或Markdown格式。
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Word文档处理:创建、编辑、读取.docx文件。用户提到"Word"、"文档"、".docx"、"报告"、"信函"时使用。
使用腾讯云 API 密钥调用腾讯云各种服务,包括翻译、CVM、COS等。
You MUST use this for gathering contexts before any work. This is a Knowledge management for AI agents. Use `brv` to store and retrieve project patterns, decisions, and architectural rules in .brv/context-tree. Uses a configured LLM provider (default: ByteRover, no API key needed) for query and curate operations.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
| name | Image Recognition |
| description | 图片识别与图文理解,基于 PaddleOCR-VL 模型,支持识别图片中的文字、场景、物体等信息。支持109种语言,可输出JSON或Markdown格式。 |
| triggers | ["识别图片","看图","图片识别","OCR","文字识别","图片内容"] |
| mcp | {"command":"uvx","args":["paddleocr-vl-mcp"],"env":{"PADDLEOCR_API_KEY":"your_api_key"}} |
基于 PaddleOCR-VL 的图像识别服务:
百度开源的视觉语言模型:
功能:从图片中提取文字内容
参数说明:
| 参数 | 类型 | 必需 | 说明 |
|---|---|---|---|
| image | string | ✅ | 图片文件路径或URL |
| format | string | ❌ | 输出格式:json/markdown,默认markdown |
| language | string | ❌ | 语言代码,默认自动检测 |
使用示例:
{
"image": "/path/to/image.png",
"format": "markdown",
"language": "ch"
}
返回信息:
功能:分析文档图片的版面结构
参数:
image: 文档图片output_format: 输出格式返回:
功能:从图片中提取表格数据
参数:
image: 包含表格的图片返回:
{
"mcpServers": {
"image-recognition": {
"command": "uvx",
"args": ["paddleocr-vl-mcp"],
"env": {
"PADDLEOCR_API_KEY": "your-api-key"
}
}
}
}
用户:帮我把这份扫描文档转成文字
助手:[调用extract_text,返回Markdown格式]
用户:提取这张图片里的表格数据
助手:[调用extract_table,返回结构化数据]
用户:识别这张截图里的文字
助手:[调用extract_text]
用户:识别这张日文图片的内容
助手:[设置language=ja进行识别]
支持 109种语言 的OCR识别
{
"text": "识别的文字",
"bbox": [x1, y1, x2, y2],
"confidence": 0.95
}
适用场景:需要精确位置信息、程序处理
# 文档标题
正文内容...
| 列1 | 列2 |
|-----|-----|
| 数据 | 数据 |
适用场景:文档阅读、内容展示
# 需要位置信息
extract_text(image, format="json")
# 只需要文本内容
extract_text(image, format="markdown")
# 中文文档
extract_text(image, language="ch")
# 日文文档
extract_text(image, language="ja")
# 混合语言(自动检测)
extract_text(image, language="auto")
# 先分析版面
layout = analyze_document(image)
# 再提取各区域内容
for region in layout.regions:
if region.type == "table":
extract_table(region)
else:
extract_text(region)
⚠️ 重要提示:
| 场景 | 推荐工具 | 说明 |
|---|---|---|
| 文档数字化 | extract_text | 扫描件转文字 |
| 表格录入 | extract_table | 图片表格转Excel |
| 截图提取 | extract_text | 快速获取截图文字 |
| 学术论文 | analyze_document | 识别公式图表 |
A:
A: 支持,但准确率可能低于印刷体
A: 使用extract_table工具,会自动识别表格结构
A: 可以,PaddleOCR-VL支持公式识别
pdf(提取页面)→ image-recognition(识别)→ 整理归档
image-recognition(识别表格)→ xlsx(写入Excel)→ 数据分析
更新时间: 2026-03-08 版本: 1.0 适用对象: 文档处理、数据提取、内容识别