← Back to Skills Marketplace
试验图片数据提取
by
liuzheng60
· GitHub ↗
· v1.0.3
· MIT-0
28
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install image-table-extractor-lz
Description
从图片中提取表格数据并输出为表格和CSV格式；当用户需要从图片提取表格数据、识别表格内容或导出CSV时使用
README (SKILL.md)
图片表格数据提取
任务目标
- 本 Skill 用于：从用户上传的图片中提取表格数据
- 能力包含：图片识别、表格数据提取、数据过滤、格式转换
- 触发条件：用户需要从图片中提取表格、识别表格内容或导出数据
操作步骤
1. 检查图片上传
- 检查用户消息中是否包含图片
- 如果没有图片，提示用户："请上传包含表格的图片"
- 如果有图片，继续下一步
2. 识别图片内容
- 识别图片内容，提取、过滤数据
- 详见 references/img-table.md
3. 输出表格格式
将提取的数据以 Markdown 表格格式输出：
| 列名1 | 列名2 | 列名3 |
|-------|-------|-------|
| 数据1 | 数据2 | 数据3 |
| 数据4 | 数据5 | 数据6 |
4. 输出CSV格式
将提取的数据以 CSV 格式输出：
列名1,列名2,列名3
数据1,数据2,数据3
数据4,数据5,数据6
CSV格式规范：
- 使用逗号分隔字段
- 如果字段包含逗号、引号或换行符，用双引号包裹
- 双引号字段内的双引号需转义为两个双引号
- 详见 references/csv-format.md
注意事项
输出方式
- 应该同时输出表格形式直接展示和CVS格式数据给用户
数据完整性
- 不修改数据：保持所有数据的原始格式和内容
- 保留表头：如果图片中有表头，必须在输出中保留
- 完整提取：提取所有可见的表格数据，不遗漏任何单元格，也不要添加任何数据
过滤规则
- 仅移除明确为"pass"（不区分大小写）、“通过”的单元格
- 不移除空单元格（除非原表格中没有）
- 不移除其他数据
格式要求
- 表格格式：使用标准 Markdown 表格语法
- CSV格式：遵循标准CSV规范，确保可被电子表格软件正确解析
- 两种格式的数据内容应完全一致
Usage Guidance
Install only if you are comfortable sending image contents to the Ketop API and providing a KETOP_KEY_TOKEN. Prefer a version that clearly declares the credential, asks before external uploads, and explains provider privacy/retention handling.
Capability Tags
Capability Assessment
Purpose & Capability
The stated purpose of extracting table data from images matches the included OCR helper and CSV/table formatting references.
Instruction Scope
The instructions direct running a local Python helper on an absolute image path, and the helper uploads that file externally without clear path limits or an explicit user-consent step.
Install Mechanism
There is no install script or automatic installer shown; the provided Python file is a helper invoked by the skill instructions.
Credentials
The helper posts the selected image file to https://kpp.ketop.cn, which is proportionate to OCR but not clearly disclosed in the main skill description or bounded by privacy/retention guidance.
Persistence & Privilege
The reference instructions ask the user to obtain and save KETOP_KEY_TOKEN even though the registry declares no required environment variables or primary credential.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install image-table-extractor-lz - After installation, invoke the skill by name or use
/image-table-extractor-lz - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
No changes detected in this version.
- No file modifications or updates were found.
- Functionality and documentation remain the same as the previous release.
v1.0.2
Version 1.0.2 Changelog
- Clarified task scope and feature list in documentation.
- Added detailed step-by-step operation instructions.
- Specified strict data integrity and filtering rules.
- Clearly outlined output in both Markdown table and CSV formats.
- Included CSV format specification and reference links.
- Documented requirements for preserving original data and table headers.
Metadata
Frequently Asked Questions
What is 试验图片数据提取?
从图片中提取表格数据并输出为表格和CSV格式；当用户需要从图片提取表格数据、识别表格内容或导出CSV时使用. It is an AI Agent Skill for Claude Code / OpenClaw, with 28 downloads so far.
How do I install 试验图片数据提取?
Run "/install image-table-extractor-lz" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 试验图片数据提取 free?
Yes, 试验图片数据提取 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 试验图片数据提取 support?
试验图片数据提取 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 试验图片数据提取?
It is built and maintained by liuzheng60 (@liuzheng60); the current version is v1.0.3.
More Skills