← 返回 Skills 市场
multi-image-to-text
作者
AsianGiantDuck
· GitHub ↗
· v1.0.0
· MIT-0
125
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install test20260402
功能描述
批量识别图片中的文字内容并按图片分段输出为结构化文档；当用户需要从多张图片中提取文字、整理图片文字内容、将图片文字转为可编辑文档时使用
安全使用建议
This skill appears coherent and low-risk: it does OCR on images via the agent's read_image tool and outputs Markdown. Before installing or using it, confirm how your platform implements the read_image tool (where images are sent/processed and whether they are retained), avoid uploading highly sensitive images unless you trust the platform's data handling, and be aware that the skill can create a .md file in the agent's working directory when asked. If you need stronger guarantees about deletion or local-only processing, verify those properties with the platform or prefer local/offline OCR tools.
功能分析
Type: OpenClaw Skill
Name: test20260402
Version: 1.0.0
The skill bundle is a standard image-to-text (OCR) utility designed to batch process images and generate structured Markdown documents. It uses the expected 'read_image' tool and follows logical steps for data processing and formatting without any signs of data exfiltration, malicious execution, or harmful prompt injection (SKILL.md and references/output-format.md).
能力评估
Purpose & Capability
Name/description (batch image→text extraction) align with the SKILL.md: it instructs the agent to accept images, call a read_image OCR tool per image, and produce structured Markdown. No unrelated binaries, env vars, or config paths are requested.
Instruction Scope
Instructions are narrowly scoped to: receive images, call read_image for each image, format and output a Markdown document, and optionally write a .md file under ./ with a timestamped name. The doc claims images are used only in the current session and not stored — this is a behavioral claim but cannot be enforced by the instruction file alone; actual persistence/processing depends on the platform/tool implementing read_image and the agent runtime.
Install Mechanism
Instruction-only skill with no install spec and no code files. No downloads or package installs are performed by the skill itself.
Credentials
The skill declares no environment variables or credentials. Its functionality (OCR on user-supplied images) does not require additional secrets, so requested access is proportionate.
Persistence & Privilege
always is false, the skill is user-invocable, and it does not request modification of other skills or global agent settings. It may write a .md file to the local working directory when asked, which is consistent with its stated output options.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install test20260402 - 安装完成后，直接呼叫该 Skill 的名称或使用
/test20260402触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of image-text-extractor skill:
- Supports batch OCR recognition of text from multiple uploaded images (PNG, JPG, JPEG, GIF, WebP).
- Maintains original text structure (paragraphs, titles, lists) for each image.
- Outputs results in a structured Markdown document with clear image-by-image segmentation.
- Handles recognition failures gracefully, continues processing other images.
- Designed with privacy protection; images are used only in-session and not stored.
元数据
常见问题
multi-image-to-text 是什么？
批量识别图片中的文字内容并按图片分段输出为结构化文档；当用户需要从多张图片中提取文字、整理图片文字内容、将图片文字转为可编辑文档时使用. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 125 次。
如何安装 multi-image-to-text？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install test20260402」即可一键安装，无需额外配置。
multi-image-to-text 是免费的吗？
是的，multi-image-to-text 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
multi-image-to-text 支持哪些平台？
multi-image-to-text 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 multi-image-to-text？
由 AsianGiantDuck（@asiangiantduck）开发并维护，当前版本 v1.0.0。
推荐 Skills