← 返回 Skills 市场
170
总下载
2
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install vlm-image-helper
功能描述
Visual inspection helper for VLM and OCR workflows. Use when agent needs to help a vision model see an image more clearly before re-analysis: rotate misalign...
安全使用建议
This appears to be a focused, local image-preprocessing helper suitable for VLM/OCR workflows. Before installing or running: (1) review the full script if you will process sensitive images (it operates locally and returns base64 or files, but you should avoid pasting secrets into command arguments), (2) install Pillow from the official PyPI source (pip install Pillow) or via your vetted package manager, and (3) confirm your agent won't forward image data to external services unless you intend that. If you need a deeper audit, provide the remainder of scripts/image_helper.py for a line-by-line review.
功能分析
Type: OpenClaw Skill
Name: vlm-image-helper
Version: 0.1.0
The vlm-image-helper skill is a legitimate utility designed to assist Vision Language Models (VLMs) by preprocessing images for better OCR and visual analysis. The primary script, scripts/image_helper.py, uses the Pillow library to perform standard image transformations like rotation, cropping, and scaling, with no evidence of malicious behavior such as data exfiltration, network calls, or unauthorized system access. The instructions in SKILL.md and the documentation are consistent with the tool's stated purpose and do not contain harmful prompt-injection attempts.
能力评估
Purpose & Capability
Name/description (VLM/OCR preprocessing) match the provided CLI, SKILL.md, README and the included script: rotation, semantic cropping, scaling and enhancement are implemented and expected for this purpose.
Instruction Scope
SKILL.md limits scope to minimal transformations for re-analysis and documents input/output rules. The runtime instructions only reference the included script and local image inputs/outputs (file paths, data URIs, base64) — no directives to read unrelated files or send data externally.
Install Mechanism
No install spec in registry; the code is instruction-only plus a small Python script. The only external dependency is Pillow (pip), which is reasonable and documented. No downloads from unknown URLs or archive extraction are used.
Credentials
The skill requires no environment variables, no credentials, and no config paths. The script uses only local temp files and in-memory base64 — proportional to the stated functionality.
Persistence & Privilege
Skill is not always-enabled and uses no privileged agent APIs or modifications to other skills. It writes only its own temporary output files when asked and returns base64 on demand.
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 vlm-image-helper - 安装完成后，直接呼叫该 Skill 的名称或使用
/vlm-image-helper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
v0.1.0
- Initial release of vlm-image-helper: a visual preprocessing tool for OCR and VLM tasks.
- Provides quick commands for rotating, cropping, zooming, enhancing, or converting images to improve model analysis.
- Designed for minimal, targeted image transformations—avoid general-purpose editing.
- Supports input/output as file paths, base64 strings, or data URIs.
- Emphasizes iterative improvement: re-analyze after each edit rather than chaining many changes.
- Includes references for full CLI options and preset parameters.
元数据
常见问题
Vlm Image Helper 是什么？
Visual inspection helper for VLM and OCR workflows. Use when agent needs to help a vision model see an image more clearly before re-analysis: rotate misalign... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 170 次。
如何安装 Vlm Image Helper？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install vlm-image-helper」即可一键安装，无需额外配置。
Vlm Image Helper 是免费的吗？
是的，Vlm Image Helper 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Vlm Image Helper 支持哪些平台？
Vlm Image Helper 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 Vlm Image Helper？
由 testlbin（@testlbin）开发并维护，当前版本 v0.1.0。
推荐 Skills