← 返回 Skills 市场
74
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install pedestrian-traffic-counting-gpt-multimodal
功能描述
Analyze images and multi-frame sequences using OpenAI GPT series
安全使用建议
Before installing: (1) Expect to provide an OpenAI API key (OPENAI_API_KEY) — the skill's examples require it but the registry metadata doesn't declare it; ask the publisher to correct metadata. (2) Understand that all images (including any sensitive content or PII) will be uploaded to OpenAI for analysis — confirm this is acceptable for your data policies. (3) Check model availability, costs, and rate limits (large payloads and many images can be costly). (4) If you need stronger privacy, ask for explicit mention of where data is sent, retention policy, and whether local-only processing is possible. (5) Consider testing with non-sensitive sample images first and confirm the skill's metadata is updated to declare required environment variables.
功能分析
Type: OpenClaw Skill
Name: pedestrian-traffic-counting-gpt-multimodal
Version: 0.1.0
The skill bundle provides comprehensive documentation and code examples for using OpenAI's vision models for image and video frame analysis. It follows standard practices for API integration, including proper handling of the OPENAI_API_KEY and structured JSON outputs. No malicious patterns, data exfiltration, or prompt injection attempts were found. Files: _meta.json, SKILL.md.
能力标签
能力评估
Purpose & Capability
The name/description (image and multi-frame analysis via OpenAI vision models) aligns with the SKILL.md examples. However, the SKILL.md uses OPENAI_API_KEY in every example even though the registry metadata lists no required environment variables or primary credential.
Instruction Scope
Runtime instructions are limited to reading image files (local or via URLs/base64), encoding them, and sending them to OpenAI's vision-capable GPT models; they do not instruct reading unrelated system files or contacting third-party endpoints other than the model API. The instructions do rely on local file I/O and environment variables (OPENAI_API_KEY).
Install Mechanism
Instruction-only skill with no install spec and no bundled code — nothing is written to disk by an installer. This is the lowest-risk install mechanism.
Credentials
Examples repeatedly call os.environ.get('OPENAI_API_KEY') but the skill metadata declares no required env vars or primary credential; that is an inconsistency. Requesting an API key to call OpenAI is proportionate for the stated purpose, but the metadata omission is misleading. Also: the skill will transmit image contents (potentially sensitive) to OpenAI — users should be warned about privacy, compliance, and cost implications.
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform privileges. Autonomous invocation is allowed by default but is not combined with other high-risk flags here.
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 pedestrian-traffic-counting-gpt-multimodal - 安装完成后，直接呼叫该 Skill 的名称或使用
/pedestrian-traffic-counting-gpt-multimodal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
Bulk publish from all-task-skills-dedup
元数据
常见问题
gpt-multimodal 是什么？
Analyze images and multi-frame sequences using OpenAI GPT series. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 74 次。
如何安装 gpt-multimodal？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install pedestrian-traffic-counting-gpt-multimodal」即可一键安装，无需额外配置。
gpt-multimodal 是免费的吗？
是的，gpt-multimodal 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
gpt-multimodal 支持哪些平台？
gpt-multimodal 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 gpt-multimodal？
由 lnj22（@lnj22）开发并维护，当前版本 v0.1.0。
推荐 Skills