← 返回 Skills 市场
331
总下载
1
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install geoinfer-image-geolocation
功能描述
AI image geolocation via visual analysis — no GPS or EXIF needed. Requires GEOINFER_API_KEY.
使用说明 (SKILL.md)
GeoInfer — AI Image Geolocation
🌍 Geolocate any image using AI — no GPS, no EXIF, no metadata required.
GeoInfer analyzes visual cues (architecture, terrain, vegetation, signage) to predict where a photo was taken, down to city level. Built for OSINT, digital forensics, investigative journalism, and security workflows.
Requires the GEOINFER_API_KEY environment variable.
Setup
- Get your API key from app.geoinfer.com/en/api
- Run:
export GEOINFER_API_KEY="geo_your_key_here"
Tools
Predict Image Location
bash scripts/predict.sh /path/to/image.jpg [model_id] [top_n]
model_id— model to use (default:global_v0_1). Runmodels.shto list available models.top_n— number of top predictions to return, 1–15 (default:5)- Accepts JPEG, PNG, WebP, and other common image formats (max 10MB)
Example:
bash scripts/predict.sh photo.jpg global_v0_1 5
Output: JSON array of top location predictions with coordinates and confidence scores.
List Available Models
bash scripts/models.sh
Returns all models available to your API key (e.g., Global, Car, Property, Accuracy).
Check Credits
bash scripts/credits.sh
Returns your current credit balance.
Credit Costs
| Model type | Credits per prediction |
|---|---|
| Global | 1 |
| Car | 2 |
| Property | 3 |
| Accuracy | 3 |
Agent Usage Notes
- Always run
models.shfirst if unsure which model to use - Prefer
global_v0_1for general-purpose geolocation - Use
top_n=1for fastest single-answer responses;top_n=5for investigations requiring confidence comparison - Check credits before running large batch jobs
- Images must be local files — download remote images before passing to
predict.sh
安全使用建议
This skill appears internally consistent, but before installing: 1) Understand that any image you run through this will be uploaded to GeoInfer's servers (api.geoinfer.com) — do not upload sensitive or personally identifying images unless you trust the provider and account billing/retention. 2) The scripts use curl and bash; ensure your environment has those binaries. 3) Verify the origin and trustworthiness of the GeoInfer service and the API key you obtain (billing, rate limits, and access scope). 4) Consider using a limited/revocable API key and testing with non-sensitive images first. 5) If you need offline/air-gapped processing or stronger privacy guarantees, this hosted-solution approach may not be suitable.
功能分析
Type: OpenClaw Skill
Name: geoinfer-image-geolocation
Version: 1.0.1
The skill bundle provides a straightforward interface for an image geolocation API (geoinfer.com). The shell scripts (predict.sh, models.sh, and credits.sh) perform standard API requests using curl, properly handle the required API key via environment variables, and contain no evidence of malicious intent, data exfiltration to unauthorized domains, or obfuscation.
能力评估
Purpose & Capability
The name/description, SKILL.md, and included scripts all consistently implement image geolocation and require only GEOINFER_API_KEY. Minor note: the scripts use curl but the registry metadata lists no required binaries; curl (and bash) are implicitly required to run the provided scripts.
Instruction Scope
Runtime instructions and scripts only read a local image file and the declared GEOINFER_API_KEY environment variable, then POST the file to api.geoinfer.com. They do not reference other files, system paths, or unrelated environment variables, nor do they send data to unexpected endpoints.
Install Mechanism
No install spec (instruction-only with small helper scripts). Nothing is downloaded or extracted; files are simple bash scripts that invoke the GeoInfer API.
Credentials
Only a single service-specific credential (GEOINFER_API_KEY) is required, which is appropriate for a hosted API. The scripts do not request additional secrets or unrelated credentials.
Persistence & Privilege
The skill does not request always:true or any special persistence; it will not modify other skills or system-wide settings. Autonomous invocation is allowed by default but is not combined with any elevated privileges 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 geoinfer-image-geolocation - 安装完成后，直接呼叫该 Skill 的名称或使用
/geoinfer-image-geolocation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
v1.0.1
- Added frontmatter metadata for tool name, description, and environment variable requirement.
- No changes to functionality or usage instructions.
- Existing documentation and usage notes remain unchanged.
v1.0.0
Initial release of GeoInfer — AI Image Geolocation skill:
- Allows geolocation of any image based on visual analysis, without GPS or metadata.
- Predicts image locations down to the city level using various AI models (supports different model types).
- Provides scripts for location prediction, listing available models, and checking credit balance.
- Accepts common image formats up to 10MB in size.
- Requires a valid GEOINFER_API_KEY for access and usage.
- Designed for OSINT, forensics, journalism, and security workflows.
元数据
常见问题
GeoInfer Image Geolocation 是什么？
AI image geolocation via visual analysis — no GPS or EXIF needed. Requires GEOINFER_API_KEY. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 331 次。
如何安装 GeoInfer Image Geolocation？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install geoinfer-image-geolocation」即可一键安装，无需额外配置。
GeoInfer Image Geolocation 是免费的吗？
是的，GeoInfer Image Geolocation 完全免费（开源免费），可自由下载、安装和使用。
GeoInfer Image Geolocation 支持哪些平台？
GeoInfer Image Geolocation 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 GeoInfer Image Geolocation？
由 samtin0x（@samtin0x）开发并维护，当前版本 v1.0.1。
推荐 Skills