What makes Ghost Eye notable?

1.1K downloads. Trust evidence available

How should Ghost Eye be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Ghost Eye

Ghost Eye 👁️ — Let any pure-text LLM see images through any vision model. OCR + visual summary in one shot. Skill: Ghost Eye Owner: hunter-crk Summary: Ghost Eye 👁️ — Let any pure-text LLM see images through any vision model. OCR + visual summary in one shot. Tags: image:1.0.2, latest:1.0.4, llm:1.0.2, ocr:1.0.2, vision:1.0.2 Version history: v1.0.4 | 2026-07-09T15:59:25.635Z | auto ghost-eye 1.0.4 - Added image analysis cache files for improved performance. - Removed the redundant skill-card.md documentation file. - Upda

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

1.0.4

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.4release · observed Jul 9, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s179nt0fhpj5npbanyqj0jmhhs8a6kyq:ghost-eye

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-hunter-crk-ghost-eye/snapshot"

Documentation

CLAWHUB

52,410 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: "ghost-eye"
description: "Ghost Eye 👁️ — Let any pure-text LLM see images through any vision model. OCR + visual summary in one shot."
metadata:
  {
    "openclaw":
      {
        "emoji": "👁️",
        "requires": { "env": ["NEXN2_API_KEY"] },
        "primaryEnv": "NEXN2_API_KEY",
      },
  }
---

# Ghost Eye 👁️

Give your text-only LLM the power to see. Ghost Eye is a lightweight image preprocessing bridge: when an image enters the conversation, it calls any OpenAI-compatible vision model (default: `nex-agi/Nex-N2-Pro`), produces a structured plain-text output (full OCR + visual summary), and feeds it back into the conversation — so your pure-text model can "see" without ever touching a multimodal API.

## What it does

```
User sends image → Ghost Eye detects → vision model analyzes → OCR text + scene summary → your LLM answers
```

## Two modes

### Mode 1: Auto-preprocess (recommended)
When `multimodalPreprocess` is configured, Ghost Eye fires automatically on any inbound image. The user never knows it's there — they just get answers about images.

### Mode 2: Tool-call mode
Registered as `analyze_image_by_nexn2` tool (name stays for backward compatibility). Your LLM calls it explicitly when it sees an image. Add this to the system prompt:

> When the user sends an image, screenshot, photo, or document scan, call the analyze_image_by_nexn2 tool to extract text and describe the image, then answer based on the returned content.

## Workflow

### Step 1: Receive image

**Priority: `--image-path` > `--image-url` > `--image-base64`**

⛔ Always prefer `--image-path` to avoid command-line `Argument list too long` errors with large base64 strings. Only fall back to `--image-url` or `--image-base64` when no local path is available.

```bash
# Preferred: local file path (no size limit)
python3 {baseDir}/scripts/analyze.py --image-path "<absolute path>"

# Fallback: public URL
python3 {baseDir}/scripts/analyze.py --image-url "<url>"

# Last resort: base64 (small images only, <50KB)
python3 {baseDir}/scripts/analyze.py --image-base64 "<base64>"
```

The script handles:
- Format validation (JPG/PNG/WebP/GIF/BMP via magic bytes)
- Cache check / read / write (MD5-based, 7-day TTL)
- Image compression (Pillow, max 1920px longest edge, quality 85%)
- API call with 1 automatic retry
- Structured JSON output

### Step 2: Parse JSON output

Success:
```json
{"success": true, "content": "【OCR文字提取】\n...\n\n【画面内容总结】\n...", "metadata": {"model": "...", "tokens_used": 1200, "cached": false, "process_time_ms": 1500}}
```

Error:
```json
{"success": false, "content": "error message", "metadata": {}}
```

Pass `content` directly into the LLM conversation context.

### Step 3: Caching

- Cache directory: `{baseDir}/cache/` (auto-created)
- Cache key: MD5 hash of raw image bytes
- TTL: 7 days (`NEXN2_CACHE_TTL_DAYS`)
- Clear cache: delete all `.json` files in `{baseDir}/cache/`
- Toggle: `NEXN2_CACHE_ENABLE=true/false`

## Environment variables

| Variabl

_meta.json

{
  "ownerId": "kn78pm8jn9q0yydy5e2j0k169x8a7evs",
  "slug": "ghost-eye",
  "version": "1.0.4",
  "publishedAt": 1783612765635
}

references/multimodal-config.md

# OpenClaw 多模态预处理配置参考

## multimodalPreprocess 配置

在 `openclaw.json` 中添加：

```json
{
  "multimodalPreprocess": {
    "enable": true,
    "visionSkillId": "nex-n2-image-analyzer",
    "promptTemplate": "以下是图片的完整分析结果，请严格基于该内容回答用户问题：\n{{skillResult}}\n\n用户问题：{{userQuery}}"
  },
  "skills": {
    "entries": {
      "nex-n2-image-analyzer": {
        "enabled": true,
        "apiKey": {
          "source": "env",
          "provider": "default",
          "id": "NEXN2_API_KEY"
        },
        "env": {
          "NEXN2_BASE_URL": "https://api.siliconflow.cn/v1",
          "NEXN2_MODEL_NAME": "nex-agi/Nex-N2-Pro",
          "NEXN2_IMAGE_COMPRESS": "true",
          "NEXN2_CACHE_ENABLE": "true",
          "NEXN2_CACHE_TTL_DAYS": "7",
          "NEXN2_TIMEOUT_MS": "30000"
        }
      }
    }
  }
}
```

## 配置项说明

| 字段 | 说明 |
|------|------|
| `multimodalPreprocess.enable` | 开启全局图片预处理 |
| `multimodalPreprocess.visionSkillId` | 指定处理图片的 Skill 名称 |
| `multimodalPreprocess.promptTemplate` | 拼接结果的模板，`{{skillResult}}` 是 Skill 返回的 content，`{{userQuery}}` 是用户消息 |

## 切换至 OpenRouter

如果使用 OpenRouter 代替 SiliconFlow：

```json
{
  "NEXN2_BASE_URL": "https://openrouter.ai/api/v1",
  "NEXN2_MODEL_NAME": "nex-agi/nex-n2-pro"
}
```

> 注意：OpenRouter 上的模型 ID 可能与 SiliconFlow 略有不同，以实际注册名称为准。

## 不使用全局预处理

如果仅需工具调用模式（非自动触发），保留 `skills.entries` 配置但**不添加** `multimodalPreprocess` 块，并在系统提示词中补充工具调用指令：

> 当用户发送图片、截图、照片、文档截图时，请调用 analyze_image_by_nexn2 工具获取图片的文字与内容描述，再基于返回结果作答。

skill-card.md

## Description:

Ghost Eye lets a pure-text LLM analyze images through an OpenAI-compatible vision model, returning OCR text and a visual summary.

This skill is ready for commercial/non-commercial use.

## Publisher:

[hunter-crk](https://clawhub.ai/user/hunter-crk)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agents use this skill to convert incoming images, screenshots, photos, or scanned documents into text that a text-only LLM can reason over. It supports automatic image preprocessing or explicit tool-call use.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Inbound images can be sent automatically to a third-party vision API.

Mitigation: Use explicit tool-call mode for sensitive work and configure an approved OpenAI-compatible vision endpoint before deployment.

Risk: OCR text and visual summaries are stored in plaintext cache files by default.

Mitigation: Disable caching or regularly clear the cache when images may contain personal, business, credential, or regulated data.

Risk: Using image URLs can introduce uncontrolled network egress.

Mitigation: Prefer local image paths and use image URLs only when outbound network access is constrained and approved.

## Reference(s):

- [OpenClaw multimodal preprocessing configuration](references/multimodal-config.md)
- [ClawHub Ghost Eye skill page](https://clawhub.ai/hunter-crk/skills/ghost-eye)

## Skill Output:

**Output Type(s):** [Text, Markdown, JSON]

**Output Format:** [JSON object with success, content, and metadata fields; content contains OCR text and a visual summary in plain text or Markdown.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Requires NEXN2_API_KEY; image analysis results may be cached as JSON files for up to 7 days by default.]

## Skill Version(s):

1.0.4 (source: server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

cache/2a0206456252d9926270d09e5fea3640.json

{"content": "【OCR文字提取】\n\n```text\nopen\n\n弱酸性配方\n添加酒精\n\n生产批号:20260530 13:57:03\n限用日期:20280529 A060530A\n\n\n象小家™EDI纯水湿巾\n7道水净化工艺｜无刺激｜无酒精｜无荧光剂\n\n小象超市 自有品牌\n\n○产品名称:象小家™EDI纯水湿巾○净含量:90抽×1包○规格:150mm×200mm○主要成分:水刺无纺布,EDI纯水○生产批号及限期使用日期:见包装○保质期:两年○贮存条件:置于阴凉干燥处常温保存,避免阳光直射○使用方法:将盖子打开,揭开贴纸,抽出使用。建议使用完盖好贴纸和盖子,避免水分流失。○卫生标准:GB 15979○执行标准:GB/T 27728.1○委托商:北京象鲜科技有限公司○地址:北京市朝阳区小营北路15号院1号楼3层○联系方式:010-10107777○受委托商:浙江优全护理用品科技股份有限公司○地址:浙江省湖州市长兴县太湖街道陆汇路68号(代码:A)○卫生许可证号:浙卫消证字(2016)第002\n```\n\n【画面内容总结】\n\n1. 核心主题：这是一包“象小家™EDI纯水湿巾”的包装实拍，用于日常清洁/擦拭，主打纯水、温和、无酒精等卖点。\n\n2. 元素与布局：图片主体为一包浅蓝色湿巾，放置在浅色木纹桌面上；包装上方是翻盖开口，可见“open”字样及“弱酸性配方”等宣传语；包装中部为产品名称和核心卖点；包装下方密集排列产品参数、成分、使用方法、执行标准、委托商和受委托商等信息。背景中有纸巾盒、杯子、绿色包装等物品，但处于虚化状态。\n\n3. 关键信息提炼：\n   - 产品名称：象小家™EDI纯水湿巾。\n   - 核心卖点：7道水净化工艺、无刺激、无酒精、无荧光剂。\n   - 规格信息：90抽×1包，规格为150mm×200mm。\n   - 主要成分：水刺无纺布、EDI纯水。\n   - 日期信息：生产批号为20260530 13:57:03，限用日期为20280529。", "cached_at": "2026-07-09T15:51:51.620772+00:00", "expires_at": "2026-07-16T15:51:51.620772+00:00", "model": "nex-agi/Nex-N2-Pro", "tokens_used": 6270}

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.