← 返回 Skills 市场
269
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install glm-grounding
功能描述
Use GLM-4.7V's multimodal grounding capability to detect and locate objects/text in images. Activate when user asks to find, locate, detect, or ground specif...
使用说明 (SKILL.md)
Grounding - 多模态目标定位
利用 GLM-4.7V 的 grounding 能力,在图片中定位目标对象或文字,输出带标注框的结果图。
工作流程
用户输入(图片 + prompt)
│
▼
HttpInterface() → 调用模型 API → 得到 response 文本
│
▼
parse_bboxes_from_response() → 从回复中解析出坐标框列表
│
▼
visualize_boxes(renormalize=True) → 反归一化 + 画框 → 保存结果图
Step 1: 调用模型获取坐标
使用 HttpInterface 调用模型 API:
import os
os.environ['NO_PROXY'] = '\x3Cmodel-host>' # 跳过代理
os.environ['no_proxy'] = '\x3Cmodel-host>'
from interface_http import HttpInterface
url = 'http://\x3Chost>:\x3Cport>/v1/chat/completions'
prompt = '''请在这张图中找到所有"{target}",并以 [xmin, ymin, xmax, ymax] 格式输出每个目标的边界框坐标,坐标值为 0-1000 的归一化整数。每个目标一行,格式如下:
目标名称: [xmin, ymin, xmax, ymax]'''
response = HttpInterface(url, prompt, images=[image_path], no_think=True)
# 返回: "目标名称: [xmin, ymin, xmax, ymax]"
注意: 调用前需设置 NO_PROXY 环境变量跳过代理,否则内网请求会被代理拦截。
Step 2: 解析坐标框
from utils_boxes import parse_bboxes_from_response
boxes = parse_bboxes_from_response(response)
# 返回: [[x1, y1, x2, y2], ...] (0-1000 归一化)
parse_bboxes_from_response 会自动:
- 从回复尾部向前检查截断,拓展 context window
- 遍历所有括号风格(
[],{},(),\x3C>,\x3Cbbox>)提取坐标 - 扁平化嵌套列表,返回一维 box 列表
Step 3: 画框可视化
from utils_boxes import visualize_boxes
visualize_boxes(
img_path=image_path,
boxes=boxes, # parse_bboxes_from_response 的输出
labels=['label1', 'label2'], # 每个框的标签
renormalize=True, # 自动将 0-1000 归一化转为像素坐标
save_path='output.jpg',
colors=['red', 'blue'], # 可选
thickness=[2, 3], # 可选
)
renormalize=True 时,内部自动调用 reverse_normalize_box:pixel = coord * img_dimension / 1000
完整示例
import os
os.environ['NO_PROXY'] = '172.20.112.202'
os.environ['no_proxy'] = '172.20.112.202'
from interface_http import HttpInterface
from utils_boxes import parse_bboxes_from_response, visualize_boxes
url = 'http://172.20.112.202:5002/v1/chat/completions'
img = '/path/to/image.jpg'
# 1. 调用模型
response = HttpInterface(
url,
'请在这张图中找到"红色圣诞帽",以 [xmin, ymin, xmax, ymax] 格式输出坐标(0-1000归一化)',
images=[img],
no_think=True,
)
# 2. 解析坐标
boxes = parse_bboxes_from_response(response)
# 3. 画框
visualize_boxes(img_path=img, boxes=boxes, labels=['圣诞帽'], renormalize=True, save_path='out.jpg')
工具函数速查
| 函数 | 作用 |
|---|---|
HttpInterface(url, prompt, images, no_think) |
调用模型 API,返回文本回复 |
parse_bboxes_from_response(text) |
从模型回复中提取所有坐标框列表 |
find_boxes_all(text, flat=True) |
提取文本中所有括号风格的坐标框 |
reverse_normalize_box(box, w, h) |
0-1000 归一化 → 像素坐标 |
visualize_boxes(..., renormalize=True) |
画框 + 自动反归一化 |
注意事项
- 模型 API 地址配置在
/root/.openclaw/agents/main/agent/models.json - 调用内网模型时必须设置
NO_PROXY环境变量 no_think=True可关闭模型思考模式,加快响应
安全使用建议
This skill appears to do what it claims (call a grounding model, parse boxes, draw them), but it contains surprising instructions: it tells the runtime to set NO_PROXY/no_proxy (bypassing proxies) and references an agent config file (/root/.openclaw/agents/main/agent/models.json). Before enabling it, consider: do you trust the model host it will call? Do you want code that bypasses your organization's proxy/logging? Are the helper modules (interface_http, utils_boxes) present and from a trustworthy source? If you need to use this, prefer running it in a controlled environment or ask the author to remove proxy-bypass steps and to explicitly declare dependencies and any config file reads. If you have security policies about network egress or exposing agent internals, treat this skill with caution.
功能分析
Type: OpenClaw Skill
Name: glm-grounding
Version: 1.0.0
The skill bundle provides legitimate functionality for object grounding and image annotation using the GLM-4.7V model. The instructions in SKILL.md guide the agent through calling an internal API (using a private IP 172.20.112.202), parsing coordinates, and visualizing results, all of which are consistent with the stated purpose. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
能力评估
Purpose & Capability
The skill's name and description (multimodal grounding) align with the instructions to call a grounding model, parse bounding boxes, and visualize them. However, the skill assumes the presence of helper modules (interface_http, utils_boxes) and a local model HTTP endpoint; these dependencies are not declared in metadata and no code is bundled, which is an implementation gap (missing declared dependencies).
Instruction Scope
SKILL.md instructs setting NO_PROXY/no_proxy to a model host and points to an agent config path (/root/.openclaw/agents/main/agent/models.json). Asking the agent to change environment networking behavior (bypass proxy) and to rely on an agent-specific config file expands scope beyond simply 'call model and draw boxes' and could be used to bypass network controls or access agent internals.
Install Mechanism
There is no install spec and no code files — lowest-risk delivery. The skill is instruction-only, so nothing is written to disk by installation.
Credentials
The metadata declares no required env vars, yet the instructions explicitly set NO_PROXY/no_proxy at runtime. Modifying proxy-related environment variables is unexpected for a grounding helper and may affect network routing/monitoring. Also the instruction expects access to a local model HTTP endpoint (host:port) without declaring or validating credentials or access scope.
Persistence & Privilege
always is false and the skill is user-invocable (standard). However, the SKILL.md refers to a specific agent config file path which implies knowledge of or reliance on agent internals; the skill does not request persistent presence but it does assume read access to agent configuration, which is noteworthy.
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 glm-grounding - 安装完成后,直接呼叫该 Skill 的名称或使用
/glm-grounding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 the GLM multimodal grounding skill.
- Supports detection and localization of objects or text in images using GLM-4.7V’s capabilities.
- Skill automatically activates on relevant keywords or phrases in both English and Chinese.
- Provides simple API workflow: call model, parse bounding boxes from response, and visualize results with annotation.
- Includes utility functions for model interaction, response parsing, bounding box normalization, and visualization.
元数据
常见问题
glm-grounding 是什么?
Use GLM-4.7V's multimodal grounding capability to detect and locate objects/text in images. Activate when user asks to find, locate, detect, or ground specif... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 269 次。
如何安装 glm-grounding?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install glm-grounding」即可一键安装,无需额外配置。
glm-grounding 是免费的吗?
是的,glm-grounding 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
glm-grounding 支持哪些平台?
glm-grounding 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 glm-grounding?
由 Ji Qi(@qijimrc)开发并维护,当前版本 v1.0.0。
推荐 Skills