OpenClaw Model Card

该 Skill 通过 Python 脚本读取指定路径的 openclaw.json，输出 OpenClaw 已配置模型清单，检查默认/回退链、别名冲突和可疑 contextWindow，并可用 Node 脚本将内容渲染为模型卡片图片。

热度 59.98

最近更新 2026-05-17 13:18:00

分类：数据依赖：代码执行 / 读写文件应用场景：报告撰写 / 数据处理 / 图像生成

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add openclaw-model-card

Metadata

name: openclaw-model-card
description: Generate OpenClaw model inventory and model-card images from openclaw.json. Use when asked to list all configured models, verify default/fallback chains, or render/share a visual model card screenshot.

Use this skill to output OpenClaw model configuration in a consistent way.

Run text output:

python3 skills/openclaw-model-card/scripts/show-model-config.py --config /path/to/openclaw.json

If user wants a screenshot/image card, render image:

python3 skills/openclaw-model-card/scripts/show-model-config.py --config /path/to/openclaw.json --image ./model-card.png

If running in chat surfaces where terminal output is invisible to the user, send the script output via messaging tool instead of paraphrasing.

Do not handcraft model lists when this skill is requested; always use the script output.
Prefer --config explicitly for reproducibility.
Keep sensitive config files out of git; only publish generated, sanitized artifacts.

md2img.js depends on wkhtmltoimage.
The script includes consistency checks (missing model refs, alias conflicts, suspicious contextWindow).