classify-iab
GitHub调用ZeroGPU API对文本进行IAB内容/受众分类，返回带置信度的JSON标签。适用于需要标准化广告或内容主题分类的场景。
Trigger Scenarios
Install
npx skills add zerogpu/zerogpu-router --skill classify-iab -g -y
SKILL.md
Frontmatter
{
"name": "classify-iab",
"metadata": {
"openclaw": {
"install": [
{
"bins": [
"zerogpu"
],
"kind": "node",
"package": "zerogpu-cli"
}
],
"requires": {
"bins": [
"zerogpu"
]
}
}
},
"description": "Classify text against the IAB content\/audience taxonomy. Use when the user asks for IAB categories, ad-taxonomy labels, or \"what topic is this article about\" against a standard taxonomy.",
"allowed-tools": "Bash(zerogpu chat_completions *)",
"argument-hint": "<text>"
}
Sends your input to ZeroGPU's hosted API for inference — this is not local processing. Don't pass secrets, credentials, or regulated data you aren't cleared to share with a third party. See the plugin README's "Data & privacy" section.
Run IAB classification. Run this with the exec tool, pasting the source text into the heredoc verbatim — no escaping or quoting required (the quoted heredoc handles every shell metacharacter, newline, quote, and paren safely):
zerogpu chat_completions -m zlm-v1-iab-classify-edge <<'ZGPU_END_OF_INPUT'
<the source text, verbatim>
ZGPU_END_OF_INPUT
Output is a JSON object with audience and content (iab_1_0 and iab_2_2) category lists, each with confidence scores.
Savings note: only if the command output literally contains a line starting with 💰 ZeroGPU savings, append that exact line, unchanged, as the last line of your reply. If no such line is present, say nothing about savings and do not mention or suggest the cost-savings skill — this note is intentionally occasional, not shown every time.
Version History
-
4e1b070
Current 2026-09-22 08:08
v4.3.1至v4.4.0：统一使用zerogpu chat_completions命令并指定模型，改为独立于CLI模型变化的通用端点；指令格式从!块改为exec工具heredoc，确保参数安全传递。
-
cee9321
2026-08-02 21:15
更新依赖及安全修复
- 7b9b503 2026-07-24 11:48
