classify-iab
GitHub基于IAB内容/受众分类法对文本进行分类。适用于用户请求IAB类别、广告标签或文章主题归类等场景，返回包含置信度的JSON格式结果。
Trigger Scenarios
Install
npx skills add zerogpu/zerogpu-router --skill classify-iab -g -y
SKILL.md
Frontmatter
{
"name": "classify-iab",
"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>"
}
Run IAB classification. $ARGUMENTS is the raw source text — pass it verbatim, no escaping or quoting required (the heredoc below handles every shell metacharacter, newline, quote, and paren safely):
zerogpu chat_completions -m zlm-v1-iab-classify-edge <<'ZGPU_END_OF_INPUT'
$ARGUMENTS
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 /zerogpu-router:cost-savings — this note is intentionally occasional, not shown every time.
Version History
-
4e1b070
Current 2026-09-22 08:06
版本升级至 v2.3.0，将模型调用方式改为通用的 chat_completions 端点，使插件独立于特定 CLI 命令变化，并依赖 zerogpu-cli >= 3.8.0。
- 7b9b503 2026-07-24 11:47
