classify-structured
GitHub基于gliner2-base-v1模型的多维度结构化文本分类技能。通过JSON Schema定义分类轴及标签，支持同时按情感、主题等多维度进行分类，输出指定格式的JSON结果。
触发场景
安装
npx skills add zerogpu/zerogpu-router --skill classify-structured -g -y
SKILL.md
Frontmatter
{
"name": "classify-structured",
"metadata": {
"openclaw": {
"install": [
{
"bins": [
"zerogpu"
],
"kind": "node",
"package": "zerogpu-cli"
}
],
"requires": {
"bins": [
"zerogpu"
]
}
}
},
"description": "Multi-axis classification using a JSON schema mapping categories to allowed labels (gliner2-base-v1). Use when the user wants to classify text along several dimensions at once, e.g. \"classify by sentiment and topic\" with explicit label sets per axis.",
"allowed-tools": "Bash(zerogpu classify_structured*)",
"argument-hint": "<text> -s '<json schema>'"
}
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 schema-driven classification:
zerogpu classify_structured $ARGUMENTS
Quoting (required, to survive shell parsing of arbitrary user text): format $ARGUMENTS with the source text wrapped via heredoc command substitution, then flags after. Inside the heredoc, paste the user's text verbatim — do not escape:
"$(cat <<'ZGPU_T'
<the source text, verbatim, multi-line and special chars all OK>
ZGPU_T
)" -s '{"sentiment":["positive","negative","neutral"],"topic":["support","billing","product"]}'
Schema is a single-quoted JSON object mapping each axis to its allowed labels. Output is a JSON object with one chosen label per category.
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.
版本历史
-
cee9321
当前 2026-08-02 21:15
更新依赖库并修复安全问题
- 7b9b503 2026-07-24 11:48
