classify-zero-shot
GitHub对用户提供文本进行零样本分类，支持自定义标签列表。通过heredoc格式安全传递输入文本及--labels参数，可选设置置信度阈值过滤结果，适用于情感分析、内容打标等场景。
Trigger Scenarios
Install
npx skills add zerogpu/zerogpu-router --skill classify-zero-shot -g -y
SKILL.md
Frontmatter
{
"name": "classify-zero-shot",
"description": "Zero-shot classification against a caller-supplied list of candidate labels (deberta-v3-small). Use when the user wants to classify text into a custom set of labels they provide (e.g. \"is this positive, negative, or neutral?\", \"tag this as bug, feature, or question\").",
"allowed-tools": "Bash(zerogpu classify_zero_shot*)",
"argument-hint": "<text> (-l <label>... | --labels a,b,c) [-t <0..1>]"
}
Run zero-shot classification:
zerogpu classify_zero_shot $ARGUMENTS
Quoting (required, to survive shell parsing of arbitrary user text): format $ARGUMENTS with the input text wrapped via heredoc command substitution, then flags after. Inside the heredoc, paste the user's text verbatim — do not escape:
"$(cat <<'ZGPU_T'
<the input text, verbatim, multi-line and special chars all OK>
ZGPU_T
)" --labels a,b,c
At least one label is required — either repeat -l <label> or pass --labels a,b,c. Optional -t <threshold> filters labels below a confidence for multi-label output.
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
- 7b9b503 Current 2026-07-24 11:47
