classify-zero-shot

Agent Skills › zerogpu/zerogpu-router › classify-zero-shot

classify-zero-shot

GitHub

调用ZeroGPU API进行零样本文本分类，用户自定义标签集。适用于情感分析、内容打标等场景，需确保数据隐私合规。

agents/openclaw/plugin/skills/classify-zero-shot/SKILL.md zerogpu/zerogpu-router

Trigger Scenarios

用户要求对文本进行分类但提供自定义标签列表需要判断文本属于特定类别如bug/feature/question

Install

npx skills add zerogpu/zerogpu-router --skill classify-zero-shot -g -y

More Options

Non-standard path

npx skills add https://github.com/zerogpu/zerogpu-router/tree/main/agents/openclaw/plugin/skills/classify-zero-shot -g -y

Use without installing

npx skills use zerogpu/zerogpu-router@classify-zero-shot

指定 Agent (Claude Code)

npx skills add zerogpu/zerogpu-router --skill classify-zero-shot -a claude-code -g -y

安装 repo 全部 skill

npx skills add zerogpu/zerogpu-router --all -g -y

预览 repo 内 skill

npx skills add zerogpu/zerogpu-router --list

SKILL.md

Frontmatter

{
    "name": "classify-zero-shot",
    "metadata": {
        "openclaw": {
            "install": [
                {
                    "bins": [
                        "zerogpu"
                    ],
                    "kind": "node",
                    "package": "zerogpu-cli"
                }
            ],
            "requires": {
                "bins": [
                    "zerogpu"
                ]
            }
        }
    },
    "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 chat_completions *)",
    "argument-hint": "<text> (-l <label>... | --labels a,b,c)"
}

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 zero-shot classification. The user gives the text to classify and the candidate labels, as flags (-l bug -l feature, --labels bug,feature) or in plain words.

Run this with the exec tool, filling in the labels and pasting the text into the heredoc verbatim — no escaping, the quoted heredoc handles every shell metacharacter, newline, quote, and paren:

zerogpu chat_completions -m deberta-v3-small -i "[bug, feature, question]" <<'ZGPU_END_OF_INPUT'
<the text to classify, verbatim>
ZGPU_END_OF_INPUT

The labels go in -i as one bracketed, comma-separated list. The model reads them from the system message and rejects a request without one.
At least one label is required. If the user names none, ask which candidate labels to use.
-i is double-quoted, so leave ", $, and backticks out of the labels.

Output is a JSON object mapping each label to its score.

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
v4.4.0更新：改用zerogpu CLI通用端点而非任务专用命令，提升插件独立性；技能指令改为exec工具格式以适配Agent执行。
cee9321 2026-08-02 21:15
更新依赖库并修复安全漏洞
7b9b503 2026-07-24 11:48

Metadata

Files: 0
Version: 4e1b070
Hash: dfeb6e55
Indexed: 2026-07-24 11:48

classify-zero-shot