extract-entities

该 Skill 把用户的待处理文本与自定义实体标签组装成 zerogpu extract_entities 命令，经 Bash 调用命令行工具完成命名实体识别，支持用 -t 设置置信度阈值过滤，且至少需指定一个标签；文本需用 heredoc 形式传入以规避 shell 解析问题。

zerogpu

热度 7.65

最近更新 2026-07-14 04:18:53

分类：效率依赖：代码执行 / 第三方 API应用场景：数据处理

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add extract-entities

Metadata

name: extract-entities
description: Custom-label named-entity recognition via ZeroGPU. Use when the user wants to extract entities with their own labels — people, organizations, locations, products, dates, or any caller-defined entity types — from a passage.
argument-hint: <text> (-l <label>... | --labels a,b,c) [-t <0..1>]
allowed-tools: Bash(zerogpu extract_entities *)

Run custom-label NER:

zerogpu extract_entities $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
)" --labels person,company,date [-t 0.3]

At least one -l <label> (or --labels a,b,c) is required. Optional -t <threshold> filters spans below a confidence (default 0.3, must be in [0, 1]).

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.