classify-decisions
GitHub基于 gliner2.5-decide-v1 模型，支持动态标签的分类与决策路由。用于意图识别、工单分流、内容审核及人机协作判断，支持单次调用多任务处理，适合高并发场景。
Trigger Scenarios
Install
npx skills add zerogpu/zerogpu-router --skill classify-decisions -g -y
SKILL.md
Frontmatter
{
"name": "classify-decisions",
"metadata": {
"openclaw": {
"install": [
{
"bins": [
"zerogpu"
],
"kind": "node",
"package": "zerogpu-cli"
}
],
"requires": {
"bins": [
"zerogpu"
]
}
}
},
"description": "Dynamic-label decisions and routing with gliner2.5-decide-v1 (486M) — supply the labels or options at request time to classify intent, route agents and tools, triage support requests, make moderation decisions, and decide when a human handoff is needed. Single-label, multi-label, and several decision heads in one call. Use for high-volume routing and triage — it is the cheapest classifier on the platform and bills nothing on output.",
"allowed-tools": "Bash(zerogpu chat_completions *)",
"argument-hint": "<text> -s '<json labels>'"
}
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 a dynamic-label decision. The user gives the text and the decision heads — each head with its allowed options — as -s '<json>' or in plain words.
Run this with the exec tool, putting the heads in --metadata 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 gliner2.5-decide-v1 --metadata '{"usecase":"decide","labels":{"intent":["payment_issue","refund","account_access","general_question"],"handoff":["yes","no"]}}' <<'ZGPU_END_OF_INPUT'
<the source text, verbatim>
ZGPU_END_OF_INPUT
"usecase":"decide"is required exactly as written; the API rejects the request without it.labelsmaps each decision head to its allowed options, and several heads may be decided in one call. If the user gives heads without options, pick sensible option sets and say which you used.- For plain single- or multi-label classification against a schema,
"usecase":"classification"with aschemaworks too — the same shapeclassify-structureduses. --metadatais single-quoted JSON, so write any'inside an option as'\''.
Output is a JSON object holding the chosen option per decision head.
At $0.004 per 1M input tokens, billing nothing on output, this is the cheapest classifier on the platform — a fifth of classify-structured on input. Prefer classify-structured when you want a schema-shaped classification, and this skill when you are routing or triaging at volume.
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
- 605eceb Current 2026-11-02 19:14
