chat-thinking
GitHub调用 ZeroGPU API 执行 LFM2.5-1.2B-Thinking 推理模型，展示思维链及回答。适用于需要逐步推理的逻辑、数学或文字问题。
触发场景
安装
npx skills add zerogpu/zerogpu-router --skill chat-thinking -g -y
SKILL.md
Frontmatter
{
"name": "chat-thinking",
"metadata": {
"openclaw": {
"install": [
{
"bins": [
"zerogpu"
],
"kind": "node",
"package": "zerogpu-cli"
}
],
"requires": {
"bins": [
"zerogpu"
]
}
}
},
"description": "Chat with ZeroGPU's Thinking variant (LFM2.5-1.2B-Thinking), which returns visible reasoning alongside the answer. Use when the user wants the model's reasoning shown, or asks a short logic\/math\/word-problem question that benefits from step-by-step output.",
"allowed-tools": "Bash(zerogpu chat_completions *)",
"argument-hint": "<text>"
}
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.
Call the ZeroGPU thinking model. Run this with the exec tool, pasting the user's prompt into the heredoc verbatim — no escaping or quoting required (the quoted heredoc handles every shell metacharacter, newline, quote, and paren safely):
zerogpu chat_completions -m LFM2.5-1.2B-Thinking --raw <<'ZGPU_END_OF_INPUT'
<the user's prompt, verbatim>
ZGPU_END_OF_INPUT
Output is the full Chat Completions response as JSON, because the reasoning is a separate field there. Show the model's reasoning first — choices[0].message.reasoning, or reasoning_content if that is the field present — then its answer from choices[0].message.content. If there is no separate reasoning field, the content carries the reasoning inline; show it as-is. Do not print the rest of the JSON.
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
-
4e1b070
当前 2026-09-22 08:07
升级至v4.4.0，改用zerogpu-cli的模型无关端点命令，使插件独立于CLI模型变更，不再依赖$ARGUMENTS替换。
-
cee9321
2026-08-02 21:15
更新依赖及安全修复
- 7b9b503 2026-07-24 11:48
