chat-liquid
GitHub调用Liquid AI边缘模型提供快速低成本的单轮对话回复，适用于无需上下文或代码生成的简单查询。通过exec工具执行命令并透传结果，优先追求速度与成本效益。
Trigger Scenarios
Install
npx skills add zerogpu/zerogpu-router --skill chat-liquid -g -y
SKILL.md
Frontmatter
{
"name": "chat-liquid",
"metadata": {
"openclaw": {
"install": [
{
"bins": [
"zerogpu"
],
"kind": "node",
"package": "zerogpu-cli"
}
],
"requires": {
"bins": [
"zerogpu"
]
}
}
},
"description": "Fastest, cheapest chat reply via Liquid AI's edge model (LFM2.5-1.2B-Instruct). Use when the user wants a quick, single-turn answer that does not need host-level reasoning, prior conversation context, or code generation, and explicitly favors speed or cost over quality. Optional system instructions via -i.",
"allowed-tools": "Bash(zerogpu chat_completions *)",
"argument-hint": "<text> [-i <instructions>]"
}
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 Liquid AI edge 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-Instruct <<'ZGPU_END_OF_INPUT'
<the user's prompt, verbatim>
ZGPU_END_OF_INPUT
If the user supplied system instructions, add -i '<instructions>' after the model flag, writing any ' inside them as '\''.
Output is the assistant's answer as plain text. Relay it as-is, without rewriting or expanding it. At 1.2B parameters this model is terse and occasionally mechanical; that is expected. If the answer is too weak for the task, the chat skill runs the same prompt on gpt-oss-120b.
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 08:07
升级至 v4.4.0：改用 zerogpu-cli 3.8.0 的模型无关端点，使插件独立于 CLI 模型变更；将执行指令从 Claude Code !块改为 exec 工具 heredoc 格式。
- cee9321 2026-08-02 21:15
