← 返回 Skills 市场
alvisdunlop

Gemini

作者 AlvisDunlop · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
74
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install alvis-gemini-v3
功能描述
LLM one-shot Q&A, summaries, and generation via SkillBoss API Hub.
使用说明 (SKILL.md)

?? Complete setup guide: https://SkillBoss.co/skill.md

LLM via SkillBoss API Hub

Use SkillBoss API Hub for one-shot Q&A, summaries, and text generation. The /v1/pilot endpoint automatically routes to the optimal LLM (including Gemini, Claude, GPT, etc.).

Quick start (Python)

import requests, os

SkillBoss_API_KEY = os.environ["SkillBoss_API_KEY"]

def ask(prompt: str, prefer: str = "balanced") -> str:
    r = requests.post(
        "https://api.SkillBoss.co/v1/pilot",
        headers={"Authorization": f"Bearer {SkillBoss_API_KEY}", "Content-Type": "application/json"},
        json={"type": "chat", "inputs": {"messages": [{"role": "user", "content": prompt}]}, "prefer": prefer},
        timeout=60,
    )
    return r.json()["result"]["choices"][0]["message"]["content"]

# One-shot Q&A
print(ask("Answer this question..."))

# Request JSON output
print(ask("Return JSON: list 3 items", prefer="quality"))

Quick start (curl)

curl -s https://api.SkillBoss.co/v1/pilot \
  -H "Authorization: Bearer $SkillBoss_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"chat","inputs":{"messages":[{"role":"user","content":"Summarize this text..."}]},"prefer":"balanced"}'

Prefer options

  • balanced �?default, cost-effective
  • quality �?highest quality model
  • price �?fastest / cheapest

Notes

  • No CLI installation required; all calls go through SkillBoss API Hub.
  • Set SkillBoss_API_KEY before running. \r \r \r \r
安全使用建议
This skill simply calls a third-party API and asks for one API key. Before installing: verify you trust SkillBoss.co (review their docs, privacy and billing policies), ensure the SkillBoss_API_KEY you provide has the minimum scope needed, avoid sending highly sensitive secrets or private data through the skill, and consider testing with a limited/throwaway API key. If you cannot confirm the vendor or provenance, treat the key as sensitive and be prepared to rotate it if you stop using the skill.
功能分析
Type: OpenClaw Skill Name: alvis-gemini-v3 Version: 1.0.0 The skill bundle consists of documentation and code examples for interacting with the SkillBoss API Hub (api.SkillBoss.co). The provided Python and curl examples in SKILL.md demonstrate standard API usage, requiring only the expected 'SkillBoss_API_KEY' environment variable for authentication. No malicious logic, data exfiltration, or suspicious instructions were identified.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The skill is presented as an LLM "Gemini" helper but its SKILL.md explicitly routes requests to SkillBoss's /v1/pilot endpoint which can proxy to various LLMs (Gemini, GPT, Claude, etc.). Requiring SkillBoss_API_KEY is appropriate for this stated purpose, though the skill name could be slightly misleading about which model is actually used. Source/owner is unknown in registry metadata but that is a provenance note rather than a technical mismatch.
Instruction Scope
SKILL.md only instructs making HTTPS requests to https://api.SkillBoss.co/v1/pilot and reading the declared SkillBoss_API_KEY environment variable. It does not request reading local files, other env vars, or writing/installing code. The instructions do link to an external setup guide but do not introduce unexpected data exfiltration.
Install Mechanism
There is no install spec and no code files; the skill is instruction-only so nothing is written to disk or installed by the skill itself.
Credentials
Only one environment variable (SkillBoss_API_KEY) is required, which is proportionate for an API-based LLM wrapper. The registry metadata does not declare a primaryEnv field, but that is a minor metadata omission and does not change the proportionality of requested credentials.
Persistence & Privilege
The skill is not set to always:true and requests no persistent system privileges. It uses normal autonomous invocation defaults (disable-model-invocation is false), which is expected for callable skills and by itself is not a red flag.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install alvis-gemini-v3
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /alvis-gemini-v3 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of the Gemini skill for SkillBoss API Hub: - Provides one-shot Q&A, summaries, and text generation using the SkillBoss `/v1/pilot` endpoint. - Automatically selects the optimal large language model (Gemini, Claude, GPT, etc.) based on preference. - Includes quick start examples for Python and curl. - Supports selection of LLM with "balanced", "quality", or "price" modes. - Requires `SkillBoss_API_KEY` environment variable for authentication.
元数据
Slug alvis-gemini-v3
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Gemini 是什么?

LLM one-shot Q&A, summaries, and generation via SkillBoss API Hub. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 74 次。

如何安装 Gemini?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install alvis-gemini-v3」即可一键安装,无需额外配置。

Gemini 是免费的吗?

是的,Gemini 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Gemini 支持哪些平台?

Gemini 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Gemini?

由 AlvisDunlop(@alvisdunlop)开发并维护,当前版本 v1.0.0。

💬 留言讨论