← 返回 Skills 市场
Model Advisor
作者
MrKangZuBin
· GitHub ↗
· v0.1.0
· MIT-0
308
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install model-advisor
功能描述
模型推荐 + OpenClaw 安全系数分析工具。当用户询问"用哪个模型"、"推荐模型"、"适合什么模型"、"安全系数"、"openclaw 安全"、"根据历史"时触发。功能：(1) 根据历史会话自动分析任务类型并推荐最优的 Claude 模型（auto 模式），(2) 根据用户描述的任务推荐最优模型（recom...
安全使用建议
This skill appears to do what it says — it analyzes your OpenClaw config and recent session messages to score security and recommend models. However, it reads private files in ~/.openclaw (session messages and openclaw.json), which may contain sensitive data (conversation content, API keys or auth config). Before running or installing: (1) review the full scripts/advisor.js to confirm there are no network calls or unexpected behavior (the visible portion shows none, but the file was truncated in the listing), (2) consider running it in a restricted environment or with a copy of your OpenClaw data if you want to avoid exposing real conversations, and (3) if you do not trust the skill author, do not execute the script as your main user — inspect it line-by-line or sandbox it. If you need, ask for a full listing of advisor.js to verify there are no outbound network requests or telemetry.
功能分析
Type: OpenClaw Skill
Name: model-advisor
Version: 0.1.0
The skill performs broad read operations on sensitive local files, including the main OpenClaw configuration (openclaw.json) and the entire directory of session history logs (.jsonl), to calculate security scores and analyze user task patterns. While these capabilities are plausibly required for the stated purpose in SKILL.md and scripts/advisor.js, the access to private conversation history and gateway settings constitutes a high-risk behavior. The script does not contain evidence of data exfiltration or remote code execution, but it provides a mechanism for the agent to ingest and potentially expose sensitive historical data.
能力评估
Purpose & Capability
The skill's name/description claim recommending models and computing an OpenClaw security score — the code reads ~/.openclaw/openclaw.json, models.json, and recent session files to produce recommendations and a security report. Those file reads are necessary for the stated features and therefore proportionate.
Instruction Scope
SKILL.md and advisor.js explicitly instruct and implement reading recent session messages (~5 sessions) and openclaw.json to analyze task types and compute security metrics. That is within the stated purpose, but it means the skill will access and analyze private user messages and local gateway configuration (which may contain sensitive fields). There are no instructions to send data to remote endpoints in the visible code.
Install Mechanism
No install spec is provided (instruction-only skill) and the included script is intended to be executed locally with node. No remote downloads or extract/install steps are present, so nothing extra will be written to disk beyond running the packaged script.
Credentials
The skill requests no environment variables, no credentials, and no config paths beyond those under the user's ~/.openclaw directory. The requested access (openclaw.json, models.json, sessions directory) is appropriate for its functionality.
Persistence & Privilege
always is false and the skill does not request permanent presence or modify other skills. It only reads local files and prints recommendations — no elevated platform privileges are requested.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install model-advisor - 安装完成后，直接呼叫该 Skill 的名称或使用
/model-advisor触发 - 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
v0.1.0
Initial release of model-advisor skill.
- Automatically recommends the best Claude model based on recent user task history or specified task description.
- Analyzes OpenClaw security settings from local configuration and outputs a security score (0-100) with improvement suggestions.
- Supports four modes: history-based recommendation, description-based recommendation, security score, and full report.
- Provides reference tables for model selection and security evaluation dimensions.
元数据
常见问题
Model Advisor 是什么？
模型推荐 + OpenClaw 安全系数分析工具。当用户询问"用哪个模型"、"推荐模型"、"适合什么模型"、"安全系数"、"openclaw 安全"、"根据历史"时触发。功能：(1) 根据历史会话自动分析任务类型并推荐最优的 Claude 模型（auto 模式），(2) 根据用户描述的任务推荐最优模型（recom... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 308 次。
如何安装 Model Advisor？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install model-advisor」即可一键安装，无需额外配置。
Model Advisor 是免费的吗？
是的，Model Advisor 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Model Advisor 支持哪些平台？
Model Advisor 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 Model Advisor？
由 MrKangZuBin（@mrkangzubin）开发并维护，当前版本 v0.1.0。
推荐 Skills