← 返回 Skills 市场
Model Audit Pro
作者
aiwithabidi
· GitHub ↗
· v1.0.0
567
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install model-audit-pro
功能描述
Monthly LLM stack audit — compare your current models against latest benchmarks and pricing from OpenRouter. Identifies potential savings, upgrades, and bett...
安全使用建议
This skill appears to do what it claims, but take standard precautions before running code from unknown publishers: (1) Only provide OPENROUTER_API_KEY if you trust the service and understand the API key's scope/billing implications. (2) Inspect openclaw.json in the paths the script checks — it may contain models or other config; ensure it contains no sensitive secrets you don't want the script to read. (3) Run the script in a non-root, network-restricted environment if you're cautious (the script will attempt outbound HTTP to openrouter.ai). (4) Because the full script is included, you can review it yourself (or run with --json) to confirm output before integrating. If you need higher assurance, verify the publisher (homepage, GitHub) and review recent updates or community feedback.
功能分析
Type: OpenClaw Skill
Name: model-audit-pro
Version: 1.0.0
The skill is designed to audit LLM models against OpenRouter benchmarks. The `SKILL.md` instructions are clear and do not contain any prompt injection attempts. The `scripts/model_audit.py` script fetches model data from `openrouter.ai` using the `OPENROUTER_API_KEY` environment variable. It also attempts to read `openclaw.json` from standard OpenClaw configuration paths (`/root/.openclaw/openclaw.json`, `/home/node/.openclaw/openclaw.json`, `~/.openclaw/openclaw.json`) to discover configured models. While reading configuration files from outside the skill's immediate directory can be a sensitive operation, in this case, it is directly aligned with the skill's stated 'audit' purpose and only extracts model IDs, not sensitive credentials or arbitrary data. There is no evidence of malicious intent, data exfiltration, or unauthorized execution.
能力评估
Purpose & Capability
Name/description: audit LLM stack vs OpenRouter pricing. Declared requirement: OPENROUTER_API_KEY. The included script calls OpenRouter's models API, parses pricing, classifies models, and reads local openclaw.json to discover configured models — all coherent with the stated purpose.
Instruction Scope
SKILL.md instructs running scripts/model_audit.py. The script performs expected actions: HTTP GET to https://openrouter.ai/api/v1/models, reads openclaw.json from a small set of plausible locations (~/.openclaw and common container/root paths), and prints or emits JSON results. It does not transmit data to any unexpected third-party endpoints nor attempt arbitrary shell execution.
Install Mechanism
No install spec — instruction-only with a bundled Python script. Nothing is downloaded or installed automatically; the script runs with the environment and Python already present.
Credentials
Only required environment variable is OPENROUTER_API_KEY (declared as primary credential). No other secrets or unrelated credentials are requested. The script reads no other environment variables.
Persistence & Privilege
Skill is not always-enabled and does not modify other skills or system-wide config. It only reads local config files and makes outbound requests; it does not write persistent data or claim elevated privileges.
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-audit-pro - 安装完成后，直接呼叫该 Skill 的名称或使用
/model-audit-pro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
v1.0.0
- Initial release of the Model Audit skill for OpenClaw agents.
- Audits your LLM stack by fetching live model pricing from OpenRouter.
- Analyzes your configured models, categorizes them, and recommends alternatives by reasoning, code, fast, cheap, and vision.
- Calculates potential monthly savings and suggests cost optimizations or upgrades.
- Provides multiple output modes including JSON, category leaders, and direct model comparison.
- Requires an OPENROUTER_API_KEY to operate.
元数据
常见问题
Model Audit Pro 是什么？
Monthly LLM stack audit — compare your current models against latest benchmarks and pricing from OpenRouter. Identifies potential savings, upgrades, and bett... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 567 次。
如何安装 Model Audit Pro？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install model-audit-pro」即可一键安装，无需额外配置。
Model Audit Pro 是免费的吗？
是的，Model Audit Pro 完全免费（开源免费），可自由下载、安装和使用。
Model Audit Pro 支持哪些平台？
Model Audit Pro 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 Audit Pro？
由 aiwithabidi（@aiwithabidi）开发并维护，当前版本 v1.0.0。
推荐 Skills