← 返回 Skills 市场
Model Tester
作者
Nando Rossi
· GitHub ↗
· v1.0.0
· MIT-0
376
总下载
0
收藏
3
当前安装
1
版本数
在 OpenClaw 中安装
/install model-tester
功能描述
Test agents or models against predefined test cases to validate model routing, performance, and output quality. Use when: (1) verifying a specific agent or m...
安全使用建议
Before installing or running this skill: (1) ensure the 'openclaw' CLI is installed and accessible (the skill did not declare this dependency in metadata), (2) run it in a safe/sandboxed environment because it tails OpenClaw logs which may contain unrelated or sensitive information from your deployment, (3) verify your OpenClaw config/gateway credentials are appropriate for testing (the script will use whatever local config the CLI has), (4) review and, if desired, edit references/test-cases.json so test prompts contain no sensitive data, and (5) consider running a single case with verbose output to confirm the tool only parses the expected model/token fields before using it on broader logs or CI. If you need higher assurance, ask the skill author to (a) declare 'openclaw' as a required binary in metadata, (b) add an option to limit log scope/time window, and (c) avoid reading unrelated log lines or optionally write raw logs only to a user-specified local file for manual review.
功能分析
Type: OpenClaw Skill
Name: model-tester
Version: 1.0.0
The model-tester skill is a legitimate benchmarking and diagnostic tool designed to verify OpenClaw agent routing and performance. It uses the 'openclaw' CLI to execute predefined test cases from 'references/test-cases.json' and monitors system logs via 'openclaw logs' to extract model usage and token statistics. The Python script 'scripts/model_tester.py' uses standard subprocess handling without shell injection risks, and no evidence of data exfiltration, persistence, or malicious prompt injection was found.
能力评估
Purpose & Capability
The skill's stated purpose (testing agents/models) matches the included code: scripts/model_tester.py runs predefined prompts and checks routing via OpenClaw logs. However, the SKILL metadata declares no required binaries while the code clearly requires the 'openclaw' CLI (used for both 'openclaw logs --follow --json' and 'openclaw agent ...'). This undeclared dependency is an incoherence and should be fixed/verified before install. The code also implicitly requires that the user has a valid OpenClaw configuration (gateway/credentials) available to the 'openclaw' binary.
Instruction Scope
The runtime instructions and the script explicitly tail OpenClaw logs and run 'openclaw agent' subprocesses. The SKILL.md asserts only structured fields are captured and no user data is sent to models, which the script mostly enforces by using fixed test prompts. However, tailing logs with '--follow' collects arbitrary log lines from the OpenClaw runtime and the script inspects those lines with regexes — that can inadvertently match or expose other log content. The tool does not transmit logs externally, but it reads them and includes parsed tokens/model fields in output; if logs contain unexpected sensitive fields, parsing may capture them. The instruction text is otherwise scoped to the testing task and does not ask for additional unrelated files or env vars.
Install Mechanism
There is no install spec (instruction-only plus a script file). That is low-risk in that nothing is downloaded or executed at install time, but the packaged script will execute subprocesses at runtime. No external archives or network installers are used.
Credentials
The skill declares no required environment variables or credentials, which is reasonable. However, it relies on the local 'openclaw' CLI and therefore implicitly on whatever credentials/config the user's OpenClaw installation uses (gateway keys, local config). That implicit access is proportional to the tool's purpose but should be understood by the user: running this script will cause the agent/CLI to execute and may read the user's OpenClaw config.
Persistence & Privilege
The skill does not request persistent presence (always:false) and does not modify other skills or system settings. It runs as a normal, user-invoked tool and does not autonomously enable itself or persist new credentials.
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-tester - 安装完成后，直接呼叫该 Skill 的名称或使用
/model-tester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 model-tester.
- Provides a command-line tool to validate agents or models against predefined test cases.
- Supports testing model routing, performance, and output quality with structured JSON reporting.
- Allows targeting specific agents or models using `--agent`, `--model`, and `--case` parameters.
- Extracts actual model usage, token counts, and runtime from OpenClaw logs for verification.
- Ensures privacy by using only static prompts and structured log fields—no user data involved.
元数据
常见问题
Model Tester 是什么？
Test agents or models against predefined test cases to validate model routing, performance, and output quality. Use when: (1) verifying a specific agent or m... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 376 次。
如何安装 Model Tester？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install model-tester」即可一键安装，无需额外配置。
Model Tester 是免费的吗？
是的，Model Tester 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Model Tester 支持哪些平台？
Model Tester 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 Tester？
由 Nando Rossi（@nandorocker）开发并维护，当前版本 v1.0.0。
推荐 Skills