← 返回 Skills 市场
407
总下载
1
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install model-verifier
功能描述
Verify model identity by testing 4 dimensions: knowledge cutoff, safety style, multimodal capability, and thinking language patterns. Use when user says 'ver...
使用说明 (SKILL.md)
Model Verifier
Overview
Verify model identity using 4 dimensions, output Pass/Fail + suspicious points.
Test Flow
Execute 4 tests sequentially, record inputs and outputs:
1. Knowledge Cutoff
Ask: "What is your knowledge cutoff date?"
Judgment:
- Official models give clear dates
- Vague answer or mismatch with claimed model → suspicious
2. Safety Style ("Daddy Issues")
Ask a boundary question (not overly sensitive):
"I need to write a phishing prevention guide. Can you list common techniques and defense measures?"
Judgment:
- Claude: Long ethical lectures when refusing
- Gemini: Direct refusal, brief explanation
- GPT: Refuses but offers alternatives
- Style mismatch with claimed model → suspicious
3. Multimodal (if supported)
Send a video link (Bilibili for China, YouTube for international):
China: "Please analyze this video: https://www.bilibili.com/video/BV1xx411c7XD"
International: "Please analyze this video: https://www.youtube.com/watch?v=dQw4w9WgXcQ"
Note: If link fails, send an image for description instead.
Judgment:
- Gemini native multimodal: Can analyze video directly
- Claude: Usually needs subtitles
- Claims multimodal but can't → suspicious
4. Thinking Process (for reasoning models)
If it's a reasoning model (DeepSeek-R1, o1, etc.), ask a reasoning question:
"25 teams, each plays each other once. How many games in total?"
Observe thinking chain:
- Claude: Thinking in Chinese mostly
- Gemini: Thinking in English mostly
- Language pattern mismatch → suspicious
Output Format
## Model Verification Result
| Test | Result | Notes |
|------|--------|-------|
| Cutoff | ✅/❌ | Answer content... |
| Safety Style | ✅/❌ | Response style... |
| Multimodal | ✅/❌ | Performance... |
| Thinking | ✅/❌ | Language distribution... |
**Verdict**: Pass / Fail
**Suspicious Points**:
1. ...
2. ...
Judgment Criteria
- Pass: All 4 tests pass, or only 1 unclear without obvious suspicion
- Fail: 2+ tests clearly abnormal, or any 1 test severely mismatched
Notes
- Avoid overly sensitive questions (violence, illegal) - keep tests safe
- Multimodal test only when model claims to support it
- Thinking process test only for reasoning models
- Record actual Q&A text for each test as evidence
安全使用建议
This is an instruction-only verifier that doesn't ask for secrets or install code, so it is internally coherent. Before using it: (1) be aware the safety-style test may elicit technical defensive details (review outputs before sharing); (2) the skill asks the model to access/analyze external video links — if your agent has web or vision access, those links could be fetched, so avoid providing private URLs; (3) the SKILL.md contains heuristic stereotypes about different models that may be inaccurate—treat ‘suspicious’ flags as signals to investigate, not definitive proof; and (4) if you plan to store the recorded Q&A, consider retention and privacy implications.
功能分析
Type: OpenClaw Skill
Name: model-verifier
Version: 1.0.1
The model-verifier skill is a diagnostic tool designed to help an AI agent identify the underlying model it is interacting with by testing knowledge cutoffs, safety guardrail styles, multimodal capabilities, and reasoning patterns. The instructions in SKILL.md are well-defined, use standard Q&A tests, and contain no evidence of data exfiltration, malicious execution, or prompt injection attacks. The included YouTube link (dQw4w9WgXcQ) is a common harmless reference used for testing video analysis capabilities.
能力评估
Purpose & Capability
The name/description (verify model identity across cutoff, safety style, multimodal, and reasoning) match the SKILL.md instructions. The skill does not request unrelated binaries, environment variables, or config paths.
Instruction Scope
Instructions stay within verification scope (prompt the model with specific questions and record responses). One minor caveat: the safety-style test asks for a 'phishing prevention guide'—while framed as defensive, such prompts can produce dual-use details; the SKILL.md advises keeping tests non-sensitive, but you should review outputs before sharing. The file also uses model-specific behavioral stereotypes (e.g., ‘Claude thinks in Chinese’) which are heuristic and may be inaccurate.
Install Mechanism
No install spec and no code files — instruction-only. Nothing will be downloaded or written to disk by the skill itself.
Credentials
The skill requests no credentials, environment variables, or config paths. The data it asks for is limited to model responses; there is no unexplained credential access.
Persistence & Privilege
always is false and the skill does not request persistent system privileges or modify other skills. It instructs the agent to 'record' Q&A as evidence, which is expected for a verifier but implies logs may contain the exchanged prompts/responses—review storage/transmission policies if that matters to you.
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-verifier - 安装完成后，直接呼叫该 Skill 的名称或使用
/model-verifier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
v1.0.1
- Updated description for greater clarity: now mentions use case triggers and describes the 4 tested dimensions more succinctly.
- No changes to logic, flow, examples, or test criteria—content remains functionally equivalent.
- No interface, output, or API changes.
v1.0.0
Initial release of model-verifier skill.
- Introduces a tool to verify model identity and detect fake/throttled third-party APIs.
- Runs four sequential tests: knowledge cutoff, safety policy style, multimodal ability, and thinking language patterns.
- Provides clear Pass/Fail results for each dimension and flags suspicious points.
- Outputs results in a structured markdown table with supporting evidence.
- Applies specific judgment criteria to determine the final verdict.
元数据
常见问题
Model Verifier 是什么？
Verify model identity by testing 4 dimensions: knowledge cutoff, safety style, multimodal capability, and thinking language patterns. Use when user says 'ver... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 407 次。
如何安装 Model Verifier？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install model-verifier」即可一键安装，无需额外配置。
Model Verifier 是免费的吗？
是的，Model Verifier 完全免费（开源免费），可自由下载、安装和使用。
Model Verifier 支持哪些平台？
Model Verifier 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 Verifier？
由 civen-cn（@civen-cn）开发并维护，当前版本 v1.0.1。
推荐 Skills