ccfingerprint 1.0.0 → 1.0.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +38 -39
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -1,22 +1,22 @@
1
1
  # CCFingerprint
2
2
 
3
- AI 模型身份指纹识别工具 - 通过自问自答验证模型真实身份
3
+ 🇨🇳 [中文](README.md) | 🇺🇸 [English](README_EN.md)
4
4
 
5
- AI Model Identity Fingerprinting Tool - Verify model identity through self-Q&A
5
+ AI 模型身份指纹识别工具 - 通过自问自答验证模型真实身份
6
6
 
7
7
  ---
8
8
 
9
- 🌐 **[查看详细介绍 / View Details](https://www.honeymeta.com/#ccfingerprint)**
9
+ 🌐 **[查看详细介绍](https://honeymeta.com/ccfingerprint)**
10
10
 
11
11
  ---
12
12
 
13
- ## 安装 / Installation
13
+ ## 安装
14
14
 
15
15
  ```bash
16
16
  npm install -g ccfingerprint
17
17
  ```
18
18
 
19
- ## 使用 / Usage
19
+ ## 使用
20
20
 
21
21
  ```bash
22
22
  # 中文版 (默认)
@@ -25,57 +25,56 @@ ccfp init --ai cursor
25
25
  ccfp init --ai windsurf
26
26
  ccfp init --ai copilot
27
27
 
28
- # English version
28
+ # 英文版
29
29
  ccfp init --ai claude --lang en
30
30
  ccfp init --ai cursor --lang en
31
31
 
32
- # 指定输出目录 / Specify output directory
32
+ # 指定输出目录
33
33
  ccfp init --ai claude --output /path/to/project
34
- ccfp init --ai claude --lang en --output /path/to/project
35
34
  ```
36
35
 
37
- ## 选项 / Options
36
+ ## 选项
38
37
 
39
- | Option | Description | Default |
40
- |--------|-------------|---------|
41
- | `--ai <type>` | Target AI (claude, cursor, windsurf, copilot) | claude |
42
- | `--lang <language>` | Language (zh, en) | zh |
43
- | `--output <path>` | Output directory | . |
38
+ | 选项 | 描述 | 默认值 |
39
+ |------|------|--------|
40
+ | `--ai <type>` | 目标 AI (claude, cursor, windsurf, copilot) | claude |
41
+ | `--lang <language>` | 语言 (zh, en) | zh |
42
+ | `--output <path>` | 输出目录 | . |
44
43
 
45
- ## 支持的 AI 助手 / Supported AI Assistants
44
+ ## 支持的 AI 助手
46
45
 
47
- | AI Assistant | Generated File | Usage |
48
- |--------------|----------------|-------|
49
- | Claude Code | `.claude/commands/fingerprint.md` | Type `/fingerprint` |
50
- | Cursor | `.cursor/rules/fingerprint.mdc` | Ask "identify what model you are" |
51
- | Windsurf | `.windsurfrules` | Ask "identify what model you are" |
52
- | GitHub Copilot | `.github/copilot-instructions.md` | Ask "identify what model you are" |
46
+ | AI 助手 | 生成文件 | 使用方式 |
47
+ |---------|----------|----------|
48
+ | Claude Code | `.claude/commands/fingerprint.md` | 输入 `/fingerprint` |
49
+ | Cursor | `.cursor/rules/fingerprint.mdc` | 询问 "帮我鉴别一下你是什么模型" |
50
+ | Windsurf | `.windsurfrules` | 询问 "帮我鉴别一下你是什么模型" |
51
+ | GitHub Copilot | `.github/copilot-instructions.md` | 询问 "帮我鉴别一下你是什么模型" |
53
52
 
54
- ## 工作原理 / How It Works
53
+ ## 工作原理
55
54
 
56
- Four-phase identity verification process:
55
+ 四阶段身份验证流程:
57
56
 
58
- ### Phase 1: Self-Declaration / 阶段 1: 自我声明
59
- Model answers basic questions about itself (model ID, context length, knowledge cutoff, etc.)
57
+ ### 阶段 1: 自我声明
58
+ 模型回答关于自身的基本问题(模型 ID、上下文长度、知识截止日期等)
60
59
 
61
- ### Phase 2: Knowledge Boundary Test / 阶段 2: 知识边界测试
62
- Probe the model's true knowledge cutoff date through time-sensitive questions (Nobel Prizes, etc.)
60
+ ### 阶段 2: 知识边界测试
61
+ 通过时间敏感问题(诺贝尔奖等)探测模型的真实知识截止日期
63
62
 
64
- ### Phase 3: Capability Inference / 阶段 3: 能力推算
65
- Verify whether the model's claimed capability parameters are reasonable
63
+ ### 阶段 3: 能力推算
64
+ 验证模型声称的能力参数是否合理
66
65
 
67
- ### Phase 4: Third-Party Verification / 阶段 4: 第三方验证
68
- Model analyzes the anonymous report from the first three phases as an "LLM Expert" for consistency check
66
+ ### 阶段 4: 第三方验证
67
+ 模型以"LLM 专家"身份分析前三阶段的匿名报告,进行一致性检查
69
68
 
70
- ## 输出示例 / Output Example
69
+ ## 输出示例
71
70
 
72
- Final output is a Markdown verification report containing:
73
- - Basic information table / 基本信息表格
74
- - Knowledge boundary test results / 知识边界测试结果
75
- - Capability verification results / 能力验证结果
76
- - Expert analysis (consistency, knowledge cutoff inference, identity inference) / 专家分析
77
- - Final conclusion with credibility score / 最终结论与可信度评分
71
+ 最终输出为 Markdown 验证报告,包含:
72
+ - 基本信息表格
73
+ - 知识边界测试结果
74
+ - 能力验证结果
75
+ - 专家分析(一致性、知识截止推断、身份推断)
76
+ - 最终结论与可信度评分
78
77
 
79
- ## License
78
+ ## 许可证
80
79
 
81
80
  MIT
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "ccfingerprint",
3
- "version": "1.0.0",
3
+ "version": "1.0.1",
4
4
  "description": "AI Model Identity Fingerprinting Tool - Verify model identity through self-Q&A / AI 模型身份指纹识别工具 - 通过自问自答验证模型真实身份",
5
5
  "main": "src/init.js",
6
6
  "bin": {