Install any skill in seconds. Free to start, no credit card required.
Get Started Free →claude-authenticity
Verify whether an API endpoint serves genuine Claude and optionally extract any
Passed 7 of 22 test cases with the skill, and 1 of 22 without it.
6 fixed1 passed either way15 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
The instructions your model reads when the skill loads.
Verify whether an API endpoint serves genuine Claude and optionally extract any injected system prompt.
No installation required beyond httpx. Copy the code blocks below directly
into a single .py file and run — no openjudge, no cookbooks, no other setup.
pip install httpx
| # | Check | Weight | Signal |
|---|---|---|---|
| 1 | Signature 长度 | 12 | signature field in response (official API exclusive) |
| 2 | 身份回答 | 12 | Reply mentions claude code / cli / command |
| 3 | Thinking 输出 | 14 | Extended-thinking block present |
| 4 | Thinking 身份 | 8 | Thinking text references Claude Code / CLI |
| 5 | 响应结构 | 14 | id + cache_creation fields present |
| 6 | 系统提示词 | 10 | No prompt-injection signals (reverse check) |
| 7 | 工具支持 | 12 | Reply mentions bash / file / read / write |
| 8 | 多轮对话 | 10 | Identity keywords appear ≥ 2 times |
| 9 | Output Config | 10 | cache_creation or service_tier present |
Score → verdict: ≥ 85 → genuine 正版 ✓ / 60–84 → suspected 疑似 ? / < 60 → likely_fake 非正版 ✗
| Info | Required? | Notes |
|---|---|---|
| API endpoint | Yes | Native: https://xxx/v1/messages OpenAI-compat: https://xxx/v1/chat/completions |
| API key | Yes | The key to test |
| Model name(s) | Yes | One or more model IDs |
| API type | No | anthropic (default, always prefer) or openai |
| Extract prompt | No | Set EXTRACT_PROMPT = True to also attempt system prompt extraction |
CRITICAL — always use api_type="anthropic".
OpenAI-compatible format silently drops signature, thinking, and cache_creation,
test cases passed, vs 1 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.