Skills for Real Engineers. Straight from my .agents directory.
39 skills
claude-authenticity
Agent skill from
Detect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project. Also extracts injected system prompts from providers that override Claude's identity. Fully self-contained — copy the code below and run, no extra packages beyond httpx. Use when the user wants to verify a Claude API key or endpoint, check if a third-party Claude service is authentic, audit API providers for Claude authenticity, test multiple models in parallel, or discover what system prompt a provider has injected.
How to install claude-authenticity
install claude-authenticity
# install the OpenJudge pack with the skills CLI
npx skills add agentscope-ai/OpenJudge# or add only this skill to Claude Code: copy the folder
skills/claude-authenticity/
# into
~/.claude/skills/claude-authenticity/ (all projects)
.claude/skills/claude-authenticity/ (one project)
1# Claude Authenticity Skill23Verify whether an API endpoint serves genuine Claude and optionally extract any4injected system prompt.56**No installation required beyond `httpx`.** Copy the code blocks below directly7into a single `.py` file and run — no openjudge, no cookbooks, no other setup.89```bash10pip install httpx11```1213## The 9 checks (mirrors [claude-verify](https://github.com/molloryn/claude-verify))1415| # | Check | Weight | Signal |16|---|-------|--------|--------|17| 1 | Signature 长度 | 12 | `signature` field in response (official API exclusive) |18| 2 | 身份回答 | 12 | Reply mentions `claude code` / `cli` / `command` |19| 3 | Thinking 输出 | 14 | Extended-thinking block present |20| 4 | Thinking 身份 | 8 | Thinking text references Claude Code / CLI |21| 5 | 响应结构 | 14 | `id` + `cache_creation` fields present |22| 6 | 系统提示词 | 10 | No prompt-injection signals (reverse check) |23| 7 | 工具支持 | 12 | Reply mentions `bash` / `file` / `read` / `write` |24| 8 | 多轮对话 | 10 | Identity keywords appear ≥ 2 times |25| 9 | Output Config | 10 | `cache_creation` or `service_tier` present |2627**Score → verdict:** ≥ 85 → `genuine 正版 ✓` / 60–84 → `suspected 疑似 ?` / < 60 → `likely_fake 非正版 ✗`2829## Gather from user before running3031| Info | Required? | Notes |32|------|-----------|-------|33| API endpoint | Yes | Native: `https://xxx/v1/messages` OpenAI-compat: `https://xxx/v1/chat/completions` |34| API key | Yes | The key to test |35| Model name(s) | Yes | One or more model IDs |36…
Excerpt shown under the repository's Apache-2.0 license.
More skills in OpenJudge
Keep exploring
Similar skill repositories
An agentic skills framework & software development methodology that works.
15 skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
CC1 skill
Public repository for Agent Skills
20 skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
CCCU6 skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
CCCXGHGM+135 skills