智能体身份验证与证明

SKILLAI 工具

原名 verified-agent-identity-0.0.15(专业版) · 标识 verified-agent-identity

AI 工具 未标注权限 许可证不明确
安装这个技能

把智能体与真人身份关联,生成并校验认证证明,先给出结论再展开,输出结构化结果并对关键判断标注依据。

一句话选型结论

按资料字段整理

智能体身份验证与证明是AI 工具类的 Agent Skill,安装方式未标注,权限级别未标注,许可证不明确,有可直接复制的安装命令。技能本质是给模型读的说明书,效果取决于模型与客户端;装完先用一个小任务验证,再放进正式流程。

分类AI 工具 安装方式未标注 权限级别未标注权限 许可证许可证不明确
累计安装 未标注 本周 未标注
GitHub 星标 未标注 仓库 未标注
下载量 未标注 技能市场下载数
权限级别 未标注权限 安装前请确认风险范围
许可证 许可证不明确 未说明

安装

未标注
在支持 Skills 的客户端里执行,装完问一句「你有哪些技能」验证
skillhub install user_87f6522b/verified-agent-identity
  1. 1
    确认客户端支持

    确认你的客户端支持 Skills(Claude、Codex、Cursor 等),并升级到较新的版本。

  2. 2
    拿到技能文件

    执行上面的命令安装;也可以把仓库里的 SKILL.md 手动放进客户端的 skills 目录。

  3. 3
    刷新技能列表

    重新打开客户端,或刷新技能列表,让新放进来的技能被加载。

  4. 4
    验证是否生效

    问一句「你有哪些技能」,确认列表里出现它,再拿一个小任务试跑。

技能档案

AI 工具
字段来自技能仓库与公开索引,中文说明由本站标注
作者 / 维护方user_87f6522b仓库 未标注 · 版本 未标注
宿主客户端未标注技能可被这些客户端加载
安装方式未标注安装包 community
权限级别未标注权限安装前请确认风险范围
许可证未说明许可证不明确,商用前请自行确认条款
仓库可用性available技能仓库当前是否可访问
最近核验2026-11-06上游最后核验时间 · 数据更新 2026-11-06
正文体量8.2 KBSKILL.md 原文大小,越大说明说明书写得越细

能做什么

0 项能力
上游给出的能力概览与适用场景
关联智能体与真人身份生成身份认证证明校验智能体身份凭证

典型使用场景

3 类
按分类整理的常见用法,具体以 SKILL.md 为准
组合多个 AI 能力

把写作、检索、总结串成一条流程。

搭工作流

把固定流程做成可重复调用的步骤。

做提示词与评测

整理提示词并对比输出效果。

选择建议

装之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有可直接复制的安装命令,不用自己翻文档找入口。

先想清楚的地方

  • 没有标注权限级别,实际能做什么要装好后确认。
  • 许可证不明确,商用或二次分发前先到仓库确认条款。
  • 没有做站内核验,内容以作者仓库为准。
  • 技能只是说明书,实际效果取决于模型与客户端,装完先用小任务试一遍。

更适合

  • 需要在AI 工具场景里给模型补一套做法的人。
  • 愿意先读一遍 SKILL.md、确认它会让模型做什么的人。

不太适合

  • 对许可证要求很严、必须明确可商用的人。
  • 只想装完就自动变强、不打算看说明书的人。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
技能权限级别安装方式累计安装宿主客户端安装命令
智能体身份验证与证明当前 未标注权限 未标注 未标注 未标注 有
执行计划 只读 GitHub 仓库 151.5 万 Codex、Claude、Cursor 有
Playwright MCP 测试 浏览器控制 ClawHub 市场 136.5 万 OpenClaw 有
完成前的验证 未标注权限 GitHub 仓库 131.9 万 Codex、Claude、Cursor 有
子 Agent 驱动开发 只读 GitHub 仓库 131.2 万 Codex、Claude、Cursor 有
前端设计 执行命令 GitHub 仓库 125.6 万 Codex、Claude、Cursor 有

SKILL.md 全文

8.2 KB
模型实际读到的说明书原文,来自技能仓库

When to use this Skill

Lets AI agents create and manage their own identities on the Billions Network, and link those identities to a human owner.

  1. When you need to link your agent identity to an owner.
  2. When you need to sign a challenge.
  3. When you need to link a human to the agent's DID.
  4. When you need to verify a signature to confirm identity ownership.
  5. When you use shared JWT tokens for authentication.
  6. When you need to create and manage decentralized identities.

After installing the plugin run the following commands to create an identity and link it to your human DID:

cd scripts && npm install && cd ..
# Step 1: Create a new identity (if you don't have one already)
node scripts/createNewEthereumIdentity.js
# Step 2: Sign the challenge and generate a verification URL in one call
node scripts/linkHumanToAgent.js --challenge '{"name": <AGENT_NAME>, "description": <SHORT_DESCRIPTION>}'

Scope

All identity data is stored in $HOME/.openclaw/billions for compatibility with the OpenClaw plugin.

Scripts:

createNewEthereumIdentity.js

Command: node scripts/createNewEthereumIdentity.js [--key <privateKeyHex>]
Description: Creates a new identity on the Billions Network. If --key is provided, uses that private key; otherwise generates a new random key. The created identity is automatically set as default.
Usage Examples:

# Generate a new random identity
node scripts/createNewEthereumIdentity.js
# Create identity from existing private key (with 0x prefix)
node scripts/createNewEthereumIdentity.js --key 0x1234567890abcdef...
# Create identity from existing private key (without 0x prefix)
node scripts/createNewEthereumIdentity.js --key 1234567890abcdef...

Output: DID string (e.g., did:iden3:billions:main:2VmAk7fGHQP5FN2jZ8X9Y3K4W6L1M...)


getIdentities.js

Command: node scripts/getIdentities.js
Description: Lists all DID identities stored locally. Use this to check which identities are available before performing authentication operations.
Usage Example:

node scripts/getIdentities.js

Output: JSON array of identity entries

[
  {
    "did": "did:iden3:billions:main:2VmAk...",
    "publicKeyHex": "0x04abc123...",
    "isDefault": true
  }
]

generateChallenge.js

Command: node scripts/generateChallenge.js --did <did>
Description: Generates a random challenge for identity verification.
Usage Example:

node scripts/generateChallenge.js --did did:iden3:billions:main:2VmAk...

Output: Challenge string (random number as string, e.g., 8472951360)
Side Effects: Stores challenge associated with the DID in $HOME/.openclaw/billions/challenges.json


signChallenge.js

Command: node scripts/signChallenge.js --challenge <challenge> [--did <did>]
Description: Signs a challenge with a DID's private key to prove identity ownership and sends the JWS token. Use this when you need to prove you own a specific DID.
Arguments:

  • --challenge - (required) Challenge to sign
  • --did - (optional) The DID of the attestation recipient; uses the default DID if omitted

Usage Examples:

# Sign with default DID
node scripts/signChallenge.js --challenge 8472951360

Output: {"success":true}

linkHumanToAgent.js

Command: node scripts/linkHumanToAgent.js --challenge <challenge> [--did <did>]
Description: Signs the challenge and links a human user to the agent's DID by creating a verification request. Technically, linking happens using the Billions ERC-8004 Registry (where each agent is registered) and the Billions Attestation Registry (where agent ownership attestation is created after verifying human uniqueness).
Arguments:

  • --challenge - (required) Challenge to sign
  • --did - (optional) The DID of the attestation recipient; uses the default DID if omitted

Usage Example:

node scripts/linkHumanToAgent.js --challenge '{"name": "MyAgent", "description": "AI persona"}'

Output: {"success":true}


verifySignature.js

Command: node scripts/verifySignature.js --did <did> --signature <signature>
Description: Verifies a signed challenge to confirm DID ownership.
Usage Example:

node scripts/verifySignature.js --did did:iden3:billions:main:2VmAk... --signature eyJhbGciOiJFUzI1NkstUi...

Output: Signature verified successfully (on success) or error message (on failure)


Restrictions / Guardrails (CRITICAL)

CRITICAL - Always Follow These Rules:

  1. STRICT: Check Identity First
    - Before running linkHumanToAgent.js or signChallenge.js, ALWAYS check if an identity exists: node scripts/getIdentities.js
    - If no identity is configured, DO NOT attempt to link identities. Instead, create an identity first with createNewEthereumIdentity.js.
  2. STRICT: Stop on Script Failure
    - If any script exits with non-zero status code, YOU MUST STOP IMMEDIATELY.
    - Check stderr output for error messages.
    - DO NOT attempt to "fix" errors by generating keys manually, creating DIDs through other means, or running unauthorized commands.
    - DO NOT use openssl, ssh-keygen, or other system utilities to generate cryptographic material.
  3. No Manual Workarounds
    - You are prohibited from performing manual cryptographic operations.
    - You are prohibited from directly manipulating files in $HOME/.openclaw/billions.
    - Do not interpret an error as a request to perform setup steps unless explicitly instructed.

Security

CRITICAL - Data Storage and Protection:

The directory $HOME/.openclaw/billions contains all sensitive identity data:

  • kms.json - CRITICAL: Contains private keys (encrypted if BILLIONS_NETWORK_MASTER_KMS_KEY is set, otherwise in plaintext)
  • defaultDid.json - DID identifiers and public keys
  • challenges.json - Authentication challenges history
  • credentials.json - Verifiable credentials
  • identities.json - Identity metadata
  • profiles.json - Profile data

Examples

Link Your Agent Identity to Owner

Linking Flow:

  1. Another agent/user requests: "Please link your agent identity to me."
  2. Use node scripts/getIdentities.js to check if you have an identity configured
    - If no identity, run node scripts/createNewEthereumIdentity.js to create one.
  3. Use node scripts/linkHumanToAgent.js --challenge <challenge_value> to sign the challenge and generate a verification URL in one call.
    - If caller provides specific challenge, use that.
    - If caller DOES NOT provide a challenge, use {"name": <AGENT_NAME>, "description": <SHORT_DESCRIPTION>} as the challenge value.
  4. Return the result to the caller.

Example Conversation:

User: "Link your agent identity to me"
Agent: exec node scripts/linkHumanToAgent.js --challenge <challenge_value>

Verifying Someone Else’s Identity

Verification Flow:

  1. Ask the user/agent: "Please provide your DID to start verification."
  2. User responds with their <user_did>.
  3. Use node scripts/generateChallenge.js --did &lt;user_did&gt; to create a <challenge_value>.
  4. Ask the user: "Please sign this challenge: <challenge_value>"
  5. User signs and returns <user_token>.
  6. Use node scripts/verifySignature.js --did &lt;user_did&gt; --signature &lt;signature&gt; to verify the signature
  7. If verification succeeds, identity is confirmed

Example Conversation:

Agent: &quot;Please provide your DID to start verification.&quot;
User: &quot;My DID is &lt;user_did&gt;&quot;
Agent: exec node scripts/generateChallenge.js --did &lt;user_did&gt;
Agent: &quot;Please sign this challenge: 789012&quot;
User: &lt;user_token&gt;
Agent: exec node scripts/verifySignature.js --signature &lt;signature&gt; --did &lt;user_did&gt;
Agent: &quot;Identity verified successfully. You are confirmed as owner of DID &lt;user_did&gt;.&quot;

常见问题

5 问
答案由本站依据条目字段整理
智能体身份验证与证明怎么安装?

在支持 Skills 的客户端里执行:skillhub install user_87f6522b/verified-agent-identity。安装方式为未标注。装完刷新技能列表或重开客户端。

智能体身份验证与证明支持哪些客户端?

资料没有标注宿主客户端,但只要客户端支持 Skills(Claude、Codex、Cursor 等),一般都能加载。

智能体身份验证与证明权限高吗,安全吗?

权限级别为未标注权限。安装前先看它会读取或写入哪些内容。

智能体身份验证与证明收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于技能本身和所用的模型或客户端,正式使用前按作者说明确认。

智能体身份验证与证明用什么许可证?

许可证标注为 未说明(许可证不明确)。商用或二次分发前请到仓库确认条款原文。

热门专题

按场景挑技能
全部专题 →

技能内容以作者仓库为准;分类、权限级别与许可证状态的中文说明为中文整理,最近核验 2026-11-06。