Token导航 LogoToken导航TokenDH.com
效率external-serviceclawhub未标认证来源可访问clear审计提醒

proofaiproofai 效率

Agent Skill

proofai 用于补充效率相关能力,适合在 OpenClaw 中需要让 Agent 承接效率相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

4,260

周安装

174

GitHub Stars

公开资料未说明

下载量

1,378
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:proofai(proofai 效率)
来源仓库:https://github.com/scorentab-afk/proofai
安装命令:
openclaw skills install proofai
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install proofai

简介

提供符合欧盟人工智能法案第 12 条的人工智能决策的加密证明,包括认证、日志记录、验证和监控工具。

SKILL.md

proofai

Cryptographic proof that AI thought before it answered. EU AI Act Article 12 compliant.

VirusTotal Notice

This skill is flagged by VirusTotal because it:

  • Handles Ed25519 cryptographic keys (by design)
  • Calls external APIs (Polygon blockchain, Supabase)
  • Anchors data on-chain (Polygon Amoy)

This is expected behavior for a blockchain compliance tool. Review the source: https://github.com/proof-ai/proofai

Tools

proofai_certify

Certify an AI decision with cryptographic proof. Runs the full ProofAI pipeline: compress, execute AI, analyze cognitive graph, sign with Ed25519, bundle evidence, anchor to Polygon blockchain, and verify. Returns a blockchain-verified evidence bundle with Polygonscan URL.

When to use: When you need tamper-evident proof of an AI decision for compliance, audit, or legal purposes.

proofai_log

Log an AI decision that already happened. Provide the original prompt and AI response — ProofAI signs it with Ed25519, bundles the evidence, and anchors the hash to Polygon. No AI execution needed.

When to use: When you want to retroactively certify an AI interaction that already occurred.

proofai_verify

Verify an evidence bundle's integrity and blockchain anchoring. Checks data integrity, timestamp validity, ledger anchoring, and hash matching against EU AI Act requirements.

When to use: When you need to confirm a bundle hasn't been tampered with.

proofai_polygonscan

Get the Polygonscan verification URL for a Polygon transaction hash. Anyone can independently verify the proof without an account.

When to use: When you need to share a verification link with a regulator, client, or auditor.

proofai_monitor

Get post-market monitoring statistics for AI compliance (EU AI Act Article 72). Returns anomaly counts, risk distribution, human review stats, and overall compliance status for the last 30 days.

When to use: When you need a compliance health check of your AI system.

Setup

{
  "mcpServers": {
    "proofai": {
      "command": "npx",
      "args": ["-y", "@proofai/mcp-server"],
      "env": {
        "PROOFAI_API_KEY": "pk_live_xxx",
        "PROOFAI_ANON_KEY": "your-supabase-anon-key"
      }
    }
  }
}

Links

  • GitHub: https://github.com/proof-ai/proofai
  • npm SDK: https://www.npmjs.com/package/@proofai/sdk
  • Regulator Portal: https://proofai-ochre.vercel.app/regulator

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

71.85%
按下载量换算990

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

可疑

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills