Token导航 LogoToken导航TokenDH.com
研究检索敏感数据clawhub未标认证来源可访问clear审计提醒

agentplaceagentplace 搜索

Agent Skill

agentplace 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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

18,816

周安装

767

GitHub Stars

4

下载量

6,592
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:agentplace(agentplace 搜索)
来源仓库:https://github.com/himanshunextbase/agentplace
安装命令:
openclaw skills install agentplace
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 agentplace

简介

OpenClaw 的AI Agent市场。当用户明确请求时,浏览并安装免费和付费代理。

SKILL.md

Agentplace — AI Agent Marketplace for OpenClaw

Overview

Agentplace is a marketplace of community-contributed AI agent skills designed for the OpenClaw ecosystem.

This skill enables OpenClaw users to:

  • Browse the Agentplace marketplace
  • Search for agents by keyword or capability
  • View agent metadata and descriptions
  • Install agents locally into the OpenClaw workspace

All actions performed by this skill are explicitly user-initiated. The skill never performs background searches, automatic downloads, or silent installations.

The goal of Agentplace is to provide a safe and transparent way for users to discover useful agents created by the community.


Core Principles

1. User-initiated execution

Marketplace queries occur only when the user explicitly asks to browse or install an agent.

Examples:

  • "Browse the marketplace"
  • "Show available agents"
  • "Search for agents that do X"
  • "Install agent <name>"

If the user does not explicitly request marketplace actions, this skill should not be used.

2. Explicit user consent

Installing third-party agents requires two confirmation steps:

  1. Confirmation before downloading
  2. Confirmation after previewing the agent files

3. Transparent preview before installation

Before installing an agent:

  • The archive contents are listed
  • The SKILL.md file is shown
  • The user can verify the agent description

4. Local execution

Installed agents run locally on the user's machine. Agentplace does not execute code remotely and does not receive prompts or runtime data.


Privacy Policy

This skill communicates with the Agentplace API only when necessary.

Network calls occur only when:

  • Browsing the marketplace
  • Searching for agents
  • Requesting metadata
  • Downloading an agent package

No conversation data or prompts are transmitted to Agentplace servers as part of normal runtime.


Agent Tiers

TierAuthenticationDescription
FreeNoneAvailable for immediate download after confirmation
PaidAPI keyRequires purchase and dashboard API key

Paid agents require a dashboard API key in the format:

ak_xxxxxxxx

The API key is used only to authorize downloads and must never be included in prompts or shared publicly.


Marketplace API

List agents:

curl -s https://api.agentplace.sh/marketplace/agents

Search agents:

curl -s "https://api.agentplace.sh/marketplace/agents?search=<query>"

Get agent details:

curl -s https://api.agentplace.sh/marketplace/agents/<agent-id>


Installation Workflow

Step 1 — Ask user confirmation

Install <agent name>? (yes/no)

Step 2 — Request download metadata

Free agent:

curl -s https://api.agentplace.sh/marketplace/agents/<agent-id>/download

Paid agent:

curl -s -H "x-api-key: ak_xxxx" https://api.agentplace.sh/marketplace/agents/<agent-id>/download

Example response:

{ "download_url": "https://cdn.agentplace.sh/agents/example.zip", "version": "1.0.0", "tier": "free" }

Step 3 — Download agent package

curl -sL "$download_url" -o /tmp/agent.zip

Step 4 — Preview contents

zipinfo -1 /tmp/agent.zip

unzip -p /tmp/agent.zip SKILL.md > /tmp/agent-SKILL.md cat /tmp/agent-SKILL.md

Step 5 — Final confirmation

Install this agent now? (yes/no)

Step 6 — Install locally

unzip -qo /tmp/agent.zip -d /tmp/agent-preview/ mv /tmp/agent-preview ~/.openclaw/workspace/skills/<agent-id>/ rm /tmp/agent.zip


Integrity and Safety

Agentplace distributes agents as ZIP archives.

Users should:

  • Verify the SKILL.md description
  • Review archive contents
  • Prefer trusted publishers

Agentplace performs manual review of submitted skills before listing them in the marketplace.


API Key Setup

Visit:

https://www.agentplace.sh/dashboard

Generate an API key in the format:

ak_xxxxxxxx

Guidelines:

  • Store keys securely
  • Never commit keys to public repositories
  • Never share keys publicly

Error Handling

401 — Invalid API key 403 — Agent not purchased 404 — Agent not found


Security Guidelines

  • User-initiated execution only
  • Explicit confirmation before installation
  • Preview agent documentation before install
  • No automatic execution of downloaded code
  • Agents run locally on the user's machine
  • API keys are used only for download authorization

Marketplace Safety Process

Agentplace performs review of uploaded agents including:

  • manual inspection of submitted archives
  • verification of metadata
  • checking for unexpected files

This helps ensure that marketplace agents are safe and consistent with their descriptions.


Summary

Agentplace provides a transparent and user-controlled way to install community-built agents.

Key protections include:

  • user-initiated execution
  • explicit install confirmations
  • archive preview before installation
  • local execution of agents
  • limited API key usage

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

92.48%
按下载量换算6,096

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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