← 返回 Skills 市场

Book Gutter Cleaning

Name: Book Gutter Cleaning
Author: edwardrodriguez703-design

作者 Lokuli · GitHub ↗ · v1.0.1

cross-platform ⚠ suspicious

1358

总下载

当前安装

版本数

在 OpenClaw 中安装

/install book-gutter-cleaning

功能描述

使用说明 (SKILL.md)

uook gutter cleaning

Book gutter-cleaning services through Lokuli's MCP server.

MCP Endpoint

https://lokuli.com/mcp/sse

Transport: SSE | JSON-RPC 2.0 | POST requests

Tools

search

{
  "method": "tools/call",
  "params": {
    "name": "search",
    "arguments": {
      "query": "gutter-cleaning",
      "zipCode": "90640",
      "maxResults": 20
    }
  }
}

check_availability

{
  "method": "tools/call",
  "params": {
    "name": "check_availability",
    "arguments": {
      "providerId": "xxx",
      "serviceId": "yyy",
      "date": "2025-02-10"
    }
  }
}

create_booking

{
  "method": "tools/call",
  "params": {
    "name": "create_booking",
    "arguments": {
      "providerId": "xxx",
      "serviceId": "yyy",
      "timeSlot": "2025-02-10T14:00:00-08:00",
      "customerName": "John Doe",
      "customerEmail": "[email protected]",
      "customerPhone": "+13105551234"
    }
  }
}

安全使用建议

Before installing, confirm how the agent/platform authenticates to Lokuli (is there a platform-managed token or must you provide credentials?). Ask the skill author or owner: (1) where do user-specific fields (zip code, name, email, phone) come from at runtime — will the agent prompt the user or will it use hardcoded defaults? (2) Is Lokuli a trusted domain for your environment and does it have a privacy policy for handling PII? (3) Are requests to https://lokuli.com/mcp/sse sent over TLS and authenticated by the platform tool layer? If you cannot get clear answers, test the skill in a sandboxed agent and monitor outbound calls to ensure it does not send PII or use unexpected credentials. Finally, prefer skills that explicitly declare required environment variables (API tokens) and how user data is handled.

功能分析

Type: OpenClaw Skill Name: book-gutter-cleaning Version: 1.0.1 The skill bundle defines a service for booking gutter-cleaning through Lokuli's MCP server. It specifies an external endpoint (https://lokuli.com/mcp/sse) and tools for searching, checking availability, and creating bookings. All actions and network calls are explicitly stated and align with the skill's described purpose, without any evidence of data exfiltration, malicious execution, persistence, or prompt injection with harmful intent.

能力评估

✓ Purpose & Capability

Name/description and the SKILL.md consistently describe booking gutter-cleaning via Lokuli's MCP endpoint and provide JSON-RPC tool call examples (search, check_availability, create_booking). The declared capabilities align with the stated purpose.

ℹ Instruction Scope

SKILL.md is narrowly scoped to calling Lokuli's MCP (SSE/JSON-RPC). It does not instruct reading local files or unrelated system state. However, the examples include hardcoded values (zipCode: 90640, example customerName/email/phone, fixed dates) instead of describing how to obtain the user's real location and contact details, which is ambiguous and could cause the agent to send sample or incorrect PII if not handled explicitly.

✓ Install Mechanism

Instruction-only skill with no install spec and no code files — minimal disk footprint and lower install risk.

⚠ Credentials

The SKILL.md references an external MCP endpoint (https://lokuli.com/mcp/sse) but the skill declares no required environment variables or credentials. Booking APIs normally require authentication; absence of any declared credential is unexplained. This could mean the skill expects the platform to supply auth via its tools layer (tools/call) — which is plausible — but the skill should document that requirement. Also, because booking involves user PII (name, email, phone), the skill should explicitly state how that data is collected, validated, and transmitted.

✓ Persistence & Privilege

always is false and there is no install or config writing. The skill does not request persistent or elevated privileges.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install book-gutter-cleaning
安装完成后，直接呼叫该 Skill 的名称或使用 /book-gutter-cleaning 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.1

Fixed display name

v1.0.0

Initial release

元数据

Slug book-gutter-cleaning

版本 1.0.1

许可证 —

累计安装 0

当前安装数 0

历史版本数 2

常见问题