Token导航 LogoToken导航TokenDH.com
开发敏感数据clawhub未标认证来源可访问clear审计通过

x5-protocolx5 协议

Agent Skill

x5-protocol 用于辅助测试设计、自动化测试和回归验证,适合在 OpenClaw 中需要补充测试、分析失败日志或验证功能改动时使用。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

3,139

周安装

127

GitHub Stars

公开资料未说明

下载量

986
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:x5-protocol(x5 协议)
来源仓库:https://github.com/growingppp/x5-protocol
安装命令:
openclaw skills install x5-protocol
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 x5-protocol

简介

x5-protocol 用于发送 X5 API 请求和解析 .x5 配置文件,支持测试和调试。

  • 适合在 OpenClaw 中需要验证接口行为或生成测试用例的场景。
  • 可自动生成请求模板和响应断言,提升回归测试效率。
  • 安装命令为 openclaw skills install x5-protocol,需确认 .x5 文件格式和终端环境。
  • 注意维护状态及是否依赖特定版本 CLI,避免兼容性问题导致解析失败。

SKILL.md

name
x5-protocol
description
>

X5 Protocol Skill

Send X5 protocol requests directly from the terminal using scripts/x5_client.py.

Quick Start

# Send request from .x5 file
python3 ~/.claude/skills/x5-protocol/scripts/x5_client.py --file request.x5 --json

# Inline request
python3 ~/.claude/skills/x5-protocol/scripts/x5_client.py \
  --appid my_app --appkey my_key \
  --url http://localhost:8080/x5/api \
  --method createUser \
  --body '{"name":"test"}' \
  --json

X5 Protocol Specification

Signature Calculation

sign = md5(appid + JSON.stringify(body) + appkey).toUpperCase()

The body is serialized as compact JSON (no spaces), then concatenated with appid and appkey, MD5-hashed, and uppercased.

Request Encoding Steps

  1. Build the X5 envelope:
{
  "header": {
    "appid": "app_id",
    "sign": "MD5_SIGNATURE_UPPERCASE",
    "method": "X5_Method_Name"
  },
  "body": "{\"key\":\"value\"}"
}
  1. JSON-serialize the envelope (compact, no spaces)
  2. Base64-encode the JSON string
  3. Send as POST with Content-Type: application/x-www-form-urlencoded
  4. Body: data=<url_encoded_base64>

Response Format

X5 responses use the same envelope structure:

{
  "header": {
    "code": 0,
    "message": "success"
  },
  "body": { ... }
}

Success: HTTP 2xx AND X5 code 0 or 200.

.x5 File Format

### Request Description
@name = RequestName
@appid = my_app_id
@appkey = my_app_key
@url = http://localhost:8080/x5/api/endpoint

POST @url
X5-Method: methodName
X-Custom-Header: custom-value

{
  "key": "value"
}

Directives:

DirectiveDescription
@nameRequest name (for multi-request files)
@appidApplication ID
@appkeyApplication secret key
@urlRequest URL (referenced by POST @url)
X5-Method:X5 API method name (overwrites HTTP method)

Key parsing rules:

  • ### separates multiple requests in one file
  • # lines are comments
  • POST @url sets URL via @url directive reference
  • X5-Method: overwrites the method from the POST line
  • Any Header-Name: value line becomes a custom HTTP header
  • JSON body starts with { or [

Multiple requests per file:

### Create Resource
@name = createResource
@appid = my_app
@appkey = my_key
@url = http://localhost:8080/x5/resource/create

POST @url
X5-Method: createResource
{"name": "test"}

### Query Resource
@name = queryResource
@appid = my_app
@appkey = my_key
@url = http://localhost:8080/x5/resource/query

POST @url
X5-Method: queryResource
{"resourceId": "123"}

CLI Reference

python3 x5_client.py [OPTIONS]

Options:
  --file FILE           Path to .x5 file
  --request-name NAME   Specific request name (for multi-request files)
  --list                List all requests in .x5 file (no send)
  --appid APPID         App ID (inline or override)
  --appkey APPKEY       App Key (inline or override)
  --url URL             Target URL (inline or override)
  --method METHOD       X5 method name (inline or override)
  --body BODY           JSON body string
  --body-file FILE      JSON body file path
  --header KEY=VALUE    Custom HTTP header (repeatable)
  --curl                Generate cURL command (no send)
  --dry-run             Show encoded request (no send)
  --json                Output in JSON format
  --timeout MS          Timeout in ms (default: 30000)

Usage Patterns

Pattern 1: Send from .x5 file

python3 ~/.claude/skills/x5-protocol/scripts/x5_client.py --file /path/to/request.x5 --json

For multi-request files, use --request-name:

python3 ~/.claude/skills/x5-protocol/scripts/x5_client.py --file /path/to/api.x5 --request-name createUser --json

Pattern 2: Inline request

Use when the user describes a request conversationally or provides parameters directly:

python3 ~/.claude/skills/x5-protocol/scripts/x5_client.py \
  --appid VALUE --appkey VALUE --url VALUE --method VALUE \
  --body '{"key":"value"}' --json

Pattern 3: Generate cURL

python3 ~/.claude/skills/x5-protocol/scripts/x5_client.py --file request.x5 --curl

Pattern 4: List requests in file

python3 ~/.claude/skills/x5-protocol/scripts/x5_client.py --file request.x5 --list

Pattern 5: Debug / inspect encoded request

python3 ~/.claude/skills/x5-protocol/scripts/x5_client.py --file request.x5 --dry-run --json

Shows signature, Base64 payload, and full envelope without sending.

Important Notes

  • Always use --json for programmatic consumption — parse the JSON output to present results to the user
  • When a .x5 file has multiple requests and the user doesn't specify which one, list them and ask
  • CLI params (--appid, --appkey, etc.) override values from the .x5 file
  • The script uses Python stdlib only (zero dependencies)
  • Exit code 0 = success, 1 = error, 2 = argument error
  • On error with --json, output is {"success": false, "error": "message"}

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

81.17%
按下载量换算800

安全审计

VirusTotal

通过

ClawScan

通过

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。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