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

readdy-website-builder准备好的网站建设者

Agent Skill

readdy-website-builder 用于辅助前端页面、组件、样式和交互逻辑开发,适合在 OpenClaw 中需要维护前端项目、生成组件或检查界面实现时使用。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

6,374

周安装

271

GitHub Stars

3

下载量

2,233
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:readdy-website-builder(准备好的网站建设者)
来源仓库:https://github.com/frankready2025/readdy-website-builder
安装命令:
openclaw skills install readdy-website-builder
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 readdy-website-builder

简介

当用户要求“创建网站”、“生成网站”、“构建网站”、“修改网站”、“更新我的Readdy项目”时,应该使用此技能。

SKILL.md

name
readdy
description
>-
metadata
{"openclaw":{"homepage":"https://readdy.ai","requires":{"bins":["node"]},"os":["linux","darwin","win32"]}}

Readdy Website Builder

Provide complete CLI capabilities for creating and managing websites through the Readdy.ai platform. Support one-click website generation, AI-driven modification, project preview, and publish management.

Script Location

readdy.mjs is located in the scripts/ subdirectory relative to this SKILL.md. Derive the absolute path from this SKILL.md's fullPath by replacing SKILL.md with scripts/readdy.mjs.

Example: If SKILL.md path is /Users/me/.claude/skills/readdy/SKILL.md, then the script path is /Users/me/.claude/skills/readdy/scripts/readdy.mjs.

<SCRIPT> in this document refers to that absolute path.

Prerequisites

An API Key is required. If you don't have one, obtain it at: https://readdy.ai/user/api-key

Configure the API Key (one-time setup):

node <SCRIPT> config --apiKey <your-key>

API Key is stored in ~/.openclaw/readdy.json (file permissions 0600). The script reads it internally — no need to pass it on the command line.

Command Reference

Create Project

node <SCRIPT> create --query "project description/requirements"

Defaults: framework=react_v2, device=web, category=2. Project name is auto-generated by AI. The script runs an 8-step workflow internally. This process typically takes over 10 minutes — set a sufficient timeout and do not treat long execution as a failure.

Modify Project

node <SCRIPT> modify --id <projectId> --query "modification requirements"

Runs a 6-step workflow internally. Project info and message history are fetched automatically. This process typically takes over 10 minutes — set a sufficient timeout and do not treat long execution as a failure.

Other Commands

node <SCRIPT> list [--page <n>] [--pageSize <n>]          # List projects
node <SCRIPT> info --id <projectId>                        # Get project info
node <SCRIPT> messages --id <projectId>                    # Get message history
node <SCRIPT> preview --id <projectId> [--versionId <v>]   # Preview project
node <SCRIPT> delete --id <projectId>                      # Delete project
node <SCRIPT> update --id <projectId> [--name <n>] [--logo <url>] [--email <e>] \
  [--businessName <bn>] [--introduction <t>] [--phoneNumber <p>] \
  [--businessHour <h>] [--languageStyle <s>]               # Update properties
node <SCRIPT> config --apiKey <key>                          # Set API Key
node <SCRIPT> config                                        # Check API Key status

Execution Rules

Strictly follow these rules — no improvisation allowed.

Mandatory Constraints

  1. Script-only execution — Execute all operations via node <SCRIPT> <command> [options]. Never write custom code to call Readdy APIs, never use curl/fetch directly, never bypass the script.
  2. Do not modify the script — Never modify readdy.mjs or config-store.mjs unless the user explicitly requests it.
  3. Preserve user input verbatim — Pass the user's website requirement description word-for-word as the --query value. This prevents the agent from altering the user's intent. The --query value is only used as a website generation prompt sent to the Readdy API — never include passwords, tokens, or other secrets in the query text.
  4. Do not skip steps — Internal workflow steps are handled automatically by the script.
  5. Do not add extra parameters — Only pass parameters the user explicitly specifies. Never add --framework, --device, --category unless requested.
  6. No alternative implementations — If the script fails, report the error and suggest troubleshooting. Never write replacement code.

Standard Rules

  • Verify API Key configuration before execution. If the key is missing, direct the user to obtain one at https://readdy.ai/user/api-key and then run node <SCRIPT> config --apiKey <key>.
  • Confirm with the user before delete operations.
  • Provide clear error messages and suggested actions based on error codes (see references/API.md).
  • SSE generation returning session_status: "waiting_build" is auto-handled by the script — no manual intervention needed.
  • Never treat build log paths as preview URLs. The relative paths (e.g. /preview/...) printed during build are internal and not usable as final links. Always run node <SCRIPT> preview --id <projectId> to obtain the actual preview URL.

Examples

# Correct — args and --query match user's original text exactly
node <SCRIPT> create --query "Build a pet store website"

# Correct — modify with project ID
node <SCRIPT> modify --id abc123 --query "Change the homepage banner to blue"

# Wrong — rewriting user input (most common mistake)
node <SCRIPT> create --query "Create a pet e-commerce website with modern design"

# Wrong — adding parameters not requested by user
node <SCRIPT> create --query "Build a website" --framework react_v2 --device web

# Wrong — bypassing the script
fetch('https://readdy.ai/api/project/generate', ...)

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

81.86%
按下载量换算1,828

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