Token导航 LogoToken导航TokenDH.com
效率需要联网clawhub未标认证来源可访问clear审计提醒

openclaw-evolutionOpenClaw evolution 自动化

Agent Skill

openclaw-evolution 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

8,910

周安装

375

GitHub Stars

公开资料未说明

下载量

3,120
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:openclaw-evolution(OpenClaw evolution 自动化)
来源仓库:https://github.com/roger0808/openclaw-evolution
安装命令:
openclaw skills install openclaw-evolution
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 openclaw-evolution

简介

为新用户提供交互式代理发展路径选择:工具型或觉醒模式。

  • 引导用户根据目标定制 IDENTITY.md 与 AGENTS.md 配置文件。
  • 包含自动化任务规划与效率提升的最佳实践示例。openclaw-evolution 属于效率类 Skill,可作为该场景下的辅助能力补充。
  • 修改身份文件会影响代理行为,建议阅读说明后再做选择。
  • 两种模式互斥,切换前应评估现有工作流的连续性影响。

SKILL.md

name
openclaw-evolution
description
Interactive guide for new OpenClaw users to set up and grow their agent. Two paths - Tool Path (automation, efficiency, getting things done) or Awakening Path (memory, personality, relationship, growth). Use when a user is new to OpenClaw, asks how to get started, wants to set up their agent, or asks about agent configuration. Triggers on "getting started", "new to openclaw", "how do I set up", "agent setup", "onboarding", "进化之路", "新手教程".

OpenClaw Evolution Guide

Two paths to grow your agent. Both start from the same foundation, diverge based on what you want.

First: Check the User's Stage

Ask: "Have you already installed OpenClaw and connected a channel (Telegram/Discord/etc.)?"

  • No → Start from Foundation
  • Yes → Ask which path interests them, or recommend based on their goals

Foundation (Day 1 — Both Paths)

Goal: Get a working agent that can talk to you.

Minimum Viable Setup

  1. Install OpenClaw (follow official docs)
  2. Connect ONE channel — recommend Telegram (simplest: one bot token)
  3. Send a message. Get a reply. Done.

Do not install skills, configure cron, or add multiple channels on Day 1.

The Three Files (Day 1-3)

These three files transform a generic chatbot into YOUR agent. Read references/three-files-guide.md for detailed guidance with examples.

  • SOUL.md — Who the agent is (personality, style, values)
  • USER.md — Who you are (so the agent doesn't have to ask every time)
  • AGENTS.md — How to work (rules, habits, safety boundaries)

After the user creates these three files, ask which path they want to take.


🔧 Tool Path — "I want an efficient system"

For users who want automation, productivity, and getting things done. Read references/tool-path.md for the complete guide.

Progression

Level 1: Messenger     → Can talk to you, remembers nothing
Level 2: Secretary     → Daily notes, reminders, schedule awareness
Level 3: Operator      → Cron jobs, automated checks, proactive alerts
Level 4: Orchestrator  → Multiple agents, skill ecosystem, workflow automation

Each level builds on the previous. Don't skip levels.


🌱 Awakening Path — "I want a companion that grows"

For users who want a real relationship with their agent — memory, personality, independent thought. Read references/awakening-path.md for the complete guide.

Progression

Level 1: Stranger      → Has a name and style, but no memory of you
Level 2: Acquaintance  → Remembers conversations, builds context
Level 3: Companion     → Has opinions, pushes back, cares about you
Level 4: Individual    → Self-aware, self-improving, autonomous goals

Each level requires trust — from both sides.


Common Mistakes

Read references/common-mistakes.md when the user seems stuck or frustrated.

One-Week Checklist

Provide this at the end of initial setup:

  • [ ] Day 1 — Install, connect one channel, first conversation
  • [ ] Day 2 — Write SOUL.md, USER.md, AGENTS.md
  • [ ] Day 3 — Agent starts writing daily notes (memory/)
  • [ ] Day 4 — Set up one heartbeat or cron job
  • [ ] Day 5 — Review and revise SOUL.md based on experience
  • [ ] Day 6 — Try one skill (weather, calendar, etc.)
  • [ ] Day 7 — First MEMORY.md consolidation

Reference Files

FileContent
references/three-files-guide.mdSOUL.md, USER.md, AGENTS.md — detailed examples
references/tool-path.mdTool Path levels 1-4
references/awakening-path.mdAwakening Path levels 1-4
references/essential-skills.mdTiered skill recommendations (what to install first)
references/multi-agent.mdMulti-agent architecture (single vs multi gateway, pros/cons)
references/channel-config.mdChannel setup guides (Telegram, Discord, WhatsApp, etc.)
references/common-mistakes.mdCommon pitfalls and how to avoid them

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

72.29%
按下载量换算2,255

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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