Xiaoyaoclaw Workspace Initializer — Development skill for Claude Code
给每个 OpenClaw agent 一个「家」:标准目录结构 + WORKSPACE.md 规范 + 多 agent 配置安全.
How to install Xiaoyaoclaw Workspace Initializer
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open dtsola/xiaoyaoclaw-workspace-initializer and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Xiaoyaoclaw Workspace Initializer does
给每个 OpenClaw agent 一个「家」:标准目录结构 + WORKSPACE.md 规范 + 多 agent 配置安全。 OpenClaw workspace initialization & standardization — the agent home your agents deserve.
Alternatives in Development
- Check 1: Cache Exists? — CLAUDE_DIR="${CLAUDE_CONFIG_DIR:-$HOME/.claude}" CACHE_EXISTS=$(ls -d "$CLAUDE_DIR/plugins/cache/claude-hud" 2 10.9k ★
- IPolloWork — Enterprise-grade, local-first Agent Workbench for people and agent teams 4.9k ★
- Seomachine — A specialized Claude Code workspace for creating long-form, SEO-optimized blog content for any business 2.8k ★
README
OpenClaw Workspace Initializer 🏠
给每个 OpenClaw agent 一个「家」:标准目录结构 + WORKSPACE.md 规范 + 多 agent 配置安全。 OpenClaw workspace initialization & standardization — the agent home your agents deserve.
 [](https://clawhub.ai/dtsola/skills/xiaoyaoclaw-workspace-initializer)
为什么需要它
OpenClaw agent 每次会话都是全新启动。没有工作区规范,你的 agent 会:
- ❌ 把文件乱扔在根目录,越攒越乱
- ❌ 忘记自己的记忆系统(
memory/),每次醒来都失忆 - ❌ 在多 agent 共享配置时,用
config.apply整份覆盖 openclaw.json,抹掉其他 agent 的修改
这个 skill 一次性解决:**目录结构 + 持久化规范 + 配置安全**。
特性
- 🗂️ 标准目录结构:
projects/tasks/outputs/knowledge/scripts/memory/tmp/ - 📜 WORKSPACE.md 持久化规范:重启后依然生效的目录管理规则
- 🛡️ 多 agent 配置安全:只用
config.patch,禁止config.apply覆盖他人修改 - ⚖️ 技能路径冲突仲裁:其他技能若约定与 WORKSPACE.md 冲突的输出路径,一律以工作区规范为准,由执行 agent 完成路径翻译(如
~/Downloads/research/→tasks//)——装再多技能也不乱
安装
# ClawHub(推荐)
clawhub install xiaoyaoclaw-workspace-initializer
# 或从 GitHub 手动安装
git clone https://github.com/dtsola/xiaoyaoclaw-workspace-initializer
# 把 SKILL.md 和 templates/ 放到你的 skills 目录
使用
- 把 skill 放到 OpenClaw 的 skills 目录
- 首次进入(或重置)一个工作区时,agent 会自动:
- 创建
projects/ tasks/ outputs/ knowledge/ scripts/ memory/ tmp/ - 写入
WORKSPACE.md目录规范(重启后依然生效) - 检测多 agent 场景,把「config.patch ✅ / config.apply ❌」安全规范持久化进
AGENTS.md - 在
memory/记录初始化日志
- 创建
🚀 快速上手(三步,10 分钟)
以飞书 Bot 接入为例,三步让你的 agent 拥有一个规范的家:
Step 1:接入你的 agent
新建一个智能
Related Skills
Xiaoyaoclaw Memory Distill
OpenClaw memory distillation & organization: distill conversations into MEMORY.md + daily logs, solves context
Xiaoyaoclaw Agent Orchestrator
OpenClaw multi-agent daily collaboration orchestrator - split tasks, dispatch via sessions_send, track progres
Openclaw Workspace
Claude Code skill for maintaining and optimizing OpenClaw workspace files (AGENTS.md, SOUL.md, TOOLS.md, MEMOR
Migrate Openclaw
Migrate your OpenClaw workspace to Claude Code. Converts agents to skills, preserves souls and knowledge bases
Multi Openclaw Agents
OpenClaw skill for creating and managing multiple agents - workspace setup, Telegram multi-bot config, routing
Jarface
Load the jarface skill from ~/.openclaw/workspace/projects/droneteleo/claude-code-integration/skills/jarface/S
Related Agents
Proj Init
Use this agent when bootstrapping a new project workspace during automated setup cycles. Typical triggers incl
Vault Curator
Decides which session artifacts deserve long-lived storage in the Obsidian vault and writes the survivors via
Fleet Review Alt
Independent second reviewer on a different model. Use for risky changes that deserve two reviews, or when the