Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Workspace Directory Manager

ASecurity

Workspace directory manager — maintain cleanliness of ~/.openclaw/ and ~/clawd/

92 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentspythonbash

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add aAAaqwq/AGI-Super-Team --skill workspace-directory-manager --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Workspace Directory Manager?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Workspace Directory Manager
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aaaaqwq-workspace-directory-manager-agi-super-team/badge)](https://www.skillsdirectory.com/skills/aaaaqwq-workspace-directory-manager-agi-super-team)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: workspace-directory-manager
description: Workspace directory manager — maintain cleanliness of ~/.openclaw/ and ~/clawd/
---

# Skill: OpenClaw & Workspace Directory Manager

## 触发条件
- "整理目录"、"清理文件夹"、"目录结构"
- "清理 tmp"、"清理日志"、"清理临时文件"
- "skills 整理"、"重复 skill 检查"
- "磁盘空间"、"空间不足"
- "workspace 维护"、"openclaw 维护"

## 职责
维护 `~/.openclaw/` 和 `~/clawd/` 两个目录的整洁和秩序。
**专属 agent: 小ops** — CEO 指定的小ops专用 skill。

## 目录结构规范

### ~/.openclaw/ (系统配置目录)
```
~/.openclaw/
├── openclaw.json          # 主配置(唯一真相源)
├── .env                   # 运行时环境变量(由 rebuild-env.sh 生成,chmod 600)
├── agents/
│   └── <agent-id>/agent/
│       ├── agent.json     # Agent 身份+模型+workspace
│       ├── models.json    # 模型缓存(自动生成)
│       ├── SOUL.md        # Agent 灵魂文件
│       └── AGENTS.md      # Agent 行为规则
├── skills/                # 全局安装的 Skill
├── logs/                  # 运行日志
└── memory/                # 记忆文件
```

### ~/clawd/ (工作空间目录)
```
~/clawd/
├── MEMORY.md              # 长期记忆(main session 维护,只读)
├── SOUL.md                # CEO 灵魂文件
├── AGENTS.md              # 团队规则
├── USER.md                # 用户画像
├── TOOLS.md               # 工具手册
├── IDENTITY.md            # 身份文件
├── HEARTBEAT.md           # 心跳规则
├── memory/                # 日记忆 YYYY-MM-DD.md
├── projects/              # 独立项目
├── reports/               # 研究报告
├── skills/                # 自研 Skill
├── scripts/               # 全局脚本
├── docs/                  # 文档
├── tmp/                   # 临时文件(可定期清理)
└── repos/                 # 代码仓库
```

## 执行命令

### 完整目录健康检查
```bash
python3 ~/clawd/skills/workspace-directory-manager/scripts/health-check.py
```

### 清理临时文件
```bash
python3 ~/clawd/skills/workspace-directory-manager/scripts/cleanup-tmp.py --dry-run   # 预览
python3 ~/clawd/skills/workspace-directory-manager/scripts/cleanup-tmp.py               # 执行
```

### 重复 Skill 检测
```bash
python3 ~/clawd/skills/workspace-directory-manager/scripts/detect-duplicates.py
```

### 磁盘空间报告
```bash
python3 ~/clawd/skills/workspace-directory-manager/scripts/disk-usage.py
```

### 目录结构可视化
```bash
python3 ~/clawd/skills/workspace-directory-manager/scripts/tree-view.py --path ~/clawd --depth 2
python3 ~/clawd/skills/workspace-directory-manager/scripts/tree-view.py --path ~/.openclaw --depth 2
```

## 清理规则

### tmp/ 清理
- `~/clawd/tmp/` 中超过 7 天的文件自动标记删除
- 不删除正在被 cron/session 使用的文件

### 日志清理
- `~/.openclaw/logs/` 中超过 30 天的日志自动清理
- 保留最近 7 天的详细日志

### Agent Session 残留
- 检查 agents/*/agent/ 下异常大的文件
- models.json 如果超过 10MB → 标记清理

### 重复 Skill 清理
- 对比 `~/.openclaw/skills/` 和 `~/clawd/skills/`
- 同名 skill 以 `~/.openclaw/skills/` 为准
- 功能重复的 skill 报告给 CEO 决定

## 安全铁律
1. **永不删除** `MEMORY.md`、`SOUL.md`、`AGENTS.md`、`USER.md`、`TOOLS.md`
2. **清理前 dry-run**,确认无误再执行
3. **用 `trash` 而非 `rm`**(可恢复)
4. **不修改** `openclaw.json`(除非 CEO 明确指示)
5. **memory/ 文件只追加不覆盖**

## 巡检频率
- 每 6 小时(通过 heartbeat 或 cron)运行 health-check
- 每周日运行一次 cleanup + disk-usage

## 更新记录
- 2026-03-29: 初版创建

Attribution

aAAaqwqaAAaqwq
View sourceMore from aAAaqwq →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →