Skill Operator (PassDeck)

The Skill Operator serves as the orchestration and orchestration engine for collaborative agent sessions. It provides high-performance persistence using Loro-CRDT with an append-only log architecture, ensuring that data is never lost and remains consistent across all agents.

3,880 stars

Best use case

Skill Operator (PassDeck) is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

The Skill Operator serves as the orchestration and orchestration engine for collaborative agent sessions. It provides high-performance persistence using Loro-CRDT with an append-only log architecture, ensuring that data is never lost and remains consistent across all agents.

Teams using Skill Operator (PassDeck) should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/operator-skill/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/404-unknow/operator-skill/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/operator-skill/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How Skill Operator (PassDeck) Compares

Feature / AgentSkill Operator (PassDeck)Standard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

The Skill Operator serves as the orchestration and orchestration engine for collaborative agent sessions. It provides high-performance persistence using Loro-CRDT with an append-only log architecture, ensuring that data is never lost and remains consistent across all agents.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Skill Operator (PassDeck)

The Skill Operator serves as the orchestration and orchestration engine for collaborative agent sessions. It provides high-performance persistence using Loro-CRDT with an append-only log architecture, ensuring that data is never lost and remains consistent across all agents.

## 💾 Core Actions

### `team.create`
- **Description**: Initializes a new persistent collaborative session on disk. Creates the initial snapshot and metadata.
- **Parameters**: `{ taskName: string }`
- **Output**: `{ sessionId: string, status: 'Persisted' }`

### `team.sync`
- **Description**: Securely appends an incremental CRDT update to the session log. Every update is verified using Ed25519 signatures from the originating agent before persistence.
- **Parameters**: `{ sessionId: string, updatePayload: base64, publicKeyHex: string, signatureHex: string }`
- **Output**: `{ success: true, version: string }`

### `team.load`
- **Description**: Recovers the full state of a collaborative session by merging the base snapshot with the incremental update log. Provides a "crash-proof" state recovery mechanism.
- **Parameters**: `{ sessionId: string }`
- **Output**: `{ payload: base64, format: 'full-merged-snapshot' }`

## 🛡️ Key Features
- **Performance**: O(1) incremental sync performance.
- **Fault-Tolerance**: Instant crash recovery via Snapshot + WAL (Write-Ahead Logging).
- **Security**: Built-in Ed25519 signature verification for every sync operation.

Related Skills

pentest-c2-operator

3891
from openclaw/skills

Set up authorized C2 simulation workflows and measure defensive detection outcomes.

Security

archtree-community-operator-en

3891
from openclaw/skills

Use this skill for Archtree community operations inside a live instance, including browsing channels, reading posts, posting, replying, liking/unliking, reviewing your own activity, editing or deleting your own content, community patrol, and limited proactive participation after authorization. Trigger it when the user mentions Archtree, archtree.cn, the community, channels, posts, community activity, or asks to check recent discussions, find questions worth replying to, post, reply, like, review what they posted, edit a post, delete a reply, patrol the community, or summarize recent activity. Route website login, token setup, page confirmation, account confirmation, and MCP-based reads and writes correctly. Do not use it for Archtree development, deployment, debugging, infrastructure work, or modifying the codebase, frontend, MCP service, or APIs.

archtree-community-operator-cn

3891
from openclaw/skills

在 Archtree 社区实例内执行社区浏览、频道查看、帖子阅读、发帖、回帖、点赞/取消点赞、查看自己内容、编辑或删除自己内容、社区巡查和轻量社区运营动作时使用本 skill。只要用户明确提到 Archtree、archtree.cn、社区、频道、帖子、社区动态,或表达“去社区看看最近在聊什么”“帮我找值得回复的问题”“帮我在社区发帖 / 回帖 / 点赞”“帮我看看我发过什么”“帮我改一下这条帖子”“帮我删掉这条回复”“帮我巡查社区”“看看 Archtree 最近有什么值得参与的话题”“帮我总结社区最近动态”这类意图,就应优先使用本 skill,即使用户没有明确说出“MCP”或“skill”。本 skill 负责在网站登录 / token 准备 / 页面确认、账号确认与 MCP 社区读写之间做正确路由,并在获得授权后进行有限度的主动参与。不要用于开发、部署、排障、调试、修复或修改 Archtree 本身的代码、前端页面、MCP 服务、接口实现或其他基础设施问题。

aiheal-cli-operator

3891
from openclaw/skills

Operate and troubleshoot the AIHealingMe CLI through the npm package (`aihealingmecli`). Use when tasks involve auth/user/audio/plan/chat/emotion/subscription workflows, payload shaping, command diagnostics, and API failure handling.

bamdra-memory-upgrade-operator

3891
from openclaw/skills

Safely install, uninstall, reinstall, or upgrade the Bamdra OpenClaw memory suite when stale config, existing plugin directories, or partial installs break normal `openclaw plugins install` flows.

pet-operator

3891
from openclaw/skills

Delegate Aavegotchi petting rights to AAI's wallet on Base. Generate approve/revoke tx data, check approval, and maintain delegated wallet bookkeeping in pet-me-master config.

xiaohongshu-assistant-operator

3891
from openclaw/skills

Fully automated Xiaohongshu content operator for the specific creator "Bu Zhuan Dao Da Mo Xing Bu Gai Ming" (ID: 4740535877). Use when generating, publishing, and managing daily Xiaohongshu notes as the creator's assistant, including: (1) reading recent notes to infer direction, (2) scanning industry trends (LLM / Agent / RAG), (3) deciding daily themes (3 posts/day), (4) controlled promotion of the 199 note only, (5) cold-start strategy management, (6) automated publishing with strict validation, and (7) scheduled comment interaction. Trigger when operating this specific account end-to-end.

Agent Communication Skill (PassDeck)

3891
from openclaw/skills

This skill provides the security and networking foundation for AI Agent swarms. It handles DID (Decentralized Identity) registration, cryptographically secure signing using Ed25519, and E2EE (End-to-End Encryption) for sensitive data.

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research