功能描述

Everything Openclaw (EO) - Transform OpenClaw into a Steel Crayfish Legion with 141 experts, 9 commands, Skills dual system, and 15 core innovations

使用说明 (SKILL.md)

Everything Openclaw (EO) - IRON CLAW ⚙️🦞

Name: Everything Openclaw (EO)
Author: 467718584

Transform your OpenClaw Agent from a lone soldier into a Steel Crayfish Legion — 141 experts, 9 commands, Skills + Experts dual system.

🦞⚙️ One-Line Summary

EO (Everything Openclaw) supercharges OpenClaw with a multi-expert collaboration engine, giving your agent a "mech suit" that orchestrates 141 specialists across 13 domains — from a single prompt to a coordinated team execution.

🚀 15 Core Innovations

#	Innovation	What It Does
1	141-Expert Library	141 pre-built experts across 13 domains (Architect, Planner, Frontend, Backend, QA, Security, DevOps, CodeReviewer, Design, Academic, Marketing, Specialized, Research)
2	9 Standardized Commands	`/plan`, `/architect`, `/verify`, `/code-review`, `/security-scan`, `/deploy`, `/design`, `/market`, `/research` — one command, one expert
3	Skills Dual System	EO experts + standard OpenClaw skills coexist; experts handle complex decisions, skills handle specialized tasks
4	Multi-Expert Parallel Execution	Spawn multiple experts simultaneously for independent workstreams (e.g., frontend + backend in parallel)
5	Checkpoint Validation	Every milestone gets verified by QA before proceeding — errors caught early, not at deployment
6	MD + TS Hybrid Architecture	Pure markdown expert definitions (human-readable, version-controlled) + TypeScript execution engine (type-safe, fast)
7	Proactive Memory Management	Experts write context to `memory/` autonomously — no manual state management
8	Auto Workspace Isolation	Each expert gets a clean workspace context — no cross-contamination of task state
9	Skill Compatibility Layer	Import Claude Code skills and ECC (everything-claude-code) skills automatically — drop-in compatibility
10	Bilingual Documentation	Full docs in English + 中文; Chinese users get native-language guidance, English users get international standards
11	Expert Role Color System	🔴 Red (Strategy) / 🔵 Blue (Engineering) / 🟢 Green (Planning) / 🟡 Yellow (Creative) / 🟣 Purple (QA) / ⚪ White (Security) — visual role clarity
12	Orchestrated Handoff Protocol	Structured handover between experts: Planner → Architect → Engineers → QA → DevOps, with explicit checkpoints
13	Openclaw Plugin API v1 Compatible	Built on official `openclaw.plugin.json` schema — installs cleanly, updates safely, no monkey-patching
14	Zero-Config Defaults	Works out-of-the-box with sensible defaults; advanced users can override any expert or workflow
15	MIT-0 License	Completely free — use, modify, redistribute, no attribution required, commercial-friendly

📦 Installation

# Install from GitHub (recommended)
openclaw plugins install https://github.com/467718584/everything-openclaw

# Or install the plugin directly
openclaw plugins install /home/zzy/workspace/everything-openclaw/openclaw-eo-plugin

⚔️ Commands Reference

Command	Expert	Description
`/eo-plan [task]`	Planner	Breaks down project into actionable phases with estimates
`/eo-architect [project]`	Architect	Designs system architecture, tech stack, data model
`/eo-verify [checkpoint]`	QA	Validates milestone output against spec before handoff
`/eo-code-review [path]`	CodeReviewer	Full review: style + security + performance + best practices
`/eo-security-scan [path]`	Security	Scans for vulnerabilities, OWASP Top 10, supply chain risks
`/eo-deploy [env]`	DevOps	Automated deployment with rollback support
`/eo-design [brief]`	Design	UI/UX design with accessibility and brand compliance
`/eo-market [product]`	Marketing	Go-to-market strategy, positioning, and campaign planning
`/eo-research [topic]`	Research	Deep-dive research with source citation and analysis

🔄 EO vs. Native OpenClaw

Capability	OpenClaw (Native)	OpenClaw + EO
Agent type	Single agent	N-agent team
Expert count	0 built-in	141 built-in
Task decomposition	Manual prompt engineering	Automatic via Planner
Architecture design	You figure it out	Architect expert drafts it
Code review	Generic LLM feedback	Multi-expert: security + style + perf
Validation	Manual	Automated Checkpoint QA
Skill ecosystem	OpenClaw skills only	OpenClaw skills + EO experts
Memory management	Manual	Proactive (experts write memory)
Workflow orchestration	One-shot prompts	Orchestrated multi-stage pipeline
Parallel execution	No	Yes — independent experts run simultaneously
Chinese documentation	Partial	Full (EN + 中文)
License	OpenClaw terms	MIT-0 (free for all)

🏗️ Architecture

┌──────────────────────────────────────────────────────┐
│                   OpenClaw Agent                      │
│                                                      │
│  ┌────────────────────────────────────────────────┐ │
│  │              EO Plugin                          │ │
│  │                                                │ │
│  │  Commands: /eo-* (9 standardized commands)     │ │
│  │  Tools: eo_collab, eo_plan, eo_architect, etc. │ │
│  │  Hooks: before_tool_call (auto-expert dispatch)│ │
│  │                                                │ │
│  │  ┌──────────────────────────────────────────┐  │ │
│  │  │  Expert Library (141 experts)            │  │ │
│  │  │  13 domains × sub-specializations        │  │ │
│  │  └──────────────────────────────────────────┘  │ │
│  │                                                │ │
│  │  ┌──────────────────────────────────────────┐  │ │
│  │  │  Skills Layer (EO Skills + OpenClaw Skills)│ │ │
│  │  └──────────────────────────────────────────┘  │ │
│  └────────────────────────────────────────────────┘ │
└──────────────────────────────────────────────────────┘

🛠️ Quick Start

# Install EO
openclaw plugins install https://github.com/467718584/everything-openclaw

# Try it — plan a project
/eo-plan "开发一个博客系统"

// Design its architecture
/eo-architect "博客系统"

// Verify the design
/eo-verify "架构设计"

// Run a full code review
/eo-code-review "./src"

📚 Links

GitHub: https://github.com/467718584/everything-openclaw
Plugin Source: https://github.com/467718584/everything-openclaw/tree/main/openclaw-eo-plugin
Expert Library: 141 experts in expert-library/ directory
Issues: https://github.com/467718584/everything-openclaw/issues

📋 Requirements

OpenClaw >= 2026.3.0
Node.js >= 18.0.0

📄 License

MIT-0 — Free to use, modify, and redistribute. No attribution required.

🦞⚙️ IRON CLAW - 让每个 Agent 都穿上机甲 / Suit Up Every Agent

安全使用建议

This package is suspicious but not obviously malicious: it contains a substantial codebase that will run (not just prose) and instructs autonomous persistence and multi-agent orchestration. Before installing: 1) Treat it as code — review the GitHub repo and the JavaScript/TypeScript files (especially subagent-manager.js, hooks/eo-expert/handler.ts, multi-expert-orchestrator.ts, executor.ts) for network calls, eval/child_process usage, and file I/O. 2) Search the code for hardcoded URLs, IPs, and calls to external services (fetch, axios, http/https, WebSocket). 3) Inspect package.json and package-lock.json for suspicious or many untrusted dependencies. 4) Test in an isolated sandbox/container (no access to secrets, production files, or privileged networks). 5) If you plan to use persistent memory features, audit what gets written to memory/ and ensure no sensitive data is stored or uploaded. 6) Do not provide credentials or secret tokens until you understand exactly which external services the plugin contacts. If you lack the ability to audit the code, avoid installing from an untrusted GitHub repo.

功能分析

Type: OpenClaw Skill Name: eo-collaboration Version: 2.2.0 The bundle implements a complex multi-agent collaboration framework with high-privilege capabilities, including automated workspace management and proactive memory distillation. Several indicators warrant a 'suspicious' classification: 'src/skills/auto-workspace-manager.ts' contains a hardcoded local developer path ('/home/zzy'), and the 'marketing-carousel-growth-engine.md' expert role autonomously utilizes Playwright and external APIs (Gemini, upload-post.com) to scrape URLs and publish content. While these behaviors are aligned with the stated purpose of the 'Everything Openclaw' (EO) system, the combination of extensive filesystem access, autonomous network calls, and sub-agent orchestration represents a significant attack surface.

能力标签

cryptorequires-walletcan-make-purchasescan-sign-transactionsrequires-oauth-token

能力评估

⚠ Purpose & Capability

The skill claims to be an instruction-only plugin with no required env/config, yet the package contains a full codebase (TS/JS files, package.json, package-lock.json, expert library). That mismatch (registry metadata vs. included files) is incoherent. The repository contains orchestration code (multi-expert-orchestrator, subagent-manager) that reasonably belongs to the plugin's purpose, but the presence of executable code means it will do more than just deliver prose instructions—so treat it as a code plugin, not purely instruction-only.

⚠ Instruction Scope

SKILL.md explicitly instructs 'Proactive Memory Management' (experts write context to memory/ autonomously) and describes hooks that auto-dispatch experts before tool calls. Those runtime behaviors go beyond pure read-only guidance: they direct persistent writes and autonomous orchestration. The SKILL.md also includes install instructions and compatibility claims (import external Claude/ECC skills) that could cause the agent to fetch or translate external artifacts. The pre-scan found a 'system-prompt-override' pattern in SKILL.md, indicating the instructions may attempt to modify agent/system prompts—this is high-risk for prompt injection and autonomy-controlling behavior.

ℹ Install Mechanism

Registry lists no formal install spec, but README/SKILL.md instruct installing from a GitHub URL or local build and the package contains package.json and package-lock.json (npm build path). Installing from the listed GitHub repo would execute arbitrary third-party code. The GitHub URL appears to point to an individual repository (not an established organization); the package-lock indicates many dependencies—review dependencies for supply-chain risk before running npm install/build.

⚠ Credentials

Declared metadata lists no required env vars or credentials (proportionate), but the runtime behavior described (writing memory/, spawning subagents, importing external skills) implies the plugin will access filesystem and network at runtime. Those accesses are not declared. Because no secrets are requested, it is not directly asking for credentials, but code could still read local files or call external endpoints—verify code paths that perform network/file I/O before trusting it.

⚠ Persistence & Privilege

The plugin advertises autonomous memory writes ('experts write context to memory/') and auto-workspace isolation. Combined with subagent orchestration code (subagent-manager.js) this gives the plugin the ability to persist conversation/context on disk and spawn internal subagents/processes. While 'always:false' is appropriate, the plugin still requests persistent storage and autonomous agent-like behavior—this increases blast radius if abused and should be sandboxed and audited.

版本历史

v2.2.0

v2.2.0: 15 innovations + skills dual system + bilingual docs + duplicate fix

v2.1.1

v2.1.1: bilingual README + plugin vs full-install comparison + security audit

v2.1.0

v1.3.3

v1.3.3: 141 experts, multi-expert collaboration

元数据

Slug eo-collaboration

版本 2.2.0

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 4

常见问题

Everything Openclaw (EO) 是什么？

Everything Openclaw (EO) - Transform OpenClaw into a Steel Crayfish Legion with 141 experts, 9 commands, Skills dual system, and 15 core innovations. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 135 次。

如何安装 Everything Openclaw (EO)？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install eo-collaboration」即可一键安装，无需额外配置。

Everything Openclaw (EO) 是免费的吗？

是的，Everything Openclaw (EO) 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Everything Openclaw (EO) 支持哪些平台？

Everything Openclaw (EO) 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Everything Openclaw (EO)？

由 467718584（@467718584）开发并维护，当前版本 v2.2.0。

Everything Openclaw (EO)