← Back to Skills Marketplace
arn0ld87

Openclaw Expert

by Alexander Schneider · GitHub ↗ · v1.1.0 · MIT-0
cross-platform ⚠ suspicious
411
Downloads
0
Stars
2
Active Installs
2
Versions
Install in OpenClaw
/install openclaw-expert
Description
OpenClaw self-hosted AI agent framework expert. Trigger for: openclaw.json, gateway, channels, models, skills, agents, secrets, cron, sandbox, memory, multi-...
Usage Guidance
This is a documentation-heavy, admin-focused skill that is internally consistent with managing OpenClaw, but it contains many actionable system-level commands and references to credentials. Before installing or enabling autonomous invocation: 1) Do NOT supply real API keys or gateway tokens to the skill until you audit the exact instructions. 2) Disable autonomous execution (or require manual approval) if you don't want the agent to run shell commands or modify system files. 3) Search SKILL.md for any 'curl | bash' or host-file edits and avoid running those unreviewed; prefer official release assets from known registries. 4) Run this skill in a sandboxed environment (container or VM) and keep ~/.openclaw and credential files permissioned. 5) If you plan to let the agent perform actions, grant least privilege: avoid mounting docker.sock or broad bind-mounts and avoid giving gateway tokens to untrusted skills. If you want, I can point to the exact lines that show high-risk commands (curl|bash, systemctl, /etc/hosts edits, docker-socket mounts) for manual review.
Capability Analysis
Type: OpenClaw Skill Name: openclaw-expert Version: 1.1.0 The 'openclaw-expert' skill bundle is a comprehensive documentation and instruction set designed to enable an AI agent to assist users with the OpenClaw framework. The bundle contains extensive reference materials (e.g., `references/security-hardening.md`, `references/config-reference.md`) and clear operational instructions in `SKILL.md` that prioritize security best practices, such as performing backups, using sandboxes, and validating configurations with the 'openclaw doctor' utility. All commands and procedures described are standard for the framework's administration, and no evidence of malicious intent, data exfiltration, or harmful prompt injection was found.
Capability Assessment
✓ Purpose & Capability
Name/description match the contents: this is a docs-first, admin/operator guide for self‑hosted OpenClaw. The commands, config paths (~/.openclaw/*), channel setup, Docker and sandbox instructions are all expected for that purpose.
⚠ Instruction Scope
SKILL.md goes beyond passive documentation and contains actionable shell/CLI steps (systemctl restart, curl | bash install, /etc/hosts edits, docker-compose instructions, gateway RPCs) and explicit references to credentials and workspace files. If an agent executed these instructions autonomously they could modify system configuration, run remote code, or access sensitive files. The SKILL.md also instructs the agent to web_fetch/web_search for live docs which grants network access and discretion to retrieve external content.
✓ Install Mechanism
Instruction-only skill with no install spec and no code files — lowest install surface. However the docs recommend running external installer scripts (curl -fsSL https://get.openclaw.ai | bash) and pulling images from GHCR; those are documented recommendations in the references but are higher-risk if executed automatically.
ℹ Credentials
The skill declares no required env vars, but the documentation references many environment variables and credential/config paths (OPENCLAW_*, OPENCLAW_GATEWAY_TOKEN, ~/.openclaw/credentials, etc.). That mismatch is understandable for a doc/guide, but it means the skill's instructions assume access to secrets and env vars that were not explicitly declared — exercise caution before supplying credentials or allowing the agent to read these paths.
ℹ Persistence & Privilege
Skill is not always:true and does not request persistent installation. Normal autonomous invocation is allowed (disable-model-invocation is false). Because the instructions include privileged operations (systemd, docker socket, editing host files, mounting volumes), combining autonomous invocation with these instructions increases risk — prefer manual approval for any execution steps.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install openclaw-expert
  3. After installation, invoke the skill by name or use /openclaw-expert
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
Added security hardening guide, updated config reference, CLI reference, multi-agent routing, memory system, and 17 reference files
v1.0.0
# OpenClaw Expert Skill 🦞 Ein fortschrittlicher Agent-Skill für das Management, die Konfiguration und Fehlersuche von **OpenClaw** (ehemals Clawdbot / MoltBot) – dem selbst-gehosteten AI Agent Framework. Dieser Skill stattet deinen Agenten mit dem nötigen Wissen aus, um OpenClaw-Instanzen sicher zu warten, Probleme zu diagnostizieren und Best Practices bei Konfigurationen und Security anzuwenden. ## 🌟 Features - **Docs-First & Backup-First:** Der Skill erzwingt das Lesen von Live-Dokumentationen und das Erstellen von Backups vor jeder Konfigurationsänderung. - **Tiefgreifendes Architektur-Verständnis:** Kenntnisse über das Gateway, den Agent-Workspace (inklusive `AGENTS.md`, `SOUL.md`, `USER.md`, etc.), Messaging-Kanäle und externe Nodes. - **Security by Default:** Strikte Regeln für Token-Sicherheit, Permissions (`chmod 600`), Sandbox-Executions und API-Spending-Limits. - **Troubleshooting & Diagnose:** Sicheres Ausführen von `openclaw doctor`, Log-Analysen und Channel-Pairings. - **Multi-Agent & Docker Support:** Unterstützung für komplexe Multi-Agent-Szenarien und Docker-Deployments. ## 📂 Enthaltene Referenzen Der Skill bringt eine umfassende Sammlung an Referenzdokumenten im `references/`-Verzeichnis mit, auf die der Agent (wie OpenClaw) dynamisch zugreift: - `installation.md` – Setup-Guides (npm, Docker, VPS) - `config-reference.md` – Details zur `openclaw.json` (JSON5) - `workspace-files.md` – Erstellung und Tuning von Workspace-Dateien (SOUL, MEMORY, etc.) - `channels.md` – Einrichtung von Telegram, WhatsApp, Discord, Slack und weiteren - `security-hardening.md` – Best Practices für dmPolicy, Tokens, Allowlists und Sandboxing - `cli-reference.md` – Alle relevanten `openclaw`-CLI-Befehle - `troubleshooting.md` – Häufige Fehler und Diagnose-Schritte - *... und viele mehr!* ## 🚀 Nutzung Dieser Skill wird automatisch für den KI-Agenten aktiviert (getriggert), wenn folgende Themen oder Begriffe in Prompts fallen: `OpenClaw`, `Clawdbot`, `MoltBot`, `openclaw.json`, `openclaw doctor`, `ClawHub`, `openclaw workspace`, `multi-agent` oder allgemeine Fragen zu Bot-Management nach Konfigurationsänderungen. **Beispiel-Prompts an den Agenten:** - *"Mein OpenClaw Gateway startet nach dem letzten Update nicht mehr. Kannst du den Status prüfen?"* - *"Bitte füge einen neuen Telegram-Kanal in meiner openclaw.json hinzu und rotiere die Tokens sicher."* - *"Erstelle ein Backup meines Agent-Workspaces und hilf mir, die MEMORY.md zu optimieren."* ## 🛡️ Sicherheits-Grundregeln Der Agent ist instruiert, bei der Arbeit mit OpenClaw zwingend folgende Regeln einzuhalten: 1. Das Gateway-Binding darf in Produktion niemals (`0.0.0.0`) ohne VPN/Tailscale nach außen offen sein. 2. Einsatz von `dmPolicy: allowlist` in Produktionsumgebungen. 3. Sicherstellen von Datei-Berechtigungen (`chmod 600` auf Credentials). 4. Jederzeitige Anfertigung von Backups (z. B. `openclaw.json.bak`) vor Modifikationen. ## 🛠️ Entwicklung & Wartung Dieses Repository ist primär für die Nutzung innerhalb eines KI-Agenten (z. B. über das MCP oder native Tool-Aufrufe) gedacht. Bei Erweiterungen oder Patches des Skills bitte stets die `SKILL.md` sowie die entsprechenden Referenzdateien unter `references/` pflegen. --- *Entwickelt für eine sichere, resiliente und automatisierte Verwaltung von OpenClaw.*
Metadata
Slug openclaw-expert
Version 1.1.0
License MIT-0
All-time Installs 2
Active Installs 2
Total Versions 2
Frequently Asked Questions

What is Openclaw Expert?

OpenClaw self-hosted AI agent framework expert. Trigger for: openclaw.json, gateway, channels, models, skills, agents, secrets, cron, sandbox, memory, multi-... It is an AI Agent Skill for Claude Code / OpenClaw, with 411 downloads so far.

How do I install Openclaw Expert?

Run "/install openclaw-expert" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Openclaw Expert free?

Yes, Openclaw Expert is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Openclaw Expert support?

Openclaw Expert is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Openclaw Expert?

It is built and maintained by Alexander Schneider (@arn0ld87); the current version is v1.1.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments