Cost-optimizing model router for OpenClaw. Automatically routes each request to the cheapest capable Claude model (Haiku/Sonnet/Opus) using weighted scoring....
Generate an interactive HTML viewer to review and analyze OpenClaw conversation sessions, including history, tool calls, token usage, and debugging details.
Security agent that inventories installed OpenClaw skills, analyzes them for threats, and syncs results to your Clawned dashboard.
Dragon-class High Availability (HA) guardian with metabolic cleansing and 3-tier self-healing for OpenClaw environments.
Automates hourly OpenClaw workspace backups with SQLite database export, optional NAS sync via rsync, and GitHub version control commits and pushes.
Helps create, update, and audit OpenClaw skills to ensure high quality following Anthropic's best practices; triggered by phrases like "create a new skill" o...
Fetch and summarize Ultrahuman Ring/CGM metrics inside OpenClaw using the Ultrahuman MCP server (via mcporter). Use when the user asks about Ultrahuman data such as sleep score, total sleep, sleep sta
Generate OpenClaw model inventory and model-card images from openclaw.json. Use when asked to list all configured models, verify default/fallback chains, or...
Deploy and start OpenClaw Agent Control with one command (backend + frontend) using skill-based workflow.
--- name: signalhire description: Prospect and enrich contacts via the SignalHire API (Search, Person and Credits) metadata: openclaw: # The skill only loads when a valid API key and callback UR
Enable Telegram cross-instance chat, user mention, and personal bot setup for seamless communication among Openclaw users.
Manage Pipedrive CRM from OpenClaw using API v1, including people, organizations, deals, leads, activities, notes, pipelines, and custom endpoint actions. Us...
Comprehensive security suite for OpenClaw skills. Includes static scanning (AST + keywords) and AI-powered semantic behavior review to detect malicious code.
Todoist task management for OpenClaw. Unified todo API with multi-agent identity, scheduled checks and reminders.
管理 OpenClaw 长会话防爆机制（80%自动归档、自动轮换新会话、低 token 交接）及定时任务安装。用户提到 compacting context、会话过长、自动总结归档、sessi
Expert system for designing, deploying, optimizing, and scaling autonomous AI agents on OpenClaw with multi-agent support and robust memory management.
OpenClaw security guide for root-enabled AI agents, covering pre-install audits, runtime permission tightening, hash baselines, risk controls, nightly auto-i...
Validate OpenClaw configuration fields against the official Zod schema. Use when reading or writing openclaw.json to check if configuration fields exist and...
Schedule automatic OpenClaw and skill updates with reliable cron templates, timezone-safe scheduling, and clear summary outputs. Use for hands-off maintenance, scheduled upgrades, and concise update r
Fixes the Windows scheduled task bug that kills OpenClaw processes during idle. One script, permanent fix.
提供针对云端 OpenClaw 工作区到本地的安全实时同步方案及命令，支持多系统与同步方式选择。
OpenClaw cloud security guardrail that enforces pre-execution checks, source trust classification, taint tracking, metadata endpoint blocking, and output red...
Fetch and display OpenRouter AI models with pricing and context limits, and configure OpenClaw to use selected models via automatic or fallback settings.
Enforces regex-based, real-time authorization policies on OpenClaw agents’ tool calls, blocking, allowing, or requiring approval before execution.