agent-advisor模型推荐 + OpenClaw 安全系数分析工具。当用户询问"用哪个模型"、"推荐模型"、"适合什么模型"、"安全系数"、"openclaw 安全"、"根据历史"时触发。功能：(1) 根据历史会话自动分析任务类型并推荐最优的 Claude 模型（auto 模式），(2) 根据用户描述的任务推荐最优模型（recom...
Install via ClawdBot CLI:
clawdbot install mrkangzubin/agent-advisorGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Mar 21, 2026
A development team working on a complex system design project uses the auto mode to analyze recent coding sessions, automatically recommending the optimal Claude model (e.g., claude-opus-4-6 for architecture tasks) based on historical task frequency, improving efficiency and reducing manual model switching.
A content agency handling varied tasks like writing, translation, and summarization uses the recommend mode with user descriptions to match tasks (e.g., daily coding or simple formatting) to appropriate models like claude-sonnet-4-6 or claude-haiku-4-5, ensuring fast and accurate outputs tailored to specific needs.
An IT department conducts regular security audits by running the security mode to calculate the OpenClaw gateway's safety score from local openclaw.json, identifying weaknesses in authentication or network binding and following improvement suggestions to enhance system security and meet compliance standards.
An online learning platform integrates the full mode to provide students with both model recommendations for homework tasks (e.g., coding exercises or essay writing) and security reports for their local setups, offering a comprehensive tool that balances performance and safety in educational environments.
Offer tiered subscriptions where users pay monthly or annually to access advanced features like detailed security analytics, priority model recommendations, and automated reports, targeting small to medium businesses that rely on AI for daily operations.
Sell enterprise licenses to large organizations for integrating the skill into their internal AI workflows, including custom deployments, dedicated support, and tailored security configurations, ensuring seamless operation within corporate IT infrastructures.
Provide a free basic version with limited functionality (e.g., basic model recommendations) and charge for premium features such as enhanced security scoring, historical analysis, and batch processing, appealing to individual developers and startups looking to scale.
💬 Integration Tip
Ensure openclaw.json is properly configured and accessible locally, and test the skill in a controlled environment before deployment to avoid security risks.
Scored Apr 19, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...