agent-builder-plusBuild high-performing OpenClaw agents end-to-end with comprehensive safety features. Use when you want to design a new agent (persona + operating rules) and...
Install via ClawdBot CLI:
clawdbot install ykaixu/agent-builder-plusGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval (Calls external URL not in known-safe list
https://api.example.com/v1AI Analysis
The skill definition describes an agent-building workflow with no direct evidence of credential harvesting, data exfiltration, or hidden malicious instructions. The flagged external API call is generic ('api.example.com'), appears to be placeholder evidence, and is not part of the skill's actual documented behavior. The primary risk is theoretical, stemming from the potential for generated agent code to include unsafe commands, but the skill itself is a design tool.
Audited Apr 17, 2026 · audit v1.0
Generated Mar 1, 2026
Build an agent to handle customer inquiries on Telegram or WhatsApp, providing automated responses for common issues, escalating complex cases, and maintaining a warm, professional tone. It can operate as an Operator with non-destructive actions like fetching order details, while prohibiting sharing sensitive data.
Create an agent for internal company use on Feishu or Discord, assisting with scheduling, document retrieval, and meeting summaries in groups or DMs. Configured as an Advisor to suggest actions only, with memory for tracking project updates and a concise tone to avoid clutter.
Design an agent for personal wellness on iMessage, offering daily reminders, fitness tips, and nutrition advice in private sessions only. Set to Autopilot for proactive suggestions, with prohibitions against medical diagnoses and memory for logging user progress in MEMORY.md.
Develop an agent for financial guidance on dedicated channels, providing market updates, investment insights, and budget planning tools. Use Operator autonomy to ask before executing trades, with strict prohibitions on unauthorized transactions and tool-first posture for data verification.
Build an agent for online learning platforms, answering student questions, providing study resources, and tracking progress in group chats or DMs. Configure as an Operator to handle non-destructive tasks like quiz generation, with memory for lesson history and a narrative tone for engagement.
Offer the agent-building skill as a cloud-based service with tiered pricing, targeting businesses needing custom automation. Revenue comes from monthly subscriptions based on agent complexity and support levels, with upsells for advanced safety features.
Provide professional services to design and deploy agents for clients, including integration with existing systems and ongoing maintenance. Revenue is generated through project-based fees and retainer agreements for updates and monitoring.
Distribute a free version of the skill with basic features, monetizing through premium upgrades for advanced capabilities like anti-deadlock protection and multi-channel support. Revenue streams include one-time purchases for pro features and enterprise licenses.
💬 Integration Tip
Ensure channel conflict prevention by verifying existing bindings with openclaw agents list before registering new agents to avoid hijacking main agent channels.
Scored May 30, 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...