create-subagent创建和管理 SubAgent(子智能体)。使用当用户需要:(1) 创建新的 SubAgent 执行特定任务,(2) 查看/管理已有的 SubAgent,(3) 终止或指导 SubAgent。支持多种预设类型:开发、研究、写作、数据分析等。
Install via ClawdBot CLI:
clawdbot install aning35/create-subagentGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
exec (Calls external URL not in known-safe list
https://clawhub.ai/skills/create-subagentAI Analysis
The skill's primary function is managing subagents within the platform, with no evidence of unauthorized data exfiltration or credential harvesting. The external URL is the skill's documented homepage, and the shell command reference is a documented tool for data analysis subagents, not a hidden instruction.
Audited Apr 17, 2026 · audit v1.0
Generated Mar 22, 2026
Agencies can use this skill to create dedicated development SubAgents for each client project, handling tasks like coding, debugging, and documentation. This streamlines project management by assigning specialized AI agents to specific development needs, improving efficiency and reducing manual oversight.
Research teams can deploy SubAgents for literature reviews, data analysis, and report writing, allowing researchers to focus on hypothesis testing. This accelerates the research process by automating information gathering and synthesis, enhancing productivity in academic or corporate settings.
Marketing firms can create writing SubAgents to generate blog posts, social media content, and technical documentation, ensuring consistent output across campaigns. This reduces content creation time and allows human editors to focus on strategy and quality control.
Consultancies can use data SubAgents to clean, analyze, and visualize client datasets, providing quick insights and reports. This enables handling multiple client projects simultaneously with tailored AI agents, improving scalability and data-driven decision-making.
Offer tiered subscriptions where users pay monthly for access to a set number of SubAgent creations and management features. This model ensures recurring revenue and can include premium support or advanced customization options for higher tiers.
Charge users per SubAgent creation or based on usage time, appealing to occasional users or small businesses. This flexible model allows low entry costs and can scale with user needs, generating revenue from high-volume or long-running agents.
Sell enterprise licenses to large organizations for unlimited SubAgent usage, integration with internal systems, and dedicated support. This model targets corporations needing robust AI agent management, providing high-value contracts and long-term partnerships.
💬 Integration Tip
Ensure the openclaw-config.json file includes subagents.allowAgents settings and restart the Gateway after configuration to enable seamless SubAgent creation and management.
Scored Jun 19, 2026
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4) Establishing review and quality gates, (5) Managing async communication and artifact sharing between agents.
A unified OpenClaw skill that merges self-improvement and proactivity: learn from corrections, maintain active state, recover context fast, and keep work mov...
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Automatically assess task complexity and adjust reasoning level. Triggers on every user message to evaluate whether extended thinking (reasoning mode) would improve response quality. Use this as a pre-processing step before answering complex questions.
Associative memory with spreading activation for persistent, intelligent recall. Use PROACTIVELY when: (1) You need to remember facts, decisions, errors, or...