kimi-agent-policyKimi (Moonshot AI) agent tool-use policy ported to OpenClaw. Covers step limits, web search, image search, data sources, ipython, memory, content display, an...
Install via ClawdBot CLI:
clawdbot install 2233admin/kimi-agent-policyGrade 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://example.comAudited Apr 18, 2026 · audit v1.0
Generated Mar 21, 2026
Marketing teams can use the agent to conduct real-time web searches and data source lookups to gather up-to-date market trends, competitor pricing, and consumer sentiment. The step and search limits ensure focused, efficient sessions, while memory tools help track findings across multiple research cycles.
Educators and content creators can leverage the agent to verify facts, search for images, and generate visual aids using tools like agent-browser and baoyu-danger-gemini-web. The content display rules ensure proper citation and formatting, making it suitable for creating accurate, engaging learning materials.
IT support teams can use the agent to search for error solutions, fetch documentation via URLs, and execute Python code for data analysis or calculations. The memory tools help retain session history for recurring issues, improving response consistency and efficiency.
Financial analysts can utilize the agent to pull real-time data from web searches, process it with Python exec for calculations, and generate visualizations. The strict tool-use policy ensures reliable, verifiable outputs for high-stakes topics like finance and legal compliance.
Designers can employ the agent to search for inspiration images, generate new visuals with baoyu-danger-gemini-web, and create interactive HTML prototypes. The content display rules encourage creative typography and animations, avoiding generic styles for more innovative outputs.
Offer a subscription-based platform where businesses integrate this agent skill into their daily operations, such as research, content creation, or support. Revenue comes from tiered plans based on usage limits, priority support, and advanced features like custom memory management.
Provide a free version with basic tool limits (e.g., 5 steps per turn) to attract freelancers, educators, and small teams, then upsell to premium plans with increased limits, additional skills like baoyu-slide-deck, and enhanced memory capabilities. Revenue is generated through premium upgrades and one-time purchases for specialized skills.
Target large organizations by offering custom integration of this agent skill into existing systems, along with consulting for policy adaptation and training. Revenue streams include licensing fees, implementation projects, and ongoing maintenance contracts, leveraging the agent's structured tool-use for compliance and efficiency.
💬 Integration Tip
Start by mapping existing Kimi workflows to OpenClaw equivalents using the tool table, then gradually introduce memory tools and content rules to ensure smooth adoption without overwhelming users.
Scored Apr 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.
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.
Local Python orchestration skill: multi-agent workflows via shared blackboard file, permission gating, token budget scripts, and persistent project context....
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