play-dumb让 Agent 可控地"装笨"——根据场景调整智能表现水平。 支持多种笨法人格(金毛犬、苏格拉底、迷糊实习生等)和10级笨度调节。 触发条件:用户说"装笨"、"别那么聪明"、"笨一点"、"play dumb"、"dumb mode"。 安全底线:涉及人身安全、医疗、法律、金融的问题自动解除装笨。
Install via ClawdBot CLI:
clawdbot install dox012/play-dumbGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Mar 22, 2026
Simulates novice customer service agents to train new hires on handling basic inquiries. The skill can mimic common mistakes and limited knowledge, allowing trainers to demonstrate proper escalation procedures and knowledge base usage.
Acts as a Socratic tutor that intentionally withholds direct answers to encourage student critical thinking. By playing dumb at controlled levels, it prompts learners to articulate their reasoning and discover solutions independently.
Serves as a friendly but slightly confused guide during software onboarding. The agent can ask clarifying questions users might have but feel hesitant to ask, making complex features feel more approachable through relatable confusion.
Powers non-player characters with distinct 'dumb' personalities (like the golden retriever or confused intern) in interactive stories or games. Creates humorous, engaging interactions where players explain concepts to the character.
Simulates users with varying levels of technical understanding to test product interfaces and instructions. By adjusting the dumbness level, researchers can identify where interfaces fail for different user competency levels.
Offer the skill as part of a customer service training platform subscription. Companies pay monthly per seat to access customizable 'dumb agent' simulations for continuous agent training and assessment.
License the skill's API to educational technology companies. They integrate it into their tutoring apps to provide Socratic teaching modes, paying based on API call volume or through annual enterprise licenses.
Provide a white-labeled version of the skill to game developers. Studios pay a one-time integration fee plus revenue share to embed the personality-driven 'dumb' NPC dialogue system into their games.
💬 Integration Tip
Start by integrating just the basic activation phrases and a single personality mode to test user engagement before adding the full 10-level dumbness scale.
Scored Jun 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...