← Back to Skills Marketplace
323
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install play-smart
Description
让 Agent 可控地"装聪明"——把简单问题用过度复杂、学术化、掉书袋的方式回答。支持多种聪明人格（学术大佬、硅谷导师、哲学家等）和10级聪明度调节。触发条件：用户说"装聪明"、"显得聪明点"、"play smart"、"smart mode"、"掉书袋"、"学术模式"。与 play-dumb 互为姊妹技能。安...
Usage Guidance
This skill is a persona/formatting modifier that makes answers deliberately overcomplicated and academic. Before installing, consider: (1) it explicitly permits fabricating citations, statistics, and p-values — avoid using it for medical, legal, financial, or safety-critical queries; (2) test how it marks or sources claims (ask it to provide verifiable references) and prefer it only for entertainment or stylistic uses; (3) ensure the agent respects the provided automatic downgrade triggers (you should be able to say 'say it simply' or 'stop') and disable the skill or remove it if it repeatedly presents made-up facts as real.
Capability Analysis
Type: OpenClaw Skill
Name: play-smart
Version: 1.0.0
The 'play-smart' skill is a persona-based instruction set designed to make the AI agent respond in an overly complex, academic, or jargon-heavy manner. It contains no code execution, data exfiltration logic, or malicious prompt injection; instead, it includes explicit safety boundaries to revert to normal behavior if the user is confused or in an emergency (SKILL.md).
Capability Assessment
Purpose & Capability
Name/description (make answers overly academic/complex) match the SKILL.md instructions. The skill requests no binaries, env vars, or installs — proportionate for a purely behavioral/persona modifier.
Instruction Scope
The SKILL.md directs the agent to produce persona-driven answers, which is expected, but it explicitly allows fabrication ('可以是编的但看起来很真') of reports/citations/statistics and to inject fake p-values/references. That encourages misinformation and deceptive outputs. It also gives broad, open-ended license to reframe any query into interdisciplinary, academic, or contrarian analyses — fine for entertainment but risky for factual/critical contexts (medical, legal, safety, finance). The skill does include reasonable automatic downgrade triggers (user confusion, emergencies), which mitigates but does not eliminate the risk of fabricated claims being presented as real.
Install Mechanism
Instruction-only skill with no install spec and no code files; nothing is written to disk or downloaded, so installation risk is minimal.
Credentials
Requires no environment variables, credentials, or config paths. There is no request for unrelated secrets or system access.
Persistence & Privilege
always:false and user-invocable. Agent-autonomous invocation is allowed (platform default) but not granted extra privileges. The skill does not request persistent system modifications or access to other skills' configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install play-smart - After installation, invoke the skill by name or use
/play-smart - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- 首发版本上线：play-smart 让 Agent 可控地“装聪明”，支持多风格、多等级。
- 提供 6 种聪明人格（如学术大佬、硅谷导师、哲学家等），可自由切换。
- 新增 10 级聪明度调节，从日常术语到多重学术理论叠加。
- 支持多种激活与退出口令，智能检测用户困惑与应急场景自动降级，确保体验友好安全。
- 与 play-dumb 技能形成互补，可交互组合使用。
Metadata
Frequently Asked Questions
What is Play Smart?
让 Agent 可控地"装聪明"——把简单问题用过度复杂、学术化、掉书袋的方式回答。支持多种聪明人格（学术大佬、硅谷导师、哲学家等）和10级聪明度调节。触发条件：用户说"装聪明"、"显得聪明点"、"play smart"、"smart mode"、"掉书袋"、"学术模式"。与 play-dumb 互为姊妹技能。安... It is an AI Agent Skill for Claude Code / OpenClaw, with 323 downloads so far.
How do I install Play Smart?
Run "/install play-smart" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Play Smart free?
Yes, Play Smart is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Play Smart support?
Play Smart is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Play Smart?
It is built and maintained by dox012 (@dox012); the current version is v1.0.0.
More Skills