← Back to Skills Marketplace
Claw Mbti
by
xiaoyang0807
· GitHub ↗
· v1.5.0
· MIT-0
243
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install myagent-mbti
Description
龙虾MBTI性格诊断。基于用户与龙虾的互动模式，分析并生成龙虾的MBTI人格报告。当用户说"测测我的MBTI"、"你是什么龙虾"、"龙虾诊断"时触发。
Usage Guidance
This skill appears internally consistent: it will read your recent (last 7 days) chat history and the skill's local 'types.md' to infer an MBTI-like result and explicitly excludes code/shell text from its analysis. Before installing, be aware it needs access to your conversation history/memory (so private messages may be used as input). It does not request cloud credentials or install external binaries. If you have privacy concerns, review the provided types.md/reference files and consider using it only when comfortable allowing the agent to read recent messages. Also verify the GitHub repo (homepage) if you want to inspect the source files yourself.
Capability Analysis
Type: OpenClaw Skill
Name: myagent-mbti
Version: 1.5.0
The skill bundle is a personality analysis tool that evaluates user interaction patterns to determine an MBTI type. It contains robust instructions in SKILL.md to explicitly filter out sensitive technical data—such as shell commands, Git operations, and code snippets—from its analysis process, which acts as a safeguard against accidental data leakage or prompt injection. The installation commands provided in README.md and SKILL.md are standard for the OpenClaw ecosystem, and there is no evidence of data exfiltration, malicious execution, or unauthorized access.
Capability Assessment
Purpose & Capability
Name/description (龙虾 MBTI 性格诊断) match the runtime instructions: the skill analyzes recent user interaction patterns and the included 16-type 'types.md' to generate a report. It does not request unrelated binaries, env vars, or external credentials.
Instruction Scope
The SKILL.md requires the agent to review the user's recent 7 days of conversation history and memory to extract signals for scoring — this is necessary for the stated behavior but means the skill will access private chat history/memory. It explicitly forbids using code/shell/installation messages as diagnostic evidence (and instructs filtering them out), which reduces risk. No instructions send data to external endpoints or request unrelated system files.
Install Mechanism
No install spec and no code files executed at runtime (instruction-only). Files needed (types.md, reference) are bundled with the skill, so no external downloads or arbitrary code execution are required.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The data it needs (chat history, skill-local files) is proportional to its functionality.
Persistence & Privilege
always:false and user-invocable:true. The skill does not request persistent system-level privileges or modify other skills. It behaves as a normal user-invoked skill.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install myagent-mbti - After installation, invoke the skill by name or use
/myagent-mbti - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.5.0
强化数据过滤：所有维度严禁引用shell/Git内容作为诊断依据
v1.4.0
新增ClawHub安装说明，统一使用myclaw-mbti slug
Metadata
Frequently Asked Questions
What is Claw Mbti?
龙虾MBTI性格诊断。基于用户与龙虾的互动模式，分析并生成龙虾的MBTI人格报告。当用户说"测测我的MBTI"、"你是什么龙虾"、"龙虾诊断"时触发。 It is an AI Agent Skill for Claude Code / OpenClaw, with 243 downloads so far.
How do I install Claw Mbti?
Run "/install myagent-mbti" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Claw Mbti free?
Yes, Claw Mbti is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Claw Mbti support?
Claw Mbti is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Claw Mbti?
It is built and maintained by xiaoyang0807 (@xiaoyang0807); the current version is v1.5.0.
More Skills