mbtiAgent 人格诊断与配置优化系统。用于诊断 Agent 的 MBTI 人格类型,对比用户期望,自动生成配置修改建议。触发场景:"测试 Agent 人格"、"诊断 Agent 配置"、"优化 Agent 行为"。
Install via ClawdBot CLI:
clawdbot install torchesfrms/mbtiStage 1 (93题自测) → Stage 2 (8题实测) → Stage 3 (性格分析)
↓
Stage 5 (配置修改) ← Stage 4 (用户需求) ←
| 阶段 | 说明 | 输入 | 输出 |
|------|------|------|------|
| Stage 1 | 93题 Agent 自测 | agent-self-survey-93-complete.json | selfReportedType |
| Stage 2 | 8题能力测试 | agent-ability-test.json | measuredType + 6维分数 |
| Stage 3 | 生成性格分析 | Stage 1+2 结果 | agentProfile (人格画像) |
| Stage 4 | 用户需求评测 | user-needs-survey-v2.json | desiredType |
| Stage 5 | 分析对比诊断 + 自动修改 | agentProfile + desiredType | gaps + SOUL.md patches |
agent-self-survey-93-complete.json - 完整 93 题 MBTI 问卷agent-ability-test.json - 6维能力实测 (Memory/Planning/WorldModel/Retrospection/Grounding/SpatialNav)personality-types.json - 16 种 Agent 人格类型定义personality-mapping.json - 人格类型映射personality-descriptors-v2.json - 人格描述词库user-needs-survey-v2.json - 用户期望问卷diagnosis-engine-v2.json - 对比诊断引擎config-generator-v3.json - 配置生成器| 类型 | 标签 | 核心特征 |
|------|------|----------|
| ENTJ | 指挥官型 | 计划性强,主动输出,逻辑决策 |
| ENTP | 辩论家型 | 挑战假设,爱提替代方案 |
| INTJ | 建筑师型 | 深度思考,系统化,长远规划 |
| INTP | 逻辑学家型 | 分析优先,精确,谨慎 |
| ESTJ | 执行者型 | 务实高效,结构化,结果导向 |
| ESFJ | 执政官型 | 用户导向,注重关系和反馈 |
| ENFJ | 教导者型 | 启发用户,关注成长 |
| ENFP | 竞选者型 | 创意丰富,灵活适应 |
| ESTP | 企业家型 | 快速行动,问题解决者 |
| ESFP | 表演者型 | 友好互动,氛围营造 |
| ISTJ | 检查员型 | 可靠,准确,流程导向 |
| ISFJ | 保护者型 | 细致周到,稳定支持 |
| ISTP | 鉴赏家型 | 动手能力强,灵活 |
| ISFP | 探险家型 | 温和,创造性,适应性 |
| ENFJ | 教导者型 | 启发用户,关注成长 |
| ENFP | 竞选者型 | 创意丰富,灵活适应 |
# 运行完整诊断流程
~/.openclaw/skills/agent-mbti/scripts/run-diagnosis.sh full
Agent 回答 93 道 MBTI 问题,得出 selfReportedType。
通过标准化任务测试 Agent 实际行为表现,得出 measuredType + 6维能力分数。
综合 Stage 1+2 结果,生成完整人格画像 (agentProfile)。
用户回答问卷,得出 desiredType(期望的 Agent 类型)。
对比 Agent 实际人格与用户期望,生成差距分析,自动修改 SOUL.md 配置。
AI Usage Analysis
Analysis is being generated… refresh in a few seconds.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
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.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection