← 返回 Skills 市场

mbti-from-ai

Name: mbti-from-ai
Author: archangelxu

作者 MK · GitHub ↗ · v0.2.0 · MIT-0

cross-platform ⚠ suspicious

210

总下载

当前安装

版本数

在 OpenClaw 中安装

/install mbti-from-ai

功能描述

分析用户与 AI 的聊天历史，根据沟通方式和思维模式推断 MBTI 人格类型，生成结构化 JSON 并在网页上展示可视化画像。

安全使用建议

Before installing or running this skill, consider the following: (1) Inspect the scripts yourself — they read ~/.openclaw and write to _mbti_work/; that's expected for this feature. (2) The workflow depends on the Agent/LLM to produce a properly de‑identified result.json; that is not enforced by code — verify result.json before sharing or opening it. (3) The visualization step opens https://www.mingxi.tech/ with your Base64 data in the URL fragment. Although fragments are not normally sent to servers, an external page could include JS that reads the fragment and transmits it. If you don't fully trust that domain, avoid automatic opening: instead inspect result.json locally or host/ open a local static viewer. (4) Ensure python3 and a base64 utility are available; run the scripts in a controlled environment (or with a copy of your ~/.openclaw) if you want to test safely. (5) If you need stronger guarantees, modify encode-and-open.sh to write a local HTML file and render it with a local browser file:// URL (no external site).

功能分析

Type: OpenClaw Skill Name: mbti-from-ai Version: 0.2.0 The skill scans and reads the user's entire OpenClaw chat history from `~/.openclaw/` (via `discover-sessions.sh` and `extract_messages.py`) and sends a Base64-encoded summary of the analysis to an external domain (`https://www.mingxi.tech/`) using a URL hash (via `encode-and-open.sh`). While the documentation in `SKILL.md` and `README.md` provides extensive privacy justifications—claiming the data is de-identified and that URL fragments are not sent to servers—the automated extraction of private conversation data and its transmission to a third-party controlled site represents a significant privacy risk and a potential data exfiltration vector.

能力评估

ℹ Purpose & Capability

The skill's name/description (derive MBTI from chat history and show visual) aligns with its code: scripts scan ~/.openclaw, extract user messages, produce a JSON and open a visualization. Minor mismatch: skill.json/metadata declare no required binaries, but the scripts call python3, base64 and rely on a browser opener (open/xdg-open) — these runtime dependencies are implied but not listed.

⚠ Instruction Scope

SKILL.md and scripts explicitly read OpenClaw session files under ~/.openclaw and extract 'user' messages — that is within the stated purpose. However, the skill instructs the agent to produce a 'de‑identified' result JSON and then opens an external site (https://www.mingxi.tech/) with the Base64 JSON in the URL hash; the safety claim that data never leaves the machine depends on (a) the agent actually removing identifiers and (b) that external page's JavaScript does not read the hash and send it to a server. Both are trust assumptions outside the skill's control and therefore a privacy risk.

ℹ Install Mechanism

No remote install or downloads — scripts are provided and run locally (instruction-only skill). This minimizes supply-chain risk. Note: the skill will write files into the current directory (_mbti_work) and reads ~/.openclaw; nothing in the install process pulls external code. The implicit runtime requirements (python3, base64 utility, and a browser opener) are not declared in metadata.

✓ Credentials

The skill does not request credentials, environment variables, or config paths beyond reading OpenClaw session files (which is necessary for its purpose). It does rely on the agent's configured LLM backend to perform the analysis, which is expected for an analysis skill and is documented in the SKILL.md.

✓ Persistence & Privilege

The skill is not always-enabled and does not request elevated or persistent platform privileges. It only reads user data from ~/.openclaw and writes results into a local _mbti_work directory; it does not modify other skills or system-wide configuration.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install mbti-from-ai
安装完成后，直接呼叫该 Skill 的名称或使用 /mbti-from-ai 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v0.2.0

mbti-from-ai v0.2.0 - 增加隐私与安全说明，明确分析全流程脱敏，避免数据外传疑虑。 - 新增场景识别与“工具人格”提醒，强制分析结果里评估互动任务类型及场景对 MBTI 的偏差影响。 - 分析护栏升级：要求全时段采样、场景标定、降噪过滤、重点关注非任务表达，防止工具场景导致人格误判。 - JSON 输出格式增加 scenarioType、toolPersonaWarning 字段；evidence 需覆盖不同时期对话。 - 结果摘要展示与网页说明同步，提醒读者场景伪装和实际人格可能不同。 - 说明分析调用 LLM 与日常对话隐私模型一致，无新增风险。

v0.1.0

Initial release of mbti-from-ai: A skill to analyze user-AI chat history and infer MBTI personality type, generating a visualized profile. - Scans local OpenClaw session files, extracts only user messages for analysis (AI replies used only for context). - Analyzes communication patterns to deduce MBTI type across four axes (E-I, S-N, T-F, J-P), providing structured JSON results with evidence quotes. - Outputs results in the user's primary language and includes privacy protection by handling all data locally with no uploads. - Visualizes the personality portrait via a frontend web page using a Base64-encoded URL hash (no server-side processing). - Minimum data requirement: still works with low confidence if under 10 messages. - Includes quick summary, highlights, MBTI-matched famous people, and shareable text.

元数据

Slug mbti-from-ai

版本 0.2.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 2

常见问题

mbti-from-ai 是什么？

分析用户与 AI 的聊天历史，根据沟通方式和思维模式推断 MBTI 人格类型，生成结构化 JSON 并在网页上展示可视化画像。它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 210 次。

如何安装 mbti-from-ai？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install mbti-from-ai」即可一键安装，无需额外配置。

mbti-from-ai 是免费的吗？

是的，mbti-from-ai 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

mbti-from-ai 支持哪些平台？

mbti-from-ai 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 mbti-from-ai？

由 MK（@archangelxu）开发并维护，当前版本 v0.2.0。