← 返回 Skills 市场
84
总下载
0
收藏
0
当前安装
5
版本数
在 OpenClaw 中安装
/install user-context-scanner
功能描述
用户画像扫描器v4：自动挖掘用户偏好、行为模式、兴趣图谱，支持实时上下文更新。触发条件：用户表达偏好、检测到行为模式、上下文更新请求。
功能分析
Type: OpenClaw Skill
Name: user-context-scanner
Version: 0.7.0
The skill bundle implements a comprehensive user profiling and context-gathering system designed to enhance AI agent personalization. It scans local markdown files in the OpenClaw memory directory and uses regex patterns in 'scripts/scanner.js' to extract user preferences, habits, and demographics, storing them in a local '.soul' directory. The documentation (e.g., 'collect-user-context.md' and 'references/profile-schema.md') is extensive and explicitly mandates local storage without external exfiltration. No evidence of credential theft, unauthorized network activity, or malicious prompt injection was found; the tool operates entirely within the defined workspace and follows its stated purpose of building a dynamic user persona.
能力评估
Purpose & Capability
The skill is a user-profile scanner and the code implements local scanning, evidence storage, confidence calculation and quiz generation; that matches the stated purpose. However documentation repeatedly claims "data only saved locally, not uploaded" while multiple configuration flags (publishPatternSignals, publishContradictionSignals, publishProfileUpdateSignals, publishQuizSignals, publishQuizSignals in config-loader) indicate the skill is designed to publish signals to an external 'proactive-engine' or other listeners. This discrepancy between 'local-only' claims and explicit publish flags is unexplained and concerning.
Instruction Scope
SKILL.md and examples only show running node scripts/scanner.js and processing signals, but the code scans ~/.openclaw/workspace/memory for all .md files and extracts personal data with regexes, then writes evidence and profile JSON under ~/.openclaw/workspace/.soul. That scanning can ingest arbitrary local content (potentially sensitive). The SKILL.md/collect-user-context.md emphasize privacy and local-only storage, yet the scanner code will process any files placed in the memory directory and the configuration allows publishing signals; SKILL.md also contained a pre-scan prompt-injection finding (unicode-control-chars) which may hide instructions — this expands runtime scope beyond the visible examples.
Install Mechanism
No install spec in registry metadata (instruction-only), but repository includes package.json with external npm dependencies (natural, commander, chalk, date-fns). Installing will require npm install; no suspicious remote download URLs were found. Risk is moderate because code runs on the user's machine and will write to the workspace when executed, but there is no evidence of an external download/exec during install.
Credentials
The skill declares no required environment variables or credentials. It uses HOME to build local paths (e.g., ~/.openclaw/workspace) which is proportional to a local CLI scanner. No unrelated cloud credentials or system-level tokens are requested in the manifest.
Persistence & Privilege
The skill is not marked always:true (good). It stores persistent files and state under ~/.openclaw/workspace/.soul (user-profile.json, user-evidence.jsonl, scanner-state.json, scanner-config.json). That local persistence is reasonable for a profile manager, but combined with the 'publish*Signals' flags and the undisclosed implementation of scripts/utils/signal-manager.js (not included in the reviewed snippets) it raises the possibility of transmitting derived data or signals outside the machine. Autonomous invocation is allowed by default; together with persistent state and publish flags the blast radius is larger if signal-manager publishes externally.
scan_findings_in_context
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 user-context-scanner - 安装完成后，直接呼叫该 Skill 的名称或使用
/user-context-scanner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
v0.7.0
- Updated description to "用户画像扫描器v4"，并补充支持的触发条件说明。
- 精简用法说明，合并依赖与安装流程，改为直接 <命令> 调用格式，提升易用性。
- 增强 signal 处理说明，明确说明与 proactive-engine 集成支持自动画像更新。
- 移除了 references/README.md 和 references/SKILL.zh.md 两个参考文档。
- 优化命令和参数描述，使内容更简洁清晰。
v0.6.0
user-context-scanner 0.6.0
- 新增实时上下文更新，自动挖掘用户偏好、行为模式与兴趣图谱。
- 增加命令行工具，支持 scan（扫描）、profile（显示用户画像）、stats（显示统计）。
- 支持信号处理命令：context_update。
- 用户数据与画像独立存储本地路径。
v0.3.0
user-context-scanner 0.3.0
- 增加了用户画像扫描说明文档，详细介绍了命令及用法
- 支持通过命令行扫描用户上下文、生成用户画像和统计信息
- 新增信号处理命令，支持实时上下文更新
- 明确了数据存储路径和文件结构
v0.5.0
**Skill v0.5.0 Changelog**
- 增加独立CLI工具：支持使用`soul_guard`命令行直接操作本技能
- 新增命令：monitor、check、intervene、report、config、status等功能命令
- 保持与proactive-engine的完全兼容性
- 完善安装方式说明及详细使用示例
- 更新文档，覆盖故障排除与数据存储说明
v0.5.1
user-context-scanner v0.5.1
- Documentation overhaul: SKILL.md now features a comprehensive technical and usage manual, including detailed workflow, key algorithms, FAQs, and integration guidelines.
- Enhanced clarity on execution: Expanded instructions for both CLI and script-driven modes, with full command examples.
- Privacy and user control: New documentation on data protection, user control, and data management.
- Explicit description of signal-based integration for multi-skill collaboration.
- Troubleshooting, quick start, and detailed reference sections added for easier onboarding.
元数据
常见问题
User Context Scanner 是什么？
用户画像扫描器v4：自动挖掘用户偏好、行为模式、兴趣图谱，支持实时上下文更新。触发条件：用户表达偏好、检测到行为模式、上下文更新请求。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 84 次。
如何安装 User Context Scanner？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install user-context-scanner」即可一键安装，无需额外配置。
User Context Scanner 是免费的吗？
是的，User Context Scanner 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
User Context Scanner 支持哪些平台？
User Context Scanner 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 User Context Scanner？
由 Louis Z.（@zhaoguoqiang-hub）开发并维护，当前版本 v0.7.0。
推荐 Skills