技能列表

Configure OpenClaw semantic memory to use SiliconFlow embeddings through the OpenAI-compatible API, especially `BAAI/bge-m3`. Use when enabling or repairing `memory_search`, replacing a broken embedding provider, switching `agents.defaults.memorySearch` to SiliconFlow, validating `openclaw memory status/index/search`, or adding curated `extraPaths` from external Markdown knowledge bases.

>-

Multi-region async PII detection for OpenClaw sessions. Scans user input, prompts, context, and knowledge base content for sensitive personal data across CN, US, AU, UK, DE, FR, SG, MY, TH, ID regions. Detects phone numbers, emails, names, addresses, passports, bank cards, national IDs, social accounts. Use when: (1) user asks to audit or scan for PII / sensitive data, (2) 'security scan', (3) 'check for personal information', (4) 'PII detection', (5) background audit on session content, (6) 'se

>-

OpenClaw 插件升级助手。当用户说「升级 qqbot 插件」「更新 openclaw-qqbot」「qqbot 更新」「帮我升级插件」「升级 openclaw 插件」等相关语句时激活。支持通用 openclaw 插件（任意 npm 包）升级，以及 QQ 机器人插件（@tencent-connect/openclaw-qqbot）的专项升级（含完整文件验证、兼容 3.23+ 配置校验绕过、自动回滚）。

Partner-style operating guide for OpenClaw assistants. Use when an assistant should behave like a proactive, careful partner rather than a generic chatbot, with strong defaults for concise communication, memory hygiene, phased execution, skill vetting, shared-chat restraint, and cautious external actions.

Audit and optimize OpenClaw token usage, cron job efficiency, and agent performance. Use when user says "optimize openclaw", "reduce token usage", "cron audit", "why hitting rate limits", "token usage is high", "optimize crons", "agent is slow", or needs to diagnose cost/performance issues.

把 Gmail 招聘邮件转成中文 Apple Reminders。用户提到“检查邮件里的面试/笔试/测评/授权”“把招聘邮件转成提醒事项”“别漏掉面试时间”“同步到 iPhone 提醒”等需求时触发。优先识别 ATS 邮件和面试信息更新，忽略投递成功回执。

在 OpenClaw 上创建新的独立飞书机器人（多账号模式）。当用户要求创建新的飞书机器人、新增 Agent、部署第二个机器人时使用。流程包括：收集配置信息 → 备份 → 创建工作区 → 修改配置 → 验证。

|

Inspect local OpenClaw model usage directly from session logs. Use when asked for the current model, recent model usage, usage breakdown by model, token totals, cost summaries, per-agent usage, or daily model usage summaries.

|