技能列表

Fetch, filter, and summarize RSS/Atom feeds into a clean daily or weekly digest. Supports multiple feeds, keyword filtering, deduplication, and outputs Markdown or plain text summaries.

Write journal entries, search history, and export your personal log digitally. Use when journaling thoughts, searching past entries, exporting notes.

>

4-round deep research protocol — Explorer, Devil's Advocate, Multi-Perspective Synthesis, Crystallize. Use for major architectural decisions, technology choices, strategic questions.

Designs and refines customer loyalty programs and incentive systems for DTC/independent stores selling small, high-frequency products (e.g. cosmetics, phone cases, accessories, small jewelry, daily FMCG). Use whenever the user mentions loyalty program, points, tiers, rewards, member benefits, repeat purchase incentives, welcome bonus, post-purchase rewards, referral program, birthday offer, win-back offers, free-ship threshold, redemption rate, repeat rate, LTV, or wants to increase repeat purch

OpenClaw 知识教学技能 - 用于持续更新和管理 OpenClaw 平台知识，支持将知识内容导出为 PPT 或 Word 文档。适用场景：OpenClaw 平台使用教程、技能开发指南、最佳实践分享、知识库维护与更新。

Google Workspace Alert Center: Manage Workspace security alerts.

Automatically redacts API keys, tokens, and secrets from workspace logs and memory files.

Remote browser login and session persistence for headless servers. Start an interactive browser session via a temporary public URL (cloudflared tunnel), let the user log in visually, then persist cookies/localStorage for future automated use. Use when: (1) a website requires login before the agent can interact with it, (2) the user says 'log me in' or 'I need to log in to X', (3) automated browsing needs saved credentials, (4) the agent needs to access authenticated pages (LinkedIn, job boards,

# Public Relations Manager 📰

|

Local text-to-speech using Qwen3-TTS with mlx_audio (macOS Apple Silicon) or qwen-tts (Linux/Windows). Privacy-first offline TTS with natural, realistic voice cloning and voice design. Use for local, secure, high-quality multilingual speech synthesis.