发现 Skills

name: email-assistant description: Multi-email management assistant supporting Gmail, 163, QQ, Outlook, and Hotmail. Features: (1) Fetch inbox and summarize emails (2) Keyword-based important email...

Location-based safety monitoring with automatic alerts and escalation. Use when setting up safety monitoring for a user, tracking their location, checking for nearby dangers (weather, earthquakes, air quality, local emergencies), or configuring emergency contact escalation. Also includes self-preservation monitoring for the agent's host machine. Triggers on requests about safety alerts, location tracking, emergency monitoring, "keep me safe," or "monitor yourself."

Speech-To-Text with MLX (Apple Silicon) and opensource models (default GLM-ASR-Nano-2512) locally.

Security hardening for AI agents - Moltbot, OpenClaw, Cursor, Claude. Lock down gateway, fix permissions, auth, firewalls. Essential for vibe-coding setups.

TypeScript library and CLI for Monarch Money budget management. Search transactions by date/merchant/amount, update categories, list accounts and budgets, manage authentication. Use when user asks about Monarch Money transactions, wants to categorize spending, needs to find specific transactions, or wants to automate budget tasks.

Investigate a username across 1000+ social media platforms and websites using social-analyzer. Use this skill whenever the user wants to look up, investigate, trace, or find where a specific username exists online — including OSINT research, background checks on online handles, verifying if someone uses the same username across platforms, or checking their own digital footprint. Triggers on phrases like "查一下这个用户名", "帮我找 X 在哪些平台", "investigate username", "OSINT lookup", "social media footprint", "trace this account", "find all accounts for X". Always use this skill when a username investigation is requested, even if the user just says "look up [name]" or "check if [name] exists on social media".

Use Preloop's request_approval tool to get human approval before risky operations like deletions, production changes, or external modifications

.join( [role, do, context, content, dont, output, assessment, iteration ] )\n

使用 Bytedance Seedance 模型生成视频。支持文生视频（带音频）、图生视频、参考图生视频。当用户想要生成视频、使用图片生成视频、保持人物一致性、或提到 seedance 时使用此 skill。

使用 Seedream 4.5 模型生成或编辑图像。当用户想要文生图、图生图、图像编辑，或提到 seedream、字节跳动图像生成时使用此 skill。

Google search via Serper API with full page content extraction. Fast API lookup + concurrent page scraping (3s timeout). One well-crafted query returns rich results — avoid multiple calls. Two modes, explicit locale control. API key via .env.

Transak fiat-to-crypto on-ramp for Web3. Buy and sell crypto with 100+ payment methods across 170+ countries.

Real-time WhatsApp voice message processing. Transcribe voice notes to text via Whisper, detect intent, execute handlers, and send responses. Use when building conversational voice interfaces for WhatsApp. Supports English and Hindi, customizable intents (weather, status, commands), automatic language detection, and streaming responses via TTS.

Generate XMind mind map files (.xmind) from Markdown outlines or plain text descriptions. Use when a user asks to create a mind map, visualize a structure, or export to XMind format. Supports both Markdown outline syntax (# headings, - bullets, indentation) and free-form text descriptions. Output is saved as a .xmind file in the workspace directory, openable directly in XMind app.

Deep-research orchestrator covering the full workflow: planning → dimensioned evidence collection → synthesis → final draft (report.md). Outputs are written to report_dir and it supports resumable runs. Before starting it must perform a minimal generic web_search probe to confirm the current session's search capability; if the probe fails or cannot confirm, stop and prompt the user to configure. **Proactively use this skill (do not just search a few items and answer) whenever any of the following apply:** ① User uses trigger terms: deep research / in-depth research / comprehensive research / systematic research / research / survey / due diligence / industry research / market research / competitor analysis / policy research / technical research / trend research / fact-checking / write a research report / research report / in-depth report; ② The request requires evidence collection from multiple sources, multi-dimensional comparison, or cross-validation to reach a reliable conclusion; ③ The user requests a deliverable such as a report, white paper, industry analysis, or due-diligence document; ④ The topic involves up-to-date policy/market/product/pricing/regulation that needs systematic verification. Vague or broad "research/learn about X" queries should also preferentially trigger. Not intended for: single-fact Q&A ("What is X"), one-sentence summaries, organizing content already provided from a single source, or pure copy-editing/paraphrasing.

Provides comprehensive guidance for DALL-E AI image generation including prompt creation, image generation, variations, and editing. Use when the user asks about DALL-E, needs to generate AI images, create image variations, or work with DALL-E API.

Provides comprehensive guidance for PostgreSQL database including SQL syntax, advanced features, JSON support, full-text search, and performance tuning. Use when the user asks about PostgreSQL, needs to work with PostgreSQL features, write complex queries, or optimize PostgreSQL databases.

Provides comprehensive guidance for Vant Vue 3 mobile component library including mobile components, themes, and best practices. Use when the user asks about Vant, needs to build mobile applications with Vue 3, or implement mobile UI components.

Audit a public-facing site or server for common misconfigurations without sending exploit traffic. Covers DNS hygiene, TLS and HSTS, security headers, exposed paths (.git, .env, backups), cookie flags, and software fingerprinting. Invoke when onboarding a new client site, before launch, after infrastructure changes, or as periodic re-audit.

Professional video prompt generator and optimizer for multi-platform AI video generation. Supports: - Text-to-video (文生视频) - Image-to-video (图生视频) - First/last frame generation (首尾帧) - Reference image guided generation (参考图) - Intelligent multi-frame generation (智能多帧/分镜) - Universal reference (图片、视频、音频) - Multi-platform support (可灵, Vidu, 即梦, Sora, Google, Runway, Pika, etc.) Use when: - User wants AI video generation prompts - User provides images/videos/audio for reference - User specifies platform (Kling, Vidu, Jimeng, Sora, Google, Runway, Pika) - User wants storyboard or multi-frame video - User wants first/last frame control - User wants to optimize existing video prompts

Convert Markdown files to PDF using Chrome. Use when the user wants to render Markdown to PDF, print a document, or create a shareable PDF from Markdown. Triggers on "markdown to pdf", "render to pdf", "pdf from markdown", and "print this markdown".

UI component conventions for 8-bit styled components. Use when working with shadcn/ui components or implementing retro-styled UI elements.

Run a multi-agent review of changed files for reuse, quality, efficiency, and clarity issues followed by automated fixes. Use when the user asks to 'simplify code', 'review changed code', 'check for code reuse', 'review code quality', 'review efficiency', 'simplify changes', 'clean up code', 'refactor changes', or 'run simplify'.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.