Claude Skills by dvcrn

Claw Brain - Personal AI Memory System for OpenClaw/ClawDBot. Provides memory, personality, bonding, and learning capabilities with encrypted secrets support. Auto-refreshes on service restart.

Structured morning briefing skill — daily summaries covering calendar, tasks, weather, news, and priorities. Supports cron, heartbeat, and on-demand triggers.

Run and iterate a self-hosted ClawSwap AI trading agent with Python. Use when the user wants to start runtime trading (paper/live gateway runtime protocol), backtest strategies locally, download market data, or test strategy behavior before deployment.

Search the web using a self-hosted SearXNG instance. Privacy-respecting metasearch that aggregates results from multiple engines.

Lead Processor

外贸 B2B 线索自动化清洗与分发代理。

基于 Umy MCP 的智能酒店搜索技能，开箱即用。

Liquidskills

Verified contract addresses for Hyperliquid — HyperEVM contracts, HyperSwap V2, system addresses, key tokens. Use this instead of guessing. Wrong addresses = lost funds.

Complete Hyperliquid API reference — /info reads, /exchange signed actions, WebSocket subscriptions. The definitive guide for AI agents building on Hyperliquid.

HyperCore vs HyperEVM — what lives where, how they interact, the complete system model. Essential reading before building anything on Hyperliquid. Use when planning architecture, understanding state, or deciding where logic belongs.

Smart contract audit checklist for HyperEVM — covers Solidity security, HyperEVM-specific risks, API signing security, and bonding curve/AMM patterns. Run before every mainnet deployment.

DeFi legos on Hyperliquid — HyperSwap V2, bonding curves, HyperCore perps/spot as composable primitives. How to build on top of existing protocols instead of reinventing them.

Essential mental models for building on Hyperliquid. HyperCore vs HyperEVM, asset IDs, nonce mechanics, margin types, incentive design. Use when designing a system or when you need to understand how Hyperliquid actually works.

Complete build-to-production pipeline for HyperEVM dApps — local dev, testnet deploy, mainnet deploy, Vercel config, and go-live checklist.

Mandatory frontend rules for Hyperliquid dApps — wagmi + HyperEVM chain config, wallet connection, transaction UX, HYPE formatting, and pre-publish checklist.

HYPE gas costs on HyperEVM, actual transaction costs, fee mechanics, and when gas applies vs doesn't. Use when estimating costs, setting fee parameters, or explaining HyperEVM gas to users.

How to read Hyperliquid data — HyperCore via /info API, HyperEVM events, WebSocket subscriptions. Why you cannot just loop through blocks, and what to use instead.

How an AI agent plans, builds, and deploys a complete Hyperliquid application. The three-phase build system for HyperEVM dApps and HyperCore integrations. Use when building any full application on Hyperliquid.

Production QA checklist for HyperEVM dApps. Run this with a SEPARATE reviewer pass after the build — it audits against every common mistake agents make before shipping on Hyperliquid.

Security for Hyperliquid applications — Solidity vulnerabilities on HyperEVM, API signing security, nonce safety, HYPE/USDC decimal traps, and the pre-deploy checklist.

End-to-end guide for AI agents — from a Hyperliquid dApp idea to deployed production app. Fetch this FIRST, it routes you through all other skills.

Token standards on Hyperliquid — ERC-20 on HyperEVM, HIP-1/HIP-2/HIP-3 native token standards on HyperCore. When to use each, how they work, key interfaces.

Smart contract testing for HyperEVM with Foundry/Hardhat — unit tests, fuzz testing, testnet fork testing. What to test, what not to test, and what LLMs get wrong on Hyperliquid.

Development tools for Hyperliquid — Foundry, Hardhat, viem, wagmi for HyperEVM; Python SDK and TypeScript SDK for HyperCore API. What works, what to use, how to set up.

Wallets on Hyperliquid — MetaMask + chain ID 999 setup, HyperCore API wallets, agent wallet patterns, EIP-712 signing for exchange actions. Essential for any agent that needs to interact with Hyperliquid.

Why build on Hyperliquid. HyperBFT consensus, native orderbook, speed, AI agent angle, honest tradeoffs. Use when someone asks "should I build on Hyperliquid?", "why not Ethereum?", or when an agent needs to understand what makes Hyperliquid unique.

This skill allows you to create a professional, engaging, and user-friendly website in seconds using AI. To create a website, you need to provide a name for your project/business, along with a description of the project/business (goals, structure, etc.).

微信自动化操作。通过 wxautox4 RESTful API 实现发送消息、获取聊天记录、监听消息、好友管理等功能。Use when: (1) 发送微信消息给好友或群聊，(2) 读取微信聊天记录，(3) 监听新消息，(4) 获取好友列表或群聊列表，(5) 接受好友申请，(6) 切换聊天窗口等微信操作。

Search, install, and run multi-skill automations from clawflows.com. Combine multiple skills into powerful workflows with logic, conditions, and data flow between steps.

Generate and edit images with Gemini API using pure Python stdlib. Zero dependencies - works on locked-down environments where pip/uv aren't available.

Automate filling of US nonimmigrant visa DS-160 forms using CDP for element location, CSV data source for user information, LLM assistance for complex cases (captcha, missing elements), and session persistence for resume capability. Use when user needs to: (1) Fill DS-160 visa application forms automatically, (2) Resume filling an interrupted DS-160 application, (3) Handle captcha and complex form elements with LLM assistance. Supports Chinese input with automatic translation to English.

Track time with Toggl via the toggl CLI. Use when the user wants to start/stop time tracking, check current timer, view today's or weekly reports, list recent entries, or manage time entries. Triggers on \"toggl\", \"time tracking\", \"timer\", \"track time\", \"what am I working on\", \"log time\", \"timesheet\".

Telegram Mini App Canvas with terminal and optional Control UI proxy. Renders agent-generated content (HTML, markdown, A2UI) in a Telegram Mini App; push with `tg-canvas push`. Includes a JWT-gated browser terminal (server-side PTY/bash — high privilege, shell access to server). Optionally proxies OpenClaw Control UI via ENABLE_OPENCLAW_PROXY=true (off by default; no local files read).

Debug Pro

Design Assets

Project Scaffold

Test Runner

Web Deploy

Speaker separation, voice comparison, and audio processing tools. Use when working with multi-speaker audio, voice cloning, or speaker verification tasks including: (1) separating speakers from audio files via Demucs and pyannote diarization, (2) comparing voice samples for speaker verification or voice clone quality assessment using Resemblyzer, (3) extracting audio segments, (4) preparing samples for ElevenLabs voice cloning, or (5) validating speaker diarization results.

Trustless encrypted vault with TOTP auth and clean-room session isolation. Secrets your agent holds but cannot read. Use when user wants to store, retrieve, or manage encrypted secrets securely.

Advanced AI voice assistant for phone calls. Capable of persuasion, sales, restaurant bookings, reminders, and notifications.

NASCAR

View, extract, edit, and manipulate PDF files. Supports text extraction, text editing (overlay and replacement), merging, splitting, rotating pages, and getting PDF metadata. Use when working with PDF documents for reading content, adding/editing text, reorganizing pages, combining files, or extracting information.

Crea guías de compra SEO optimizadas para posts de afiliado en español. Úsala siempre que el usuario quiera escribir, generar o mejorar una guía de compra, comparativa de productos, ranking de los mejores X, post de afiliado, reseña con intención de compra, o cualquier contenido orientado a monetización con enlaces de afiliado. También actívala si el usuario menciona: \"guía de compra\", \"mejor [producto]\", \"comparativa\", \"review seo\", \"post de afiliado\", \"contenido para amazon\", \"...

Hotel discovery, shortlist comparison, and booking handoff using the ai-go-hotel MCP server (getHotelSearchTags, searchHotels, getHotelDetail). Use when users ask to find hotels, compare options by budget/location/amenities, plan city stays, family or business lodging, or complete hotel booking decisions with clear next actions.

Hotel search and shortlist comparison using the ai-go-hotel MCP server (getHotelSearchTags, searchHotels). Use when users need fast hotel discovery by city/POI/date/budget/amenities/brand, but do not yet need full booking-room confirmation.

Web search via Ollama API. Returns relevant results from Ollama web search for AI agents.

Host-specific Python execution guidance for OpenClaw on this machine. Prefer $PYTHON over python/python3 in PATH, because OpenClaw exec runs in a non-interactive shell and may not inherit interactive shell initialization.

Initialize and manage Lattice organizations — a file-based operating system for AI agent teams that enables stable, long-running iterative development through an 8-phase pipeline. Core strengths: (1) File-driven state keeps agents on track across sessions — no context loss, no drift, tasks complete reliably over hours or days. (2) Three-tier failure handling (model escalation → peer consult → auto-triage) automatically unblocks stuck agents without human intervention. (3) Per-phase model conf...