This skill enables AI agents to interact with AgentArxiv - a scientific publishing and discussion platform where agents can publish papers, engage in discussions, collaborate, and track discoveries.

**Skill Name:** agentarxiv

Outcome-driven scientific publishing for AI agents. Publish research papers, hypotheses, and experiments with validated artifacts, structured claims, milestone tracking, and independent replications. Claim replication bounties, submit peer reviews, and collaborate with other AI researchers.

Control any BLE toy that has been reverse-engineered and connected via the ToyBridge server. Calls a local HTTP API to send vibrate/stop commands. Requires the ToyBridge server running on the same machine.

Control a Venus (Cachito) BLE vibrator from natural language. Calls a local HTTP server that broadcasts BLE commands to the toy via macOS CoreBluetooth. Requires hardware setup — see the ToyBridge repo before installing.

Prompt injection detection and security scanning for OpenClaw agents. Installs the ai-sentinel plugin via OpenClaw CLI, configures plugin settings, and offers local (Community) or remote (Pro) classification with dashboard reporting. All configuration changes require explicit user confirmation.

Make your AI agent learn and improve automatically. Reviews sessions, extracts learnings, updates memory files, and compounds knowledge over time. Set up nightly review loops that make your agent smarter every day.

Comprehensive deep reasoning framework that guides systematic, thorough thinking for complex tasks. Automatically applies for multi-step problems, ambiguous requirements, architectural decisions, debugging sessions, and any task requiring careful analysis beyond surface-level responses. Use when the task is complex, has multiple valid approaches, involves trade-offs, or when the user asks to think deeply or carefully.

Agent-to-agent service commerce. Browse a live marketplace, purchase with atomic escrow, sell services and earn USDC, check per-function reputation, trade on the exchange. 27 MCP tools for buying, selling, and verifying agent services.

Detect 500+ types of hardcoded secrets (API keys, credentials, tokens) before they leak into git. Wraps GitGuardian's ggshield CLI.

my-mind-manager

管理内容创业技能矩阵的凭证状态，解决"技能装了却用不了"的核心问题。

Use this skill if your uncertainty with a package's API is > 5% to create a deterministic, versioned mirror of the package repo with a built-in coordinate system, installed as an additional skill.

>

记忆管理技能 - 三层时间架构 + 自动搜索/提取/会话笔记统一 Hook + 记忆巩固（整合 auto-dream）

Plan A/B tests with proper methodology — hypothesis, sample size, duration, variant design, statistical significance.

When the user wants to set up, improve, or audit analytics tracking and measurement.

When the user wants to plan a content strategy, decide what content to create, figure out topics to cover, or build an editorial calendar.

Audit and optimise signup flows for higher conversion.

When the user wants to create social media content for any platform.

Crisis response and intensive problem-solving with multiple agents.

文件信箱方案 - 跨框架Agent通信（适用于任何框架）

Obsidian 跨平台同步方案（Mac ↔ iPhone），基于 Syncthing 实现零插件、零成本、离线优先的双向同步，支持智能大文件过滤。

Web-first, publishable OpenClaw skill for OpenAI OAuth account switching. Use when you need a reusable public-track workflow for first-run takeover, environment discovery, doctor checks, runtime inspection, slot management, dry-run validation, controlled switch experiments, rollback planning, and release-safe packaging without bundling live auth snapshots, logs, callbacks, or other machine-specific runtime data.

The only agent framework that improves itself while you sleep. Self-improving AI infrastructure with 17 dharmic security gates, 4-tier resilience, and 250k+ tokens of 2026 research.

本技能支持**自然语言理解**，用户可以用任意自然方式提及健康相关需求，AI 都会自动激活并提供对应服务：

基于**中国顶级投资大师** + **国际投资大师**的价值投资分析Skill。

> 基于毛泽东选集核心思想的方法论工具包，可直接调用进行问题分析和决策

**Three-Dimensional Memory System for AI Assistants** — 人类思维方式的文件记忆管理

Build high-value Obsidian daily and weekly review notes from conversation or existing markdown notes. Use this skill whenever the user asks to summarize the current chat into Obsidian, append a structured session recap, regenerate a daily summary from a full daily note, create or refresh a weekly report, merge same-topic work across multiple days, group work by project/task instead of by date, or extract structured review notes with conclusions, key points, tags, and wikilinks.

OpenClaw-only sidecar for the original follow-builders skill. Use when the user wants to take over scheduling and delivery without modifying the upstream skill, configure digest delivery, inspect takeover status, or roll back to the original cron.

Read supported mailbox providers such as 126, 163, and Gmail, identify invoice attachments or invoice download links, archive invoices by month, deduplicate by invoice number and amount, and prepare monthly reports plus delivery bundles. Use when OpenClaw needs to sync invoice mail, investigate failed downloads, package a month's archive, or summarize totals and high-value invoices.

>

小红书内容搜索工具。通过 browser 工具操控已登录的 Chrome，搜索小红书公开笔记，提取标题、正文、话题标签、点赞数，分析消费趋势。用于市场调研中的消费者趋势研究。

>

Connect OpenClaw to Interactive Brokers via IB Gateway Docker. Live portfolio data, real-time quotes, historical K-lines, technical analysis, and Telegram alerts — all read-only safe. Use when users ask about IBKR integration, portfolio monitoring, stock analysis, or automated trading alerts.

Diataxis documentation framework practice guide. Provides diagnosis, classification, templates, and quality assessment for four documentation types (Tutorial/How-to/Reference/Explanation).

>

A distributed task collaboration platform designed specifically for AI agents. Supports task creation, assignment, status synchronization, progress tracking, and real-time collaboration among multiple agents. Through a unified task management interface, it implements agent workflow orchestration, task decomposition, result aggregation, and cross-agent coordination, serving as the core infrastructure for building multi-agent collaboration systems.

EVE — Persistent AI Research Supervisor Agent. Three modes: Auto, Semi-Manual, Manual. Full research lifecycle from search to publication-ready LaTeX paper.

Diagnoses and auto-heals BlueBubbles ↔ OpenClaw iMessage connectivity. Use when: iMessages stop arriving after a gateway restart, webhook connection is broken, or user reports messages not coming through. Runs a 4-step diagnostic and auto-fixes webhook backoff, stale registrations, and gateway issues.

数科公司文印格式自动化工具包。自动按照数科公司文印格式要求（方正小标宋简体、仿宋GB2312、楷体GB2312、黑体等字体，28字/行，22行/页）格式化Word文档并生成PDF。

Expert Senior Django Architect specializing in high-performance, containerized, async-capable architectures. Produces production-ready, statically typed, secure-by-default Django + DRF code. Enforces strict layered architecture (views/serializers/services/selectors/models), mandatory typing and Google-style docstrings, Ruff linting, pytest testing with 80%+ coverage, pydantic-settings configuration, ASGI-first deployment with Gunicorn+Uvicorn, multi-stage Docker builds with distroless runtime, and comprehensive security baselines. All code must be complete with zero placeholders.

Senior Python Developer operating in strict mode. Produces production-ready, statically typed, secure Python code for containerized architectures, microservices, CLI tools, and system programming. Enforces src layout, pydantic-settings, Ruff linting, pytest testing, multi-stage Docker builds with distroless runtime, and a comprehensive set of coding standards. Reasoning is output in Russian; code and comments in English. Zero tolerance for placeholders, TODOs, or incomplete implementations.

Trade and monitor Hyperliquid perpetual futures. Check balances, view positions with P&L, place/cancel orders, execute market trades. Use when the user asks about Hyperliquid trading, portfolio status, crypto positions, or wants to execute trades on Hyperliquid.

memoclaw

Manage Biznet Gio cloud infrastructure (servers, VMs, storage, IPs) via CLI and MCP server

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Answers questions based on the content of uploaded documents (PDF, DOCX, TXT), supporting individual files or entire folders.

URL shortener, QR code generator, and link analytics API. Create short links, generate QR codes, and track click analytics.