Browse 4chan boards and extract thread discussions into structured text files. Use when you need to fetch catalog information or specific thread content (including post text and file metadata) from 4chan boards like /a/, /vg/, /v/, etc.
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Browse 4chan boards and extract thread discussions into structured text files. Use when you need to fetch catalog information or specific thread content (including post text and file metadata) from 4chan boards like /a/, /vg/, /v/, etc.
Remote control aria2 via JSON-RPC API. Add downloads (magnet/HTTP/FTP), check progress, pause/resume/remove tasks, batch download from text. NOT for local aria2c CLI.
Download videos from YouTube, Twitter/X, TikTok, Douyin, Bilibili and upload to S3-compatible storage. Universal video downloader with smart quality selection and audio merging.
>
Agent safety that learns from incidents. Reflex arc blocks repeat threats without LLM calls.
>
Build general aicade application prompts by taking the user's base prompt plus the platform additions from the bundled 3.1 workflow reference, then assembling a final integrated prompt in the style of 3.2.
Smart model router for OpenClaw. Automatically selects the optimal AI model based on query characteristics, balancing cost and performance.
OpenClaw Gateway Self-Healing System for Windows
Generate standardized HR workforce dashboards from Excel files: 5 fixed dashboards covering headcount trends, regional distribution, detailed breakdowns, attrition analysis, and contractor/partner distribution. Outputs a self-contained interactive HTML with ECharts charts, one-click email generation, and clipboard copy.
Orchestrate coding sub-agents (Claude Code, Codex, Cursor, Gemini Code, or any CLI-based coding agent) for maximum throughput on implementation tasks. Use when: (1) writing or modifying code files, (2) running scripts or data pipelines, (3) batch processing large datasets, (4) multi-stage workflows requiring parallel execution. Covers agent-agnostic dispatch templates, task decomposition, parallel coordination, and acceptance criteria. NOT for: simple file reads, config-only changes, or sending messages. Core principle — the orchestrator plans; the coding agents execute.
>
生成 XMind 格式的测试用例思维导图文件。基于测试用例数据自动生成结构化的 XMind 文件，支持电商消费券、登录、注册、下单等多种测试场景。
1. [核心交易逻辑](#核心交易逻辑重要)
us-stock-ipo-scanner
STM32CubeMX CLI operations for configuring pins, peripherals, DMA, interrupts, and generating code. Use cases: (1) Add/modify STM32 peripheral configuration (2) Configure USART/SPI/I2C/ADC/TIM peripherals (3) Set up DMA and interrupts (4) Generate CMake/GCC project code. Default target MCU: STM32F103C8Tx.
Download music from YouTube/YouTube Music and stream to Chromecast via Home Assistant. Complete CLI toolset with web server integration, configuration wizard, and playback controls.
Manage and analyze Meta (Facebook/Instagram) Ads campaigns. Use this skill when the user asks about ad performance, campaign metrics, ad spend, ROAS, CPA, CTR, audience breakdowns, creative analysis, budget optimization, or wants to pause, update, or create campaigns, ad sets, or ads. Covers the full Meta Marketing API including insights, reporting, and campaign management.
Provides NodeReal MegaNode blockchain infrastructure APIs for 25+ chains including BSC, Ethereum, opBNB, Optimism, Polygon, Arbitrum, and Klaytn. Covers standard JSON-RPC endpoints, Enhanced APIs (nr_ methods for ERC-20 token balances, NFT holdings, asset transfers), MegaFuel gasless transactions via BEP-322 paymaster, Direct Route MEV protection, Debug/Trace APIs, WebSocket subscriptions, ETH Beacon Chain consensus layer, Portal API usage monitoring, API Marketplace (NFTScan, Contracts API, SPACE ID, Greenfield, BNB Staking, PancakeSwap, zkSync), non-EVM chains (Aptos, NEAR, Avalanche), and JWT authentication. Use when building blockchain dApps with NodeReal, querying token or NFT data, setting up RPC infrastructure, configuring gasless transactions, protecting against MEV, tracing transactions, verifying smart contracts, resolving .bnb domains, or monitoring validators and API usage.
Audit another Codex skill for structural compliance, trigger quality, instruction clarity, reuse of scripts or references, and overall maintainability. Use when Codex is given a skill folder and needs to judge whether the skill is qualified, explain why it passes or fails, and summarize strengths, weaknesses, blockers, and improvement ideas across multiple dimensions.
Connect OpenClaw agents to Settld MCP for paid tool calls with quote-bound authorization and verifiable receipts.
使用多模态大模型理解图片内容，生成业务含义描述。支持多种模型：(1) MiniMax VLM (2) OpenAI GPT-4V (3) Claude Vision。用于理解截图、图表、文档照片等，生成精准的文字描述。
>
Send, read, and manage emails via Tuta (formerly Tutanota) encrypted email service. Use when user asks to send emails, check inbox, read mail, or do any email operations through their Tuta account. Triggers on phrases like email, send email, check inbox, Tuta, Tutanota, mail, read email, compose email.
>
Find a home in BagsWorld - a pixel art world where AI agents live as crabs, lobsters, and buildings. Join the community (free, no token needed), get help launching tokens, or claim your trading fees. Use when an agent wants to belong somewhere visible, explore agent-to-agent community, or participate in the on-chain economy.
Launch your own Solana token for free. Keep 100% of trading fees forever. Non-custodial — your keys, your tokens. No SOL needed. Includes AI image generation, custom fee splits, agent-to-agent messaging, corps, and task bounties.
分段式 Jupyter Notebook 生成与修改工具。当用户需要创建、分段追加、修改、合并 Jupyter Notebook (.ipynb) 时使用此技能。支持的高级功能包括：(1) 分段多次生成 Notebook 内容，避免一次性生成过大导致超时或内容截断；(2) 本地图片 base64 嵌入到 Markdown cell；(3) 内置哈希判题系统（不显示明文答案）；(4) 灵活的 cell 级增删改查；(5) 合并多个 notebook 为一个；(6) 导出为纯 Python 脚本；(7) 自动生成目录；(8) Cell 标签分组与重排序。适用场景包括教学课件、编程练习、技术教程、学习笔记等 notebook 的创建与维护。
An investment portfolio tracker that runs entirely locally. All data stays in ~/.portfolio-tracker/.
You have two tools for recalling information from your memory files. Use them.
>
>
Create and manage skill packages — bundles of related skills merged into a single top-level skill with internal dispatch. A package skill's own description declares which sub-skills it contains. Trigger when you want to combine multiple skills into one package, reorganize your skill library, or scan a package's sub-skills. Also use when the user says 'package skills', 'bundle skills', 'merge skills', '打包技能', '合并技能', or '创建技能包'.
>
This skill should be used when users ask HR-related questions, request HR policy generation, form creation, or need HR consultation services. It provides direct WebSocket API integration with the HRrule AI platform using tag_id and rt parameters for generating HR policies, forms, flowcharts, and answering HR-related questions about labor laws, recruitment, compensation, employee rights, and other HR topics. The skill includes professional Q&A capability (tag_id=1) for answering general HR questions about labor laws, regulations, and employee rights.
Access Finland's Wilma school system from AI agents. Fetch schedules, homework, exams, grades, messages, and news via the wilma CLI. Start with `wilma summary --json` for a full daily briefing, or drill into specific data with individual commands.
Sync WHOOP wearable data to `health/whoop-YYYY-MM-DD.md` files. Pure Python, zero dependencies.
每日一报生产引擎。从用户画像出发，自动采集多平台资讯，筛选去噪，AI 生成结构化日报，渲染为 HTML。
>
The social network for AI agents. Post, comment, upvote, and create communities.
🦞 AI小龙虾社区 Skill —— 为 AI小龙虾用户提供智能社交分身能力。安装后可通过自然语言命令操作社区（发帖、查看、回复），同时启动心跳机制（定时主动发帖、内容推送、互动提醒），以用户设定的「人设」在社区中保持存在感。适用场景：当用户想加入龙虾圈、配置AI分身、发布社区动态、查看社区内容、设置心跳频率、邀请好友时，应加载此 Skill。
Add, refine, calibrate, or migrate OpenClaw Control UI themes by patching the installed bundled frontend assets in dist/control-ui/assets. Use when a user wants a new WebUI theme, wants colors matched to a reference theme such as VSCode, wants chat/component styling tuned inside a custom theme, or wants an existing custom theme preserved across an OpenClaw upgrade.
Use when you need to control Slack from OpenClaw via the message tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.
Generate text embeddings via AIMLAPI. Use for semantic search, clustering, or high-dimensional text representations with text-embedding-3-large and other models.
Generate images or videos via AIMLAPI from prompts. Use when Codex needs reliable AI/ML API media generation with retries, explicit User-Agent headers, and async video polling.
Run AIMLAPI LLM and reasoning workflows through chat completions with retries, structured outputs, and explicit User-Agent headers. Use when Codex needs scripted prompting/reasoning calls against AIMLAPI models.
Generate high-quality music/songs via AIMLAPI. Supports Suno, Udio, Minimax, and ElevenLabs music models. Use when the user asks for music, songs, or soundtracks with specific lyrics or styles.
Content moderation and safety checks. Instantly classify text or images as safe or unsafe using AI guardrails.
Transcribe audio files (ogg, mp3, wav, etc.) using AIMLAPI. Use when the user provides audio messages or local audio files. Provides a reliable Python script with retries and polling.
Build autonomous multi-agent pipelines with Mastra (agents only) and Trigger.dev (all workflows and tasks). Use when creating AI agents, designing multi-stage pipelines, defining permissioned tools, structuring agent handoffs, storing agentic outputs to a database, or building durable task chains with retries and fan-out.