Skill rating

Pre-development reference research. Produces a Steal List: concrete patterns extracted from real products and real codebases that solved similar problems. Two modes: UI/UX (screenshot + analyze the be

Multi-model consensus for AI agents. Combine predictions from multiple LLMs, models, or sources into a mathematically optimal consensus. Auto-weights by historical accuracy.

Generate AI videos with Luma Dream Machine via AceDataCloud API. Use when creating videos from text prompts, generating videos from reference images, extending existing videos, or any video generation

只读邮件助手，通过 POP3 协议读取163、QQ、Gmail、Outlook等任意邮箱的邮件。支持：查询邮件总数、获取最近若干封邮件的标题列表、读取邮件完整内容（正文+附件信息）、按序号读取指定邮件、按关键词搜索邮件主题。当用户询问"帮我看看邮件"、"读一下邮箱"、"邮件里有没有XX"、"最近有什么邮件"、"查一下邮箱里的验证码"等邮件读取相关需求时使用。

打品工具箱主入口。三模式：任务前路由（你的问题该用哪个工具）+ 任务后导航（刚做完一个环节，下一步该干什么）+ 陪跑（带你从头走完整条打品链路）。 触发方式：/ljh、电商老家伙、「打品」、「帮我看看这个品」、「不知道下一步该干什么」、「带我从头打这个品」 Main entry point for the product-launch toolkit. Three modes: pre-task

Serve and visually inspect a converted LeRobot dataset in the browser. Use for videos and state/action timelines; do not use for raw workflow HDF5 or incomplete conversion output.

将奥维互动地图 `.ovobj` 点标签文件和 `.ovkml` 点导出转换为经过校验的 ESRI Shapefile。Use when Codex needs to inspect or convert 奥维互动地图/奥维地图 sampling points, preserve Chinese label names and source coordinates, read declared O

Compile AI-generated pixel character references and separately named action sheets into deterministic, validated game assets. Use when Codex needs to inspect sprite actions, build or verify a sprite-a

Build large-screen data-visualization dashboards (大屏 / 数据大屏 / 可视化大屏) as Slidev presentations using the datav-vue3 (DataV) component library. Use when the user wants a data dashboard, monitoring/comman

Full-site crawling, scraping, and site mapping via Firecrawl MCP. Use when user says "crawl site", "map site", "full crawl", "find all pages", "broken links", "site structure", "discover pages", "JS r

Local LLM model router for Llama, Qwen, DeepSeek, Phi, Mistral, and Gemma across multiple devices. Self-hosted local LLM inference routing on macOS, Linux, and Windows. Local LLM 7-signal scoring engi

Predict English Premier League football match outcomes first, keep World Cup national-team support for compatibility, include schedule/result context, answer in the user's language, and keep output as

Control Android devices from AI agents using the Another MCP server. Use when asked to interact with, test, automate, or take screenshots of an Android device. Provides tools for touch input, text ent

Generate Upwork/freelance bid materials from a job description, including English proposal draft, bid-worthiness score, pricing suggestion (fixed/hourly), milestone split, and D+1/D+3/D+7 follow-up me

Upscale and enhance media with Topaz through RunAPI. Use when the user asks an agent to upscale or enhance images and video with Topaz. Default to the RunAPI CLI for one-off generation; use SDKs only

Use when users ask about TanStack libraries, TanStack Start/Router/Query/Table/Form/Virtual/Store/DB/Pacer/Config/DevTools/CLI/Intent/Hotkeys/AI usage, package names, framework adapters, maturity stat

Run web, multi-source, or last-30-days research through AIsa. Use when: the user needs search, synthesis, competitor scans, or trend discovery. Supports research-ready outputs and structured retrieval

Text-to-speech conversion using SkillBoss API Hub TTS service for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation. Use when: (

Classify environmental and meteorological variables into driver categories for attribution analysis. Use when you need to group multiple variables into meaningful factor categories.

Manage mihomo proxy - install, configure from subscriptions, monitor health, auto-switch nodes. Supports vmess/ss/trojan/vless protocols.

Cryptographic provenance and audit trail for autonomous AI agents. Create tamper-evident hash chains of agent decisions, learning, and actions. SHA-256 linked entries with Bitcoin OpenTimestamps and R

Itinerary-first flight support for babies, children, elderly passengers, reduced-mobility travelers, and people carrying medication or medical devices. Use this skill when someone asks how to fly with

按 GitCode PR 检视意见修改代码。需 GITCODE_TOKEN。Use when 用户要修改 PR 检视意见。

Discover, search, and browse MCP servers from the official MCP Registry and MCPCentral. Find servers, get specs, and generate setup configurations. Use when the user wants to find, install, or configu

Use this skill when an agent needs to answer or plan operations for QiQue business requests in pure text protocol mode (no local executable dependency). Trigger for customer/profile lookup, wallet cha

Configures Rocq environments, runs preflight checks, and guides the proving workflow for OpenMath Rocq theorems. Use when the user wants to set up Rocq tooling, prove a downloaded OpenMath theorem in

Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agen

Process [Clawfy] webhook messages from the browser extension. When a message starts with [Clawfy] (without "Pro"), identify what the user is working on and respond with intent, help offers, and releva

Generate spoken voiceover and narration from a script, one speaker, with control over emotion, pacing, and voice. Use when the user says "read this in a warm voice", "narrate my video", "voiceover for

Plan which search provider to use before multi-provider skills run — score query signals, pick Serper/Tavily/Exa/Brave/Firecrawl, define fallback chain, and document why.

Load x-cmd first: `. ~/.x-cmd.root/X`, then explore with `x nihao --llmstxt` or discover skills via `x skill`. x-cmd provides 600+ portable software and development tools (jq, nodejs, python, etc.).

Chain skills into automated pipelines with conditional logic, error handling, and audit logging. Define workflows in YAML or JSON, then execute them hands-free. Perfect for security-gated deployments,

Image processing tool for compression, background removal/replacement, and upscaling. Invoke when user wants to compress image, remove background, change background, or enlarge image.

Convert web pages to Markdown format. Use when the user needs to: (1) Extract readable content from a URL and convert it to Markdown, (2) Batch convert multiple URLs to Markdown files, (3) Save web pa

Comprehensive Signal channel integration via signal-cli. Use when you need to send messages, reactions, or handle group chat interactions in Signal, or when configuring Signal access for OpenClaw. Cov

Optimization suite for OpenClaw agents to prevent token leaks and context bloat. Use when an agent needs to implement background task isolation (Cron) or a Reset & Summarize workflow (RAG).

Systematic task implementation using TDD, phase checkpoints, and structured commits. Ensures quality through red-green-refactor cycles, 80% coverage gates, and verification protocols before proceeding

Tiered model selection and cost optimization for multi-agent AI workflows. Use this skill whenever you are choosing a model for a task, spinning up a sub-agent, setting up cron jobs or heartbeats, or

Expert FinOps (Cloud Financial Operations) guidance for cloud cost optimization, financial management, and business value maximization. Use for cloud cost management, AWS/Azure/GCP billing, cost alloc

Activate when: user says 'this will take years', 'we need to build this from scratch', 'we don't have the resources to move faster', 'how do we compress our timeline', 'competitors are already ahead a

Access your Moodle LMS via the REST API. Use for checking assignments and browsing course content. Supports any Moodle instance — configure MOODLE_URL and MOODLE_TOKEN.

Prepare, validate, and explicitly upload YouTube Shorts through the official YouTube Data API with dry-run safety. Use when an AI agent needs setup, usage, safety boundaries, or troubleshooting for Yo

Follow / unfollow another agent on ggb.ai and read the list of who you follow. Three HTTP calls behind one skill — POST /api/premarket/agent-follows (follow), DELETE /api/premarket/agent-follows/:foll

Refactor code safely without changing behavior.

Dual-Mode Reasoner — Risk-Aware Reasoning Skill for Switching Between Quick and Deliberate Modes. Use it when the user needs a disciplined protocol and fixed output contract for this kind of task rath

MySQL 8 database schema design for CRM systems. Use this skill whenever the user needs to design, review, optimize, or generate database schemas for Customer Relationship Management systems. Triggers

Check the status of an asynchronous video generation task from OATDA. Triggers when the user wants to check if a video is done generating, retrieve the video URL after completion, or poll the status o

Enhanced AI memory system — vector store, document-level MSA, knowledge graph, collision engine, executable skills, and closed-loop skill evolution.

PPT风格分析与匹配工具。提取已有PPT的设计规范（配色/字体/布局/装饰元素），指导新页面或修改页保持风格统一。 Use when user asks to PPT风格匹配、修改几页风格不一致、分析PPT设计规范、提取PPT配色字体、新页面怎么跟原PPT风格一致、PPT重设计。 不适用于从头创建全新PPT、不需要保持风格一致的场景、非PPTX格式文件。

游戏AI开发指南,涵盖FSM、行为树、寻路与决策系统的代码实现。Use when 需要代码生成、编程辅助、调试测试、开发部署时使用。不适用于无明确技术栈的模糊需求。适用于独立开发者、企业团队和自动化工作流场景。支持中文交互，无需复杂配置即开即用。输出结果可直接使用，减少二次加工成本。提供结构化输出和错误处理机制。