发现 Skills

Avoid common Ansible mistakes — YAML syntax traps, variable precedence, idempotence failures, and handler gotchas.

Interact with Apollo.io REST API (people/org enrichment, search, lists).

#1 on DeepResearch Bench (Feb 2026). Any-to-Any AI for agents. Combines deep reasoning with all modalities through sophisticated multi-agent orchestration. Research, videos, images, audio, dashboards, presentations, spreadsheets, and more.

Complete ChatGPT Apps builder - Create, design, implement, test, and deploy ChatGPT Apps with MCP servers, widgets, auth, database integration, and automated deployment

The master tool for all advanced audio/video processing. Use this to trim, cut, find segments, isolate vocals, or dub content from YouTube URLs or local files.

Analyze contracts for risks, check completeness, and provide actionable recommendations. Supports employment contracts, NDAs, service agreements, and more. Works with English and Chinese contracts.

Review business contracts for risks, missing clauses, unfavorable terms, and compliance gaps. Use when analyzing NDAs, MSAs, SaaS agreements, vendor contracts, SOWs, or employment agreements. Generates a structured risk report with recommendations. Built by AfrexAI.

Conduct deep financial research using CueCue's AI-powered multi-agent system

Control IKEA Dirigera smart home devices (lights, outlets, scenes, controllers). Use when the user asks to control smart home devices, check device status, turn lights on/off, adjust brightness/color, control outlets, trigger scenes, check battery levels, or work with IKEA smart home automation. Also use when the user needs help finding the Dirigera hub IP address or generating an API token. Accessible via Cloudflare tunnel on VPS.

Manage persistent VMs on exe.dev. Create VMs, configure HTTP proxies, share access, and set up custom domains. Use when working with exe.dev VMs for hosting, development, or running persistent services.

自动选择最佳搜索引擎的智能搜索工具。中文→Bing，英文→DuckDuckGo。无需 API Key，免费无限使用。

Financial analysis and research workflows for market research, equity research, comparable companies, precedent transactions, and DCF valuation. Use when asked to build or critique DCF models, comps/precedents tables, competitor or strategy analysis, market sizing, or to deliver analyst-ready outputs in Excel, PowerPoint, or Markdown from CSV/Excel/SQL/API/web data.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

FiveM RP server engineering for QBCore, ESX, and QBox. Use for framework-level scripting, fxmanifest.lua/config.lua validation, resource debugging, dependency orchestration, MLO/streaming fixes, performance optimization (client/server), artifact/gamebuild compatibility, inventory/job/gang systems, and SSH key generation for SFTP.

Generate images from text with a free-quota-first multi-provider workflow. Use this skill when a user asks for text-to-image generation that needs provider routing (Hugging Face, Gitee, ModelScope, A4F, OpenAI-compatible private endpoints), token pooling with automatic rotation on quota/auth failures, public API fallback for Hugging Face, prompt optimization, model fallback, batch generation in one command, and structured generation outputs.

Google Analytics 4, Search Console, and Indexing API toolkit. Analyze website traffic, page performance, user demographics, real-time visitors, search queries, and SEO metrics. Use when the user asks to: check site traffic, analyze page views, see traffic sources, view user demographics, get real-time visitor data, check search console queries, analyze SEO performance, request URL re-indexing, inspect index status, compare date ranges, check bounce rates, view conversion data, or get e-commerce revenue. Requires a Google Cloud service account with GA4 and Search Console access.

OpenAI GPT integration. Chat completions, image generation, embeddings, and fine-tuning via OpenAI API.

Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources.

Reduces token usage from paid providers by offloading work to local LM Studio models. Use when: (1) Cutting costs—use local models for summarization, extraction, classification, rewriting, first-pass review, brainstorming when quality suffices, (2) Avoiding paid API calls for high-volume or repetitive tasks, (3) No extra model configuration—JIT loading and REST API work with existing LM Studio setup, (4) Local-only or privacy-sensitive work. Requires LM Studio 0.4+ with server (default :1234). No CLI required.

Visual AI workflow builder - ComfyUI meets n8n for LLM agents, RAG pipelines, and multimodal data flows. Local-first, open source (AGPL-3.0).

Use Model Context Protocol servers to access external tools and data sources. Enable AI agents to discover and execute tools from configured MCP servers (legal databases, APIs, database connectors, weather services, etc.).

Use when conducting security audits, reviewing code for vulnerabilities, or analyzing infrastructure security. Invoke for SAST scans, penetration testing, DevSecOps practices, cloud security reviews.

Create professional PowerPoint presentations from outlines, data sources, or AI-generated content. Supports custom templates, style presets, charts and tables from data, and AI-generated images. Use when asked to create slides, pitch decks, reports, or presentations.

Generate regex patterns from plain English descriptions. Use when the user needs to create regular expressions without memorizing syntax.