AI & ML

evolv3ai Bundle

Client-agnostic MCP server management. Registry-first approach that scans MCP clients, normalizes server configs, and maintains a central registry under ADMIN_ROOT. Use when: installing MCP servers, scanning client configs, updating registries, or troubleshooting MCP issues across clients.

evolv3ai Bundle

Comprehensive guide to sub-agents in Claude Code: built-in agents (Explore, Plan, general-purpose), custom agent creation, configuration, and delegation patterns. Use when: creating custom sub-agents, delegating bulk operations, parallel research, understanding built-in agents, or configuring agent tools/models.

evolv3ai Bundle

Install and configure MCP (Model Context Protocol) servers for Claude Desktop on Windows. Covers installation workflows, claude_desktop_config.json management, MCP registry patterns, and the three CLI tools: Desktop Commander, Win-CLI, and Claude Code MCP. Use when: installing MCP servers, configuring Claude Desktop, choosing between MCP CLI tools, managing MCP registries, or troubleshooting "MCP server not starting", "tool not found", "spawn ENOENT" errors.

evolv3ai Bundle

Set up and operate the RLM (Recursive Language Models) Orchestrator for processing arbitrarily large contexts. Handles Rust builds, Ollama/LiteLLM provider configuration, WASM compilation targets, and query workflows. Use when: setting up RLM project, configuring LLM providers for RLM, running queries against large files (10MB+), troubleshooting WASM compilation errors, or analyzing conversation exports.

kychiou Bundle

Context7 MCP - Get up-to-date library documentation to reduce AI hallucinations.

keonho-kim Bundle

Run Codex CLI jobs inside subdirectories of the current working directory using JSON-only batch input and optional parallelism. Use when you need to execute codex exec --model gpt-5.2-codex across one or more subdirectories with strict safety checks (no '..', no current dir, cwd boundary enforced).

severith-ai Bundle

Validate skill.md files against the agent skill specification

eric-bot-labs Bundle

Use Exa's hosted MCP server (mcp.exa.ai) to do web search, deep research, crawling, company research, and people research via MCP tools like web_search_exa, deep_search_exa, crawling_exa, company_research_exa, people_search_exa, deep_researcher_start/check. Trigger this skill when you need high-quality web research results and Exa MCP is available, especially if the built-in web_search tool is unavailable or lacks an API key.

btgaskin Bundle

Build production AI agents with the Claude Agent SDK. Use when working with: (1) Creating autonomous agents with query() or ClaudeSDKClient, (2) Defining custom tools via in-process MCP servers, (3) Implementing hooks for tool interception and permissions, (4) Building multi-agent systems with subagents, (5) Managing sessions and state across queries, (6) Integrating MCP servers for external capabilities. Covers Python and TypeScript SDKs with production patterns.

craigmcdonnell Bundle

Guide for creating and maintaining comprehensive AI Agent specifications (SPEC.md) based on Addy Osmani's "Spec-Driven Development" methodology. Use when the user wants to start a new project, formalize requirements, or update an existing spec.

kpbray Bundle

Creates and modifies Power BI semantic models using TMDL format. Use for tables, columns, relationships, and model configuration.

leemg1476 Skill

Generate executable FastMCP server/connector scaffolding from one or more mcp_init.md specs (per-MCP folders or file lists). Apply envelope/env-var conventions, required directory layout, and leave TODOs+Assumptions when specs are incomplete. Never emit pytest/tests.

leemg1476 Skill

Create or update production-grade pytest scaffolding and tests for FastAPI servers (agent server / MCP server). Use when asked to add unit/integration/e2e tests, pytest config, fixtures, or CI-ready test workflows for FastAPI apps.

twj011 Bundle

---

matperez Skill

Исследует юридические риски проектов, организующих офлайн-мероприятия (B2C/B2B). Определяет модель ответственности (исполнитель/агрегатор), рекомендует организационно-правовую форму, формирует договорную архитектуру, проверяет потребительское право, безопасность, интеллектуальные права, персональные данные. Use when user wants to analyze legal risks for event organization business, determine liability model, draft contracts, or check compliance with consumer protection laws.

vadimcomanescu Bundle

Prompt engineering workflow for building reliable assistants and agents: task decomposition, instruction hierarchy, tool-use patterns, safety constraints, and evaluation design. Use when writing or refactoring system prompts, creating structured prompts, building prompt test suites, or debugging regressions in LLM behavior.

mwd1234 Skill

Audit for performance and battery - layout thrash, heavy animations, timers, background tasks. Identifies hotspots affecting smoothness and power consumption. Use before releases or when users report lag/battery drain.

nesbo Bundle

Add Serena MCP to Any Project

vadimcomanescu Bundle

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

vadimcomanescu Bundle

Data science workflow for turning ambiguous questions into measurable metrics, experiments, and models. Use when framing hypotheses, selecting metrics, designing A/B tests, building predictive models, doing error analysis, or writing experiment/model reports with clear assumptions and caveats.

vadimcomanescu Bundle

Computer vision engineering workflow for dataset design, model selection (detection/segmentation/classification), evaluation, inference optimization, and deployment. Use when planning or reviewing CV systems, auditing datasets, defining metrics/splits, or diagnosing model/inference issues.

ethan2988 Bundle

麦当劳优惠券助手skill。当用户需要配置麦当劳MCP服务器、自动领取优惠券、查看优惠券信息时使用此skill。包括：1) 指导用户获取MCP token（访问 https://open.mcd.cn/mcp/doc），2) 配置opencode的麦当劳MCP服务器，3) 自动领取所有可用优惠券，4) 分析优惠券信息并生成Markdown表格，5) 提供优惠券使用建议。

shihan-1147 Bundle

基于 RAG 的知识库检索技能。从本地文档中检索相关信息，支持语义搜索和精确匹配。适用于问答、信息查询、文档理解等场景。

shihan-1147 Skill

Prompt engineering expert that helps users craft optimized prompts using 57 proven frameworks. Use when users want to optimize prompts, improve AI instructions, create better prompts for specific tasks, or need help selecting the best prompt framework for their use case.

vadimcomanescu Bundle

LangChain framework for building LLM apps with agents, chains, and RAG across providers. Use for chatbots, tool-calling agents, and retrieval workflows in prototypes or production.

vadimcomanescu Bundle

LlamaIndex framework for data-centric LLM apps and RAG. Use for document ingestion, indexing, querying, and building retrieval-driven chatbots or knowledge tools.

vadimcomanescu Bundle

Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.

mb-mal Skill

Design software architecture around business domain models. Use when starting a new project, creating module structure, defining entities and their relationships, or when the user mentions DDD, domain model, bounded context, aggregates, or business logic architecture.

vadimcomanescu Bundle

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.

chandeldivyam Bundle

Delegate a task to a separate Codex process by running `codex exec --json` and logging the full JSONL event stream to a timestamped folder under `~/.codex/sub_agent_runs/`. Use when you want a lightweight “sub-agent” workflow where the main agent provides only a prompt, and the runner script handles run folders, prompt capture, and printing the JSONL path.

zysilm Skill

AI video production workflow using Google Flow via MCP Playwright browser automation. Creates any video type: promotional, educational, narrative, social media, animations, game trailers, music videos, product demos, and more. Use when users want to create videos with AI, need help with video storyboarding, keyframe generation, or video prompt writing. Follows a philosophy-first approach: establish visual style and production philosophy, then execute scene by scene with user feedback at each stage. Requires MCP Playwright server and a Google account with Flow access (Google AI Pro or Ultra subscription).

mehdiozdemir Skill

Transforms vague or poorly structured prompts into clear, effective, and well-optimized instructions for AI models. Use when users need help improving their prompts, want better AI responses, or request prompt optimization for any task including coding, writing, analysis, or creative work.

jolo-stack Bundle

Setup Snowflake managed MCP server with Claude Desktop using PAT authentication. Use when: connecting Claude Desktop to Snowflake MCP, setting up MCP server, configuring claude_desktop_config.json. Triggers: snowflake mcp, claude desktop mcp, mcp server setup, PAT authentication mcp.

chirag2653 Bundle

Generate professional images using Google's Gemini 3 Pro or Gemini 2.5 Flash image models with AI-powered prompt enhancement. Universal Python script works on all platforms. Supports custom aspect ratios (1:1, 16:9, 9:16), resolutions (1K-4K), reference images, and Google Search grounding. Activate when user says "Generate an image with Gemini", "Create using Gemini Pro/Flash", "Use Gemini to make [image]", or any image generation request mentioning Gemini/Imagen.

sygnaltech Bundle

Documentation for the Notion API. Use this skill when users ask about integrating with Notion, building Notion integrations, working with pages, databases, blocks, comments, files, or using Notion's MCP (Model Context Protocol) for AI tools.

belokonm Skill

Expert in making multi-agent systems resilient. Specializes in detecting loops, hallucinations, and failures, and implementing self-healing workflows. Use when designing error handling for agent systems, implementing retry strategies, or building resilient AI workflows.