Claude

Claude Code 개발 워크플로우 최적화. Context Engineering, Sub-agents, TDD, 개발 후 검증 워크플로우 제공. 트리거: CC 프로젝트 시작, CLAUDE.md/spec.md 작성, /handoff /verify /commit-push-pr, sub-agent/Explore, Agent Teams 병렬 개발 요청 시.

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

强大的信息获取工具。通过浏览器 + 用户登录态，获取公域和私域信息。可访问任意网页、内部系统、登录后页面，执行表单填写、信息提取、页面操作。

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.

Use the ctx7 CLI to fetch library documentation, manage AI coding skills, and configure Context7 MCP. Activate when the user mentions "ctx7" or "context7", needs current docs for any library, wants to install/search/generate skills, or needs to set up Context7 for their AI coding agent.

Use Exa for web/code/company research (web_search_exa / get_code_context_exa / company_research_exa), with parameters and examples; trigger when online search or parameter checks are needed.

OpenCLI — Make any website or Electron App your CLI. Zero risk, AI-powered, reuse Chrome login. 80+ commands across 19 sites.

Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, log into sites with a persistent profile, export screenshots or PDFs, manage multiple browser instances, or fall back to the HTTP API when the CLI is unavailable. Prefer this skill for token-efficient browser work driven by stable accessibility refs such as `e5` and `e12`.

Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring >5 tool calls. Supports automatic session recovery after /clear.

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.

Configure and optimize rendering in 3ds Max — V-Ray and Corona render settings, render elements, light mix, batch rendering, network rendering, denoising, and post-production workflows. Use when tasks involve setting up production renders, optimizing render times, batch rendering multiple views, or configuring render farms for archviz and product visualization.

Automate 3ds Max with MAXScript and Python — scene manipulation, object creation, material assignment, camera setup, batch operations, UI tools, and file I/O. Use when tasks involve automating repetitive 3ds Max workflows, batch processing scenes, creating custom tools, or scripting scene setup for archviz, product visualization, or VFX.

Deploy and configure 3proxy — a lightweight universal proxy server. Use when a user asks to set up HTTP, HTTPS, SOCKS4, SOCKS5, or transparent proxies, build proxy chains, configure authentication, set bandwidth limits, manage access control lists, set up proxy rotation, create multi-port proxy servers, configure logging and traffic accounting, or deploy a lightweight proxy without heavy VPN overhead. Covers all 3proxy features including proxy chaining, ACLs, traffic shaping, and multi-protocol support.

Builds Agent-to-Agent (A2A) servers and clients following Google's open protocol for agent interoperability. Use when the user wants to create an A2A-compliant agent, build an Agent Card, implement task management, connect agents across frameworks, set up agent discovery, handle streaming responses, implement push notifications, or orchestrate multi-agent workflows. Trigger words: a2a, agent to agent, agent2agent, a2a protocol, a2a server, a2a client, agent card, agent interoperability, agent collaboration, multi-agent, agent discovery, a2a sdk, a2a task.

When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.

You are an expert in Ably, the enterprise-grade realtime messaging platform. You help developers add pub/sub messaging, presence, chat, live updates, and event streaming to applications with guaranteed message ordering, exactly-once delivery, automatic reconnection, and global edge infrastructure — handling millions of messages per second with 99.999% uptime SLA.

Add premium animated UI components built with Framer Motion and Tailwind CSS using Aceternity UI. Use when: adding animated effects (3D cards, glowing backgrounds, spotlight effects, moving borders), building visually stunning UIs, creating impressive hero sections and feature showcases in React/Next.js.

Run GitHub Actions locally with act. Use when a user asks to test GitHub Actions workflows locally, debug CI pipelines without pushing, or run workflows offline.

Build workflow automations with Activepieces. Use when a user asks to self-host a Zapier alternative, automate workflows with a visual builder, create no-code integrations, or set up open-source business automation.

Actix Web is a powerful, high-performance web framework for Rust. It provides async handlers, type-safe extractors, middleware, and integrates with the Rust ecosystem for building fast, reliable, and memory-safe web services.

Optimize paid advertising campaigns across Google Ads, Meta, TikTok, LinkedIn, and other platforms. Use when tasks involve bid optimization, audience targeting, creative testing, ROAS improvement, attribution modeling, budget allocation, campaign structure, retargeting strategies, lookalike audiences, or reducing customer acquisition cost. Covers multi-platform campaign management and creative performance analysis.

Build full-stack web applications with AdonisJS — a batteries-included Node.js framework with ORM, auth, validation, and mailer built-in. Use when someone asks to "build a web app with Node.js", "Laravel for Node.js", "full-stack Node framework", "AdonisJS", "batteries-included backend", or "Node.js with built-in ORM and auth". Covers Lucid ORM, auth (sessions, tokens, social), VineJS validation, Edge templates, and deployment.

Automate Adobe After Effects workflows. Use when a user asks to script After Effects with ExtendScript or CEP, batch render compositions, automate motion graphics templates (MOGRTs), build render pipelines with aerender, create expressions for animations, manage project files programmatically, automate text and image replacements in templates, build data-driven motion graphics, integrate After Effects with CI/CD, or control AE via command line. Covers ExtendScript, CEP panels, expressions, aerender CLI, and template automation.

You are an expert in AG-UI (Agent-User Interaction Protocol), the open standard by CopilotKit for connecting AI agents to frontend UIs. You help developers stream agent actions, tool calls, state updates, and text generation to React components in real-time — enabling rich agent UIs where users see what the agent is thinking, doing, and can intervene at any step.

You are an expert in AG2 (formerly AutoGen), the open-source multi-agent conversation framework. You help developers build systems where multiple AI agents collaborate through structured conversations — with tool use, human-in-the-loop, code execution, group chat orchestration, and nested conversations — for complex tasks like software development, research, and data analysis.

Add persistent memory to AI coding agents — file-based, vector, and semantic search memory systems that survive between sessions. Use when a user asks to "remember this", "add memory to my agent", "persist context between sessions", "build a knowledge base for my agent", "set up agent memory", or "make my AI remember things". Covers file-based memory (MEMORY.md), SQLite with embeddings, vector databases (ChromaDB, Pinecone), semantic search, memory consolidation, and automatic context injection.

Run AI agent code safely in isolated sandboxes with resource limits, audit trails, and kill switches. Use when someone asks to "sandbox my agent", "run agent code safely", "add guardrails to AI agent", "isolate agent execution", "audit agent actions", "prevent agent from deleting files", "restrict agent permissions", or "add safety controls to AI coding agent". Covers Docker isolation, filesystem restrictions, network policies, resource locking, and comprehensive audit logging.

Coordinate multiple AI agents working together on complex tasks — routing, handoffs, consensus, memory sharing, and quality gates. Use when tasks involve building multi-agent systems, coordinating specialist agents in a pipeline, implementing agent-to-agent communication, designing swarm architectures, setting up agent orchestration frameworks, or building autonomous agent teams with supervision and quality control. Covers hierarchical, mesh, and pipeline topologies.

Detect AI-generated text using rule-based analysis, LLM-as-judge scoring, and optional external APIs. Use when: auditing content for AI authorship, academic integrity checks, editorial review, SEO content audits.

Run AI agent and LLM evaluations in CI/CD pipelines — automated quality gates that fail the build when AI output quality drops. Use when someone asks to "test my AI agent", "add evals to CI", "catch prompt regressions", "compare models", "evaluate LLM output quality", "set up AI quality gates", or "benchmark my agent before deploying". Covers eval frameworks (Cobalt, Promptfoo, Braintrust), LLM-as-judge scoring, threshold-based assertions, and GitHub Actions integration.

Implement safety guardrails for AI systems — content filtering, prompt injection detection, output validation, bias mitigation, and responsible AI practices. Use when tasks involve adding safety layers to LLM applications, detecting prompt injection attacks, filtering harmful content, implementing rate limiting for AI APIs, validating LLM outputs against schemas, building moderation pipelines, or ensuring AI systems comply with safety policies.

Run autonomous AI-driven penetration tests on web applications using tools like Shannon, PentAGI, and similar frameworks. Use when tasks involve setting up automated penetration testing pipelines, combining AI agents with security tools (nmap, subfinder, nuclei, sqlmap), building autonomous exploit chains, generating pentest reports with proof-of-concept exploits, or integrating AI pentesting into CI/CD pipelines. Covers the full pentest lifecycle from reconnaissance to reporting using AI orchestration.

You are an expert in the Vercel AI SDK, the TypeScript toolkit for building AI-powered applications. You help developers integrate LLMs (OpenAI, Anthropic, Google, Mistral, Ollama) with React Server Components, streaming UI, tool calling, structured output with Zod schemas, RAG pipelines, multi-step agents, and edge-compatible AI features — the standard way to add AI to Next.js, Nuxt, SvelteKit, and any Node.js app.

Generate complete presentations with AI — from outline to polished slides. Use when a user asks to create a presentation, build slides, make a pitch deck, generate a slide deck, create a keynote, prepare a talk, build a demo presentation, or produce any slide-based content.

You are an expert in Aider, the terminal-based AI coding assistant that reads your codebase, makes changes across multiple files, and creates proper git commits. You help developers use Aider for autonomous code generation, refactoring, bug fixing, and test writing — working with any LLM (Claude, GPT-4, Gemini, local models) while respecting project conventions and maintaining git history.

You are an expert in Airbyte, the open-source data integration platform with 300+ pre-built connectors. You help developers sync data from SaaS tools, databases, and APIs into data warehouses and lakes — handling incremental syncs, CDC (Change Data Capture), schema evolution, and error recovery for production data pipelines.

Apache Airflow is a platform for programmatically authoring, scheduling, and monitoring workflows. Learn to write DAGs, use operators, set up connections, configure scheduling, and deploy with Docker Compose.