Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Use quando o usuário pede para promover uma entrada ou backlog já refinado, criar, iniciar ou consolidar uma especificação nova ou ainda em Draft em `spec.md`. Use também quando uma transição automática exigir criar ou completar a fonte normativa inicial. Inicializa specs em `specs/draft/` e aplica o MCR-10; para mudar spec aprovada use specsfy-update-spec, para captura sem perguntas use specsfy-01-inbox, para refinamento use specsfy-02-backlog e para revisão sem edição use specsfy-04-validate.
Use quando o usuário quer quebrar ou decompor a especificação em tarefas, preencher ou atualizar a seção `14. Tarefas` de `spec.md`, ordenar dependências, planejar fatias verticais ou preparar a execução. Use também quando uma transição automática pedir planejamento, replanejamento ou retomada após RED. Use somente para editar o backlog dentro da fonte única; não crie tasks.md, não escreva código nem marque trabalho como concluído.
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, test web applications, or extract information from web pages.
Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool APIs, implementing permission systems, or creating autonomous coding assistants.
Token-reduction skill for coding agents. Compresses JSON tool output, build logs, grep/ripgrep search results, source code, and conversation history the same way the Headroom proxy does — but in-context, with no binary install. Use this skill whenever an agent is about to paste a large tool result (a 1000-row JSON array, a 5000-line pytest log, a 200-result grep, a 1000-line source file) into its next message, or when the agent's conversation is approaching the context limit, or when the user complains about token cost or latency. Also use it to shape the agent's own output: skip ceremony, don't restate code already on screen, drop reasoning on routine turns. Triggers: "compress this output", "this is too long", "trim", "summarize the log", "reduce tokens", "context is full", "running out of context", "too many tokens", "make it shorter", "be terse"
Connect an AI coding agent to Proxyman MCP. Use when Proxyman is installed but the agent cannot see tools, or when configuring Codex, Claude, Cursor, VS Code, or Copilot and troubleshooting bridge, handshake, or tool-discovery errors.
Manage a task backlog through the tasks-axi CLI - add, list, show, start, and complete tasks; track blocked-by dependencies, structured holds, and a ready queue; prune and normalize a hand-editable backlog.md. Use whenever a task touches backlog or task state: filing or dispatching work, recording a PR or report on completion, finding dispatchable or held work, or trimming the Done list.
Use the Browser Use cloud API to spin up cloud browsers for Clawdbot and run autonomous browser tasks. Primarily, create browser sessions with profiles (persisted logins/cookies) that Clawdbot can control. Secondarily, run task subagents for fast autonomous browser automation. Docs at docs.browser-use.com and docs.cloud.browser-use.com.
Expert in LangGraph—the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when: langgraph, langchain agent, stateful agent, agent graph, react agent.
Install and configure ToolUniverse for any use case — MCP server (chat-based), CLI (command line with 14 subcommands), or Python SDK (Coding API with 3 calling patterns). Covers uv/uvx setup, MCP configuration for 12+ AI clients (Cursor, Claude Desktop, Windsurf, VS Code, Codex, Gemini CLI, Trae, Cline, etc.), full CLI reference (tu list/grep/info/find/run/test/status/build/remote/doctor/serve/connect/connections/disconnect), Coding API quickstart, agentic tools, code executor, API key walkthrough, skill installation, and upgrading. Use when user asks how to set up ToolUniverse, which access mode to use (MCP vs CLI vs SDK), configuring MCP servers, using the CLI, troubleshooting installation, upgrading, or mentions installing ToolUniverse or setting up scientific tools. Also triggers for “how do I use ToolUniverse”, “what's the best way to access tools”, “command line”, “tu command”, “coding API”, “tu build”
Direct-connection automation for personal WeCom accounts. Built on the Wechaty framework, it supports receiving WeCom messages, automatically accepting friend requests, knowledge-base Q&A, and alerts for human intervention. Suitable for personal WeCom bots and automation assistant scenarios.
This skill should be used when orchestrating multi-agent swarms using Claude Code's TeammateTool and Task system. It applies when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns.
Use when the user asks for overall progress, the status of all specifications, percentage completed, remaining work, blockers, or next work in the Specsfy repository, or when an automatic transition requests the final projection or routing based on the observed state. Produces a read-only overview of specs, gates, tasks, and checklists; do not use it to change the specification or implement tasks.
A Webflow University guided onboarding skill for anyone getting started with the Webflow MCP. Checks your Webflow connection, helps you choose a real workflow to try, coaches prompt writing, and supports you through your first MCP run.
Monitorar e ajudar a descobrir, formular e registrar regras duráveis em .specsfy/RULES.md sem alterar ou remover regras existentes. Use quando o monitor de contexto apontar revisão de regras; quando o usuário quiser adicionar regras do projeto; quando uma convenção recorrente precisar virar instrução explícita; ou ao revisar conflitos e duplicatas. Não inventa regras nem promove preferências sem confirmação.
How to work in a Codebase Wiki project (the `codebase-wiki` starter pack): an agent-authored, source-grounded wiki of the surrounding codebase. Read when the project has a `wiki/` knowledge base with `architecture/`, `modules/`, `flows/`, `concepts/`, and `guides/` sections plus `wiki/OVERVIEW.md`, or when asked to generate or refresh a wiki of this codebase. Includes per-folder rules and freshness and log discipline, summarizes audience/depth settings and source-reference conventions, and bundles the full generation/refresh procedure in `references/`. Complements the platform `open-knowledge` skill; does not replace it.
Thin router for Pipefy build and configure asks: map user intent to the correct domain skill (pipes, automations, AI agents, iPaaS, portals, etc.). Use when the user wants to create, build, configure, or integrate something in Pipefy and you need to know which skill to open. Do not use this skill as a delivery playbook — if the user already has a building skill or a detailed build prompt, follow that for how to build; use this skill only for which Pipefy domain skill to read.
Hand off the current thread to a new Pulumi Neo task as a one-way transfer. Use when the user explicitly asks to hand off, send, transfer, or continue current work in Pulumi Neo (e.g. "hand this to Neo", "continue in Neo", "/neo-handoff"). Do not load when the user only mentions Neo, asks what Neo can do, asks for an AI-written PR or preview explanation, or hands off to a different agent.
When the user wants to build or improve a sales bot's ability to ask the right questions to score and route leads automatically. Also use when the user mentions "bot qualification," "automated lead scoring," "qualification questions," "lead routing," or "qualification flow."
Use when the user describes a task and wants to know whether something similar has been done before, then turn the closest prior session into a task playbook. Triggers on phrases like "have we done this before", "recall how we did X", "find similar work", "any precedent for", "has anyone solved", "is there a template for", and "how did we do this last time"
QVeris provides professional data and tool access for AI. Use standardized capabilities/query for qveris_finance.* CAP workflows, or discover/call for specialized services such as real-time data, historical sequences, structured reports, web extraction, PDF workflows, media generation, OCR, TTS, translation, and more. Requires QVERIS_API_KEY.
Systematic step-by-step reasoning with revision and branching. Use for complex problems, multi-stage analysis, design planning, problem decomposition, or when the scope is unclear, alternative approaches are needed, or revision is required
Extension reference for Claude Code (code.claude.com). Covers Agent Skills (SKILL.md), slash commands, output styles, subagents (cross-session messaging), agent teams, agent view, workflows, routines, scheduled tasks, hooks (PreToolUse / PostToolUse), mods (Claude Code mods), plugins, plugin eval, plugin marketplace (marketplace.json), MCP configuration (.mcp.json / claude mcp add), managed MCP, channels (--channels / claude/channel push events, webhook / telegram / discord / imessage), tools-reference, advisor, and ultrareview.
Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.
You MUST use this right after a spec or implementation plan is saved or edited as Markdown - by scope-triage, plan-crafting, or the user via /scope-check <path> - to render it as an HTML preview behind a clickable file link and to list it in the folder README index. Not for general Markdown editing or for opening a browser.
Ultra-compressed Chinese communication mode. Express complete technical information with fewer Chinese characters while preserving code, terminology, original error messages, and key constraints. Supports intensity levels: lite, full (default), and ultra. Use when the user says “中文 caveman,” “穴居人模式,” “更简短,” “少点字,” or “用中文 caveman,” or invokes /caveman-cn. Also applies to Chinese conversations where the user explicitly asks to save tokens.
Expert integration patterns for Claude API and TypeScript SDK covering Messages API, streaming responses, tool use, error handling, token optimization, and production-ready implementations for building AI-powered applications
Drives a live multi-turn conversation with a LiveKit agent running locally, using `lk agent debugger`. Use when the user says "test my agent", "try my agent", "does this work", or "why did it call that tool", after editing an agent to check how it behaves, or when an agent on a speech-to-speech model or one that mishears users needs checking. The default for a bare "test"; for regression tests use testing-livekit-agents, for graded runs running-livekit-simulations.
When the user wants to build or improve a sales bot's ability to identify common pushbacks and deliver appropriate responses. Also use when the user mentions "detecting objections," "handling objections automatically," "bot objection handling," "automated objection responses," or "objection classification."
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.