Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
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.
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. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).
This skill should be used when the user wants to "deploy an agent", "deploy my ADK agent", "set up CI/CD", "configure secrets", "troubleshoot a deployment", or needs guidance on Agent Runtime, Cloud Run, or GKE deployment targets, or binding an agent to an Agent Gateway. Covers deployment workflows, service accounts, rollback, and production infrastructure. Applies to any framework agents-cli deploys (ADK, LangChain, ...). Part of the agents-cli skills suite. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), evaluation (use google-agents-cli-eval), or project scaffolding (use google-agents-cli-scaffold).
Use this skill when the user wants to “publish an agent,” “publish my ADK agent,” “register an agent with Gemini,” “publish to Gemini” (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use it when the user wants to “manage agents in Agent Registry,” “list/update/delete registered agents,” or “register an MCP server.” Covers ADK vs. A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do not use for deployment (use google-agents-cli-deploy).
This skill should be used when the user wants to "develop an agent", "build an agent using ADK", "run the agent locally", "debug agent code", "test an agent", "deploy an agent", "publish an agent", "monitor an agent", or needs the ADK (Agent Development Kit) development lifecycle and coding guidelines. Entrypoint for building ADK agents. Always active — provides the full workflow (scaffold, build, evaluate, deploy, publish, observe), code preservation rules, model selection guidance, and troubleshooting steps for ADK or any agent development.
Use this skill when the user wants to “run an evaluation,” “evaluate my agent,” “evaluate my ADK agent,” “write an eval dataset,” “analyze eval failures,” “compare eval results,” “optimize agent,” or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do not use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
This skill should be used when the user wants to "create an agent project", "start a new ADK project", "build me a new agent", "add CI/CD to my project", "add deployment", "enhance my project", or "upgrade my project". Part of the agents-cli skills suite. Covers `agents-cli scaffold create`, `scaffold enhance`, and `scaffold upgrade` commands, template options, deployment targets, and the prototype-first workflow. Do NOT use for writing agent code (ADK projects: use google-agents-cli-adk-code) or deployment operations (use google-agents-cli-deploy).
This skill should be used when the user wants to "set up tracing", "monitor my agent", "configure logging", "add observability", "debug production traffic", or needs guidance on monitoring deployed agents, including ADK (Agent Development Kit) agents. Covers Cloud Trace, prompt-response logging, BigQuery Agent Analytics, third-party integrations (AgentOps, Phoenix, MLflow, etc.), and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment setup (use google-agents-cli-deploy) or API code patterns (use google-agents-cli-adk-code).
Use when users ask to discover, install, list, check, update, remove, back up, restore, sync, or initialize Agent Skills, mention `bunx skills`, `npx skills`, `skills.sh`, or `skills-lock.json`, ask "find a skill for X", or want help extending agent capabilities with installable skills.
Use when routing Claude Code through a local LiteLLM proxy to GitHub Copilot, reducing direct Anthropic spend, configuring ANTHROPIC_BASE_URL or ANTHROPIC_MODEL overrides, or troubleshooting Copilot proxy setup failures such as model-not-found, no localhost traffic, or GitHub 401/403 auth errors.
Use when work depends on the user's live browser session or visible rendered state rather than static fetches, especially for browser debugging contexts or DevTools-selected elements or requests, logged-in dashboards or CMS flows, localhost apps, forms, uploads, downloads, media inspection, DOM or iframe inspection, Shadow DOM, or browser failures that look like soft 404s, auth walls, anti-bot checks, or rate limits.
Lark Base operations: creating tables, fields, records, views, statistics, formulas/lookup, forms, dashboards, workflows, and role permissions. Use this for Base/multi-dimensional table/bitable or /base/ links. Route file imports to lark-drive and authentication/authorization to lark-shared.
Feishu spreadsheets: create and operate spreadsheets. Supports creating spreadsheets, managing worksheets and row/column structure (add/delete, merge, resize, hide, freeze), reading and writing cells (values, formulas, styles, comments, cell images), find and replace, atomic batch updates with multiple operations, and creating and maintaining objects such as charts, pivot tables, conditional formatting, filters, sparklines and floating images. Use when the user needs to create spreadsheets, manage worksheets, batch read/write or edit data, aggregate and visualise data, beautify tables, calculate formulas (including Excel formula migration), or build financial models (DCF, three-statement, budgets, sensitivity analysis, etc.). If the user wants to search for spreadsheet files by name or keyword in cloud space (cloud drive/cloud storage), use lark-drive's drive +search first to locate the resource. When the user provides a doubao.com /sheets/ URL/token, use this skill directly rather than falling back to WebFetch because the domain is not Feishu; routing is based on the URL path pattern and token, not the domain.
Lark Wiki: manage knowledge spaces, space members, and document nodes. Create and query knowledge spaces, view and manage space members, manage node hierarchy, organize documents and shortcuts in the knowledge base. Use when users need to find or create documents, browse knowledge space structure, view or manage space members, or move or copy nodes. When users provide a doubao.com /wiki/ URL/token, use this skill directly without falling back to WebFetch due to domain name; routing is based on URL path pattern and token, not domain name. Not responsible for: uploading files to knowledge base nodes (use lark-drive), editing document/sheet/Base content (use lark-doc / lark-sheets / lark-base).
Lark Whiteboard: query and edit whiteboards in Lark Cloud Documents. Supports exporting whiteboards as preview images, exporting raw node structures, and updating whiteboard content using multiple formats. Use this skill when users need to view whiteboard content, export whiteboard images, or edit whiteboards. Not responsible for: Lark Cloud Documents content editing (lark-doc), embedded spreadsheets/Base in documents (lark-sheets / lark-base).
Lark Minutes: Search minutes, view minutes basic information, download/upload audio and video, read or edit minutes output content, change titles, replace speakers/keywords. Use when given minute_token or local audio/video files to query/modify/convert minutes output; local audio/video to minutes/transcript should prioritize this skill, do not use ffmpeg/whisper for local transcription. Not responsible for: retrieving meeting-associated minutes or locating minutes by natural language title only.
Lark VC: Search historical meeting records, query meeting notes (summaries/action items/chapters/transcripts), and retrieve attendee snapshots. Use when users query completed meetings, retrieve meeting outputs (notes/minutes), or view attendees; for future schedules, use lark-calendar. Not responsible for: Agent actual meeting entry/exit, real-time in-meeting events (use lark-vc-agent).
Meeting notes organization workflow: Consolidate meeting notes within a specified time range and generate structured reports. Use when users need to organize meeting notes, generate weekly meeting reports, or review meeting content over a period of time.
Native OpenAPI exploration for Feishu/Lark: discover native OpenAPI interfaces from official documentation that are not wrapped by CLI. Use when user needs cannot be met by existing lark-* skills or lark-cli registered commands and native Feishu OpenAPI lookup and invocation is required.
Lark Slides: create and edit slides. Create presentations, read slide content, manage slide pages (create, delete, read, partial replace). Use when users need to create or edit slides, or read or modify individual pages. When users provide a doubao.com /slides/ URL/token, use this skill directly instead of falling back to WebFetch due to domain name differences; routing is based on URL path pattern and token, not domain. Not responsible for: cloud document content editing (use lark-doc), standalone whiteboard objects in cloud documents (use lark-whiteboard; note that flowcharts/architecture diagrams embedded in slides still belong to this skill), uploading or downloading regular files (use lark-drive).
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into `${CODEX_HOME:-$HOME/.codex}/pets/<name>/` and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as `runcomfy run openai/gpt-image-2/edit` to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no `$imagegen`, no OPENAI_API_KEY required, only RUNCOMFY_TOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
See what your AI agent is doing, from anywhere. The agent keeps writing — logs, code, generated outputs, screenshots, artifacts. One command turns the folder into a live URL you (or a teammate) open in any browser to watch files evolve, edit in place, or comment — no sync, no zip, no account. Workspaces stay live 24 hours anonymously; one email claim keeps them permanent. Hosted on Cloudflare. Triggers on "show me what the agent is doing", "open the agent's folder", "share this folder", "give me a link", "hand off this workspace", or any ask to make an agent's local file state visible from another device or to another person.
Lark video conference in-meeting capabilities: allows application bots to truly join or leave ongoing meetings, read in-meeting events visible to the current identity, send in-meeting text messages or reactions. Applicable for user inquiries about what is happening in an ongoing meeting, who is speaking, whether content is being shared, or discovering currently readable meeting IDs in progress. Not responsible for ended meeting searches, participant snapshots, meeting summaries, transcripts, or recording queries—use the lark-vc skill for those.
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.
Coordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator loops, and decomposing work across agents. Use `orca-cli` for full ownership handoffs — "hand off", "handoff", "handover", "give this to another agent", "another worktree" — unless asked to supervise, monitor, or coordinate a DAG, and for terminal control, lightweight terminal prompts, shell commands, Orca worktree management, and reading or waiting on terminals.
Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video
Discover, vet, and install agent skills by searching ACROSS every major registry at once — skills.sh, clawhub.ai, and GitHub — presenting each board on its own native metric (installs / stars) with the top entry per board, security-scanning the top candidates' real SKILL.md for risky patterns, and flagging what's already installed. Use when the user asks "how do I do X", "find a skill for X", "is there a skill that…", "what skill should I install for…", or wants to extend the agent with a capability that might already exist as a published skill. Unlike single-registry search, this surfaces the best of every platform side by side, so you recommend the genuinely relevant, popular, well-maintained, and SAFE one — not whatever ranked first on one site.
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.