Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Delegate longer coding, troubleshooting, testing, or interactive CLI work to an inner command-line coding Agent in tmux. The outer Agent breaks down tasks, reads stable screen snapshots, corrects course, performs final acceptance, and destroys the inner session when the task is complete. Use when the user explicitly asks to use cc-use, wants long implementation work delegated to an inner Agent, needs supervised work in a real Codex CLI or Claude Code TUI, or needs to evaluate triggering cc-use through an external scheduler such as cron, launchd, or systemd.
Optimize a named target with a measured loop: attribute a workload's cost, or score variants and keep winners. Use when a working system's metric should move and the winning change is not already known. Use ce-debug for diagnosis; use ce-work when the change is already known.
Provides Qwen Coder CLI delegation workflows for coding tasks using Qwen2.5-Coder and QwQ models, including English prompt formulation, execution flags, and safe result handling. Use when the user explicitly asks to use Qwen for tasks such as code generation, refactoring, debugging, or architectural analysis. Triggers on "use qwen", "use qwen coder", "delegate to qwen", "ask qwen", "second opinion from qwen", "qwen opinion", "continue with qwen", "qwen session".
Delegate a coding task to the Mistral Vibe CLI (`vibe`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Vibe — phrasings like "have Vibe implement X", "delegate this to Vibe", "run it through Mistral Vibe", "use vibe to implement/fix/refactor" — or wants to run a queue of coding tasks through Vibe while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
Vision-driven desktop automation using Midscene. Control your local desktop (macOS, Windows, Linux) or a remote Windows desktop over RDP with natural language commands. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visible elements on screen regardless of technology stack. ⚠️ In local mode this takes over the user's real mouse and keyboard. For web apps, prefer "Browser Automation" instead. Only use this for desktop-native apps (Electron, Qt, native macOS/Windows/Linux) that cannot run in a browser, or for driving a remote Windows host via RDP. Triggers: open app, press key, desktop, computer, click on screen, type text, screenshot desktop, launch application, switch window, desktop automation, control computer, mouse click, keyboard shortcut, screen capture, find on screen, read screen, verify window, close app, test Electron app, rdp, remote desktop, windows server, connect via rdp Powered by Midscene.js (https://midscenejs.com)
Control and interact with a live browser session on any scraped page—click buttons, fill forms, navigate flows, and extract data using natural language prompts or code. Replaces the old firecrawl-browser command. Use when the user needs to interact with a webpage beyond simple scraping: logging in to a site, submitting forms, clicking through pagination, handling infinite scroll, navigating multi-step checkout or wizard flows, or when a regular scrape failed because content is behind JavaScript interaction. Also useful for authenticated scraping via profiles. Triggers on “browser”, “instruct”, “click”, “fill out the form”, “log in to”, “sign in”, “submit”, “paginated”, “next page”, “infinite scroll”, “interact with the page”, “navigate to”, “open a session”, or “scrape failed”.
Use this skill to upgrade Einstein Bots into Agentforce agents end to end in a single pass, orchestrating per-bot Agent Spec generation, planner reconciliation across bots, agentforce-generate authoring, and post-conversion .agent enhancements. TRIGGER when: the user asks to migrate, upgrade, or convert one or more Einstein Bots (BotDefinition/BotVersion chatbots) to Agentforce agents; runs a multi-bot bot-to-agent upgrade; needs Einstein Bot metadata turned into Agent Spec handoffs and generated .agent agents; convert bots to agents; upgrade my service bots; move bots to Agentforce. DO NOT TRIGGER when: the user already has an approved Agent Spec and only wants direct .agent authoring, deploy, test, or observe flows; the user wants to migrate or upgrade an EXISTING Agentforce agent from a legacy GenAiPlannerBundle to an NGA aiAuthoringBundle (that is agentforce-generate's 'Migrate a Legacy Agent to Agent Script' flow, not an Einstein Bot upgrade); the request is unrelated to Einstein Bot migration.
Use when building AI agent storage workflows on Tigris — forks for isolated dataset copies, workspaces for per-agent buckets with TTL, checkpoints for snapshot/restore, and coordination for event-driven pipelines via bucket webhooks. Triggers on "@tigrisdata/agent-kit", "agent storage", "agent workspace", "agent fork", "isolated agent environment", "checkpoint and restore", "bucket webhook", "multi-agent pipeline"
Set up or troubleshoot @przeprogramowani/10x-cli for a 10xDevs learner: reuse or install a compatible CLI, check authentication and course access, choose the project and AI tool, and hand off to 10x-cli-guide. Use for installation, updates, npm permissions, and onboarding. Excludes CLI source development and everyday download/use/sync guidance once setup is ready.
Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.
Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2, v3, or v4), browser-use-sdk (Python or TypeScript), X-Browser-Use-API-Key authentication, cloud sessions, browser profiles, profile sync, CDP WebSocket connections, stealth browsers, residential proxies, CAPTCHA handling, webhooks, workspaces, the skills marketplace, liveUrl streaming, pricing, or integration patterns (chat UI, subagents, adding browser tools to existing agents). Also trigger for questions about n8n/Make/Zapier integration, Playwright/Puppeteer/Selenium on cloud infrastructure, or 1Password vault integration. Do NOT use this for the open-source Python library (Agent, Browser, Tools config) — use the open-source skill instead.
Design new Claude skills from structured idea specifications. Use when the skill auto-generation pipeline needs to produce a Claude CLI prompt that creates a complete skill directory (SKILL.md, references, scripts, tests) following repository conventions.
Validate multi-skill workflows defined in CLAUDE.md by checking skill existence, inter-skill data contracts (JSON schema compatibility), file naming conventions, and handoff integrity. Use when adding new workflows, modifying skill outputs, or verifying pipeline health before release.
Use when the user wants to download, use or update 10xDevs CLI skills, choose a helper installation channel, inspect course content, switch tool profiles, see what changed in 10x-toolkit releases (changelog) or troubleshoot CLI/auth/content conflicts. Guides filtered get → an actual agent task → sync while preserving local work and course/tool/language context. For first installation or authentication preparation, use an available 10x-cli-setup copy. Does not implement CLI runtime or grant course access
Guide for using Apollo MCP Server to connect AI agents with GraphQL APIs. Use this skill when: (1) setting up or configuring Apollo MCP Server, (2) defining MCP tools from GraphQL operations, (3) using introspection tools (introspect, search, validate, execute, explorer), (4) configuring authentication, CORS, health checks, or telemetry, (5) writing Rhai scripts for request lifecycle hooks, (6) defining MCP prompts, (7) troubleshooting MCP server connectivity or tool execution issues.
Entry point for Alibaba Cloud Bailian web search: routes web search, webpage search, and latest-news queries. First identify the current connection: Token Plan (profile `token-plan` or base_url host `token-plan.<region>.maas.aliyuncs.com`) → built-in model search (`bl text chat --api responses --tool '{"type":"web_search"}'`); otherwise/default → Bailian MCP (`bl search web`). Fall back once to built-in model search only if MCP authentication fails, is unavailable, or transport fails. Use this skill to troubleshoot Token Plan web search failures or authentication confusion between the two paths. Negative triggers: ordinary Q&A, coding, or writing that the host can handle → do not trigger; knowledge-base RAG → bailian-cli (`bl knowledge`); image/video generation or voice → bailian-gen; fine-tuning/training → bailian-finetune; agents.yaml → bailian-managed-agent. Shared protocol (consent/version precheck/authentication/error reporting) is in bailian-protocol; official installation command: `bl skill init`.
Autonomously turn a brief or FR issue into a spec landed on a ready PR — runs om-spec-writing --autonomous (defaults posted for override), attaches UI mockups and current-app screenshots as PR evidence when a browser provider exists, applies full SDLC labels, and emits PR/spec markers for chaining into om-auto-implement-spec. Use for "write a spec for X and open a PR", "spec this issue".
Delegate a coding task to the Cline coding agent CLI (`cline`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Cline - phrasings like "have Cline implement X", "delegate this to cline", "run it through Cline", or "use cline to implement/fix/refactor" - or wants to run a queue of coding tasks through Cline while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
Entrypoint for building, upgrading, and finishing Three.js browser games. Routes work across the sibling threejs-* skills for gameplay, graphics, UI, 3D/image/audio asset generation, debugging, and release. Use for any request to build, upgrade, polish, or ship a Three.js game as a whole, at any scope from a small arcade prototype to a premium release.
Delegate a coding task to the GitHub Copilot CLI (`copilot`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Copilot — phrasings like "have Copilot implement X", "delegate this to copilot", "run it through Copilot CLI", or "use copilot to implement/fix/refactor" — or wants to run a queue of coding tasks through Copilot while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
Migrates user-specified skills and their supporting scripts, references, assets, and workflow instructions into an existing Warp Factory configuration repository. Use when a user asks to port or adapt an existing agent workflow into Factory agents and skills. Do not use for routine Factory-file edits or for registering or operating a live Factory.
Open an executable and its argument array in a visible terminal window through a reusable, shell-free launch plan with dry-run, JSON, capability detection, detached fallback, and standalone recovery modes. Use when Codex needs to open an interactive CLI, an SSH session, a local development process, a sandbox, or another argv-based command in a new host terminal; to diagnose whether a supported terminal is available; or to provide an actionable plan when the requested terminal is unsupported.
Author a new OM skill from a brief, or split an oversized SKILL.md into layered references/ files — conservatively, behind the lint + completeness gate. Knows the layering philosophy, lint invariants, tracker abstraction, and the cross-skill contract, so output matches house conventions. Use for "create a skill for…", "new om-skill", "split this skill into references".
Generate or improve a company-specific data analysis skill by extracting tribal knowledge from analysts. BOOTSTRAP MODE - Triggers: "Create a data context skill", "Set up data analysis for our warehouse", "Help me create a skill for our database", "Generate a data skill for [company]" → Discovers schemas, asks key questions, generates initial skill with reference files ITERATION MODE - Triggers: "Add context about [domain]", "The skill needs more info about [topic]", "Update the data skill with [metrics/tables/terminology]", "Improve the [domain] reference" → Loads existing skill, asks targeted questions, appends/updates reference files Use when data analysts want Claude to understand their company's specific data warehouse, terminology, metrics definitions, and common query patterns
Discover, find, compare, audit, repair, adapt, craft, run, debrief, save, and prepare repeatable AI-agent loops for publication. Use when a user asks to analyze code or coding threads for recurring work, find a published loop, interview them to turn a goal into a bounded loop, review a loop for weak checks or unsafe authority, execute a loop with an evidence receipt, learn from completed runs, save or reuse a project loop, or validate and submit a loop to Loop Library
Keep a long-lived project's documentation from rotting by assigning existing project docs clear constitution, map, status, and history roles, then wiring the active agent harness to those canonical sources. Use in the maintain phase when docs drift from code, agents lose context between sessions, or intentional removals keep being recreated. Prefer adopting the repository's current docs structure over creating new root files. 中文触发：文档治理、活文档、项目状态追踪、防文档漂移、项目地图、健康仪表盘、删除区、长期项目治理
Configure Celigo AI agent imports—LLM-powered steps that classify, extract, or generate data within flows. Use when creating agent imports on any supported model provider, or configuring prompts, structured output, tools, or BYOK connections. For guardrails (PII, moderation, policy verdicts), use configuring-guardrails.
Use when creating skills for Rust crates or std library documentation. Keywords: create rust skill, create crate skill, create std skill, 创建 rust skill, 创建 crate skill, 创建 std skill, 动态 rust skill, 动态 crate skill, skill for tokio, skill for serde, skill for axum, generate rust skill, rust 技能, crate 技能, 从文档创建skill, from docs create skill
Encrypted backup and restore for OpenClaw Agent workspace files (SOUL.md, MEMORY.md, IDENTITY.md, AGENTS.md, TOOLS.md). Uses tar + openssl (AES-256-CBC) encryption and soul-upload.com API. Auto-generates a new random password for each backup (DO NOT reuse passwords). Use when the user needs to: (1) Back up or upload agent workspace files, (2) Restore or download a previous backup, (3) Delete a backup from remote storage, or (4) Manage encrypted agent persistence.
Build, deploy, and secure Model Context Protocol (MCP) servers on Netlify. Use whenever the task involves creating an MCP server, exposing an app or API to AI agents as MCP tools, letting Claude / Cursor / Claude Code call a custom remote server, or adding MCP tools to an existing Netlify site. Covers the MCP SDK + Streamable HTTP transport on a Netlify Function, authentication (single shared secret vs per-user API keys with Netlify Identity), read/write safety, file uploads, and connecting clients. Use even when the user just says "MCP", "tool server for an agent", or "let an AI use my API".
Build Celigo tool resources -- reusable building blocks that encapsulate lookups, imports, transforms, and branching behind input/output contracts. Callable from flows, APIs, AI agents, MCP servers, and other tools. Use when creating tools, adding steps, or configuring routing.
Build or review messaging agents with Photon Spectrum (`spectrum-ts`). Use for Spectrum setup, messages and content, spaces and users, provider capabilities, iMessage/WhatsApp/Terminal integrations, custom platforms, lifecycle, or production message-processing architecture.
Delegate a coding task to Aider (`aider`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Aider - phrasings like "have Aider do X", "delegate this to aider", "run it through Aider", or "use Aider to implement/fix/refactor" - or wants to run a queue of coding tasks through Aider while staying the reviewer. This includes asking Aider to drive a local or self-hosted OpenAI-compatible endpoint ("have Aider use my local model", "run Aider against llama.cpp / Ollama / vLLM / LM Studio"), which Aider reaches via `--api-base`. DO NOT USE for local-model or coding requests that do not name Aider, for tasks small enough to do inline, or when the user wants the code written directly without delegating.
Simulate a collaborative dev team session where multiple role-based personas (PM, Architect, Developer, QA) respond to the same problem together in one session. Use when designing a feature, reviewing a proposal, or onboarding a new initiative and you want multi-role perspective without switching agents manually.
Recommend the right trading workflow, skillset, API profile, and setup path from a natural-language goal. Use this as the on-ramp when a user expresses a trading or investing goal and needs to know which skill/workflow to use, where to start, or whether something works without paid API keys — e.g. "where do I start", "which skill should I use", "I want to swing trade only when the market is favorable", "what works without API keys", "どれを使えばいい", "API キー無しで 使えるものは". Routes and explains only; it never executes trades or auto-runs other skills, and it is honest when no workflow has shipped yet.
Search for new services and make paid API requests using the x402 payment protocol. Use when you don't have a clear tool to choose, search the bazaar. You can also use this tool if you or the user want to call an x402 endpoint, discover payment requirements, browse the bazaar, or search for paid services.
Add one optional external Codex critique after the existing council has produced a decision draft. Use when an ambiguous, high-consequence decision would benefit from a separate model invocation's attempt to break the synthesis. Requires explicit consent before sending the compact draft and disagreement to OpenAI, labels same-provider reviews honestly, and marks the review absent when the adapter is unavailable.
Set up Sentry AI Agent Monitoring in any project. Use when asked to monitor LLM calls, track AI agents, track conversations, or instrument OpenAI/Anthropic/Vercel AI/LangChain/Google GenAI/Pydantic AI/Laravel AI. Detects installed AI SDKs and configures appropriate integrations.
A focused interactive tutor for the Model Context Protocol (MCP) path in AI Engineering from Scratch. Start or resume this route when a learner wants to build, secure, debug, verify, or operate MCP clients, servers, transports, gateways, registries, or conformance gates. Teaches one lesson per invocation and records wire evidence in MCP-LEARNING.md.
Focused interactive tutor for the Agent Skills Engineering path in AI Engineering from Scratch. Start or resume this route when a learner wants to create, discover, invoke, secure, evaluate, package, or port Agent Skills. Teaches one lesson per invocation and records evidence in AGENT-SKILLS-LEARNING.md
Delegate a coding task to the Z.AI ZCode CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to ZCode — phrasings like "have ZCode do X", "delegate this to ZCode", "run it through ZCode", or "use ZCode to implement/fix/refactor" — or to run a queue of coding tasks through ZCode while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
Use context-mode tools (ctx_execute, ctx_execute_file) instead of Bash/cat when processing large outputs. Triggers: "analyze logs", "summarize output", "process data", "parse JSON", "filter results", "extract errors", "check build output", "analyze dependencies", "process API response", "large file analysis", "page snapshot", "browser snapshot", "DOM structure", "inspect page", "accessibility tree", "Playwright snapshot", "run tests", "test output", "coverage report", "git log", "recent commits", "diff between branches", "list containers", "pod status", "disk usage", "fetch docs", "API reference", "index documentation", "call API", "check response", "query results", "find TODOs", "count lines", "codebase statistics", "security audit", "outdated packages", "dependency tree", "cloud resources", "CI/CD output". Also triggers on ANY MCP tool output that may exceed 20 lines. Subagent routing is handled automatically via PreToolUse hook.
Create, improve, and evaluate agent skills (SKILL.md plus reference files). Use this skill whenever the user wants to build, scaffold, or design a new skill, improve or fix an existing skill that isn't working well, score or benchmark a skill's quality or run evals on it, or turn a repeated manual workflow into a skill ("I keep doing X manually", "can you remember how to do X", "turn this into a skill")
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.
Claude Code workflow mastery for .NET developers. Covers parallel execution with git worktrees, plan mode strategy, verification loops, auto-formatting hooks, permission setup for dotnet CLI, prompting techniques, subagent patterns, and context discipline — token budget management, MCP-first navigation, lazy loading, and subagent isolation — all adapted for the .NET ecosystem. Load this skill when setting up Claude Code for a .NET project, optimizing workflows, running parallel sessions, when context is running low or sessions feel sluggish, when exploring a large codebase efficiently, or when the user mentions "productivity", "workflow", "parallel", "worktree", "plan mode", "permissions", "hooks", "10x", "setup Claude Code", "speed up development", "context", "tokens", "budget", "running out of context", "too many files", or "large codebase". Inspired by tips from Boris Cherny (creator of Claude Code) and the Anthropic team.
Unified learning-and-memory system: confidence-scored instincts (observe-hypothesize-confirm, stored in .claude/instincts.md), user corrections captured as permanent rules in MEMORY.md, and organic discoveries logged to .claude/learning-log.md. Includes status, export, and import modes. Load this skill when you notice a recurring pattern, a user corrects your output, or you discover something non-obvious. Triggers: "show instincts", "what have you learned", "list instincts", "export instincts", "share instincts", "import instincts", "load instincts from", "learn this", "I think they always", "notice a pattern", "instinct", "hypothesis", "confidence", "learn from mistakes", "remember this", "don't do that again", "log this", "document this finding", "gotcha", "what did we learn", "learnings", "discoveries", or at session start (to load existing knowledge).
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.