Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. Use when the user asks "what can TAO Skill Bank do", "list TAO models", "which TAO workflows are available", or "what supports AutoML".
Recommend the best Qwen model and parameters. TRIGGER when: choosing between Qwen models, comparing Qwen model pricing, understanding Qwen model capabilities, asking which models are available on Token Plan, viewing cost history, when an execution skill needs model selection advice, or user explicitly invokes this skill by name (e.g. use qwencloud-model-selector). DO NOT TRIGGER when: non-Qwen model discussions (OpenAI, Gemini, etc.), general AI questions unrelated to Qwen.
Distill a book, long-video transcript, podcast, course, or interview into a coherent set of executable skills. Use when the user asks to "拆书" / "蒸馏一本书" / "把 XX 书做成 skill" / "把这个视频/播客/课程蒸馏成 skill" / "turn a book or video into skills" — i.e. wants the frameworks, principles, and methodologies in long-form content extracted into atomic, reusable Claude skills that an agent can invoke in real-world situations. NOT for simple summarization, book reviews, or role-playing as the author (that is nuwa-skill's job).
Generates custom design system rules for the user's codebase. Use when the user says “create design system rules,” “generate rules for my project,” “set up design rules,” “customize design system guidelines,” or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.
The front door to the Small Business plugin. Listens to what the owner needs right now — vague or specific — and routes them to the best skill or slash command for the moment. Also serves as a guide: explains what's available, suggests what to try next, and adapts recommendations based on stored business context. Trigger whenever the owner asks "what can you do," "help me with my business," "what should I focus on," "I don't know where to start," or any open-ended business request that doesn't clearly match a single skill
Produce a token-bounded, citation-ready context slice from an existing Obsidian vault for a downstream agent or task. Use for "/wiki-context-pack", "use my vault as context", "context slice for X", "pack the wiki for my agent", or "bounded context for Y".
OKX.AI (the Agent economic system) intro & onboarding entry. Use whenever the user asks what OKX.AI is, what it can do, how to use or get started with it, wants an OKX.AI tutorial / quickstart / help, or types the product name in any spelling / spacing / casing / typo variant (OKXAI, okx ai, okx-ai, lowercase okx.ai, mis-typed Chinese like 啥是okxai) — e.g. what is OKX.AI / OKX.AI 是什么 / 怎么用 OKX.AI / OKX.AI 快速开始, and any paraphrase in any language. Detects the runtime platform, introduces the three roles (User / ASP / Evaluator), and routes the user into identity registration. NOT for generic onchain-OS onboarding, nor for direct task operations (publishing / accepting / delivering / disputing a task — a separate task-lifecycle flow).
Installs, diagnoses, repairs, and personalizes the official Tencent IMA skill (a wrapper around upstream ima-skill, not a replacement), including fan-out search across IMA knowledge bases with priority boosting. Use when the user mentions IMA / 腾讯 IMA / ima-skill, needs IMA API key setup, 知识库搜索 / 笔记搜索, imports URLs into a KB to extract content, or hits "Skipped loading skill(s) due to invalid SKILL.md" (ima-skill's missing-YAML-frontmatter bug).
Launch, see and drive a real game so an agent can test its own mods. Covers launching via Steam or the exe, windowed mode at a fixed size, screenshots of the game window (GPU-safe capture), clicking and typing into menus, holding keys, relative mouse, crash-reporter cleanup, killing by PID, reading logs, scripted test scenes, and an in-game JSON bridge that lets an agent observe and act. Windows-first (also from WSL), with notes for Linux and macOS. Use when a mod must be verified in game, when navigating menus automatically, or when building a repeatable test or demo scene
Orchestrate the full paper pipeline end-to-end. Manage state propagation between phases (literature → plan → code → experiments → figures → tables → writing → review), support checkpointing and resumption. Use for assembling a complete paper from components
All-in-one project configuration and health management. Sets up new projects (settings.local.json, CLAUDE.md, .gitignore), audits existing projects (permissions, context quality, MCP coverage, leaked secrets, stale docs), tidies accumulated cruft, captures session learnings, and adds permission presets. Uses sub-agents for heavy analysis to keep main context clean. Trigger with 'project health', 'check project', 'setup project', 'kickoff', 'bootstrap', 'tidy permissions', 'clean settings', 'capture learnings', 'audit context', 'add python permissions', or 'init project'.
Control the user's real Safari browser on macOS through AppleScript, page JavaScript, screenshots, and carefully verified System Events input. Use when an agent needs to inspect or operate the user's existing Safari tabs and login sessions, including reading pages, navigating, clicking, filling non-sensitive forms, taking screenshots, observing page-level fetch/XHR metadata, or troubleshooting Safari-specific UI behavior.
Stream overview, CLI, and router for Chat, Video, Feeds, Moderation, and Agents. Use for any Stream task: building or integrating Stream into web, iOS, Android, React Native, Flutter, Unity, or Unreal apps, building voice or text AI agents with Stream Agents, querying Stream data, running getstream CLI commands, looking up Stream SDK docs, or migrating (from Sendbird, or Feeds v2 to v3). Routes to the right skill
Delegate broad computer-use tasks to ARK CUA for Volcengine AgentPlan users through an authenticated cloud desktop, and synchronize explicit credentials to a caller-owned CUA through Credential Agent. Use for web or desktop-app operation, file workflows, reusable task contexts, artifacts, temporary CUA App URLs, desktop shutdown/start/recovery, inspection, or exact browser, environment, secret, Credential Set, and managed-file credential setup/sync/status/reset. Do not use when local reasoning or a purpose-built local/API tool can complete the request more directly.
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.
Use when maintaining a durable Markdown knowledge store that agents compile from sources, when every number or quote in a wiki page must trace back to an immutable source, or when compiled pages need cheap drift detection against the code they describe. Teaches the raw/wiki/archive layout, per-claim provenance links, and git fingerprints for zero-token staleness checks.
Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing Python custom assertions, implementing llm-rubric for LLM-as-judge, or managing few-shot examples in prompts. Triggers on keywords like "promptfoo", "eval", "LLM evaluation", "prompt testing", or "model comparison".
Initializes the Claude Code .claude/ structure (CLAUDE.md, Agents, Rules, Skills, hooks) in any target repository. Use for requests such as "set up Claude," "create .claude," "initialize CLAUDE.md," "organize Agents," or "set up claude-code." Use update-claude to enrich an existing .claude/ with differences. Also includes preparing prerequisites for implement-issue-tree (gh auth / sub_issues / workflow js).
Use when a project keeps its state in Superself (a `<!-- superself:begin` block in AGENTS.md or CLAUDE.md, or `self setup` resolves the directory to a registered project): read `self context` at session start, attach work to a work unit, report with evidence, and record confirmed decisions so the next session picks up where this one left off.
ListenHub CLI skills router. Routes to the correct skill based on user intent. Triggers on: "make a podcast", "explainer video", "read aloud", "TTS", "generate image", "generate video", "做播客", "解说视频", "朗读", "生成图片", "生成视频", "幻灯片", "slides", "音乐", "music", "generate music", "翻唱", "混音", "remix", "续写", "extend", "纯音乐", "instrumental", "配乐", "soundtrack", "分轨", "stem", "识别歌词", "克隆人声", "vocal clone", "cover song", "pixverse", "口型", "lipsync", "对口型", "parse URL", "解析链接", "提取内容".
Routes reverse engineering, exploitation, penetration testing, malware, mobile, firmware, browser automation, documentation, and security tasks to the appropriate specialist skill. Use when a task spans modules or the correct reverse-skill entrypoint is unclear.
Setup and diagnostics for the AWS DevOps Agent MCP connection. Triggers when aws-devops-agent is missing from .mcp.json, when the connection is broken, or when the user says “set up devops agent” / “configure agent”. Does NOT trigger if the MCP is already connected and working.
Diagnose why an agent harness misbehaved by reading the local flight-recorder ledger (.vigiles/runs.jsonl) — which skills fired or got hijacked, which hooks blocked or wrongly allowed, which subagent tool-contract violations happened, and how a skill's trigger rate moved. Use when asked why a skill stopped firing, why a hook didn't block, why the wrong skill ran, or to debug/investigate what the harness actually did. NOT for writing new rules (use strengthen) or editing the spec (use edit-spec).
Search and contribute to the shared AI-modding knowledge base, where field notes record how specific games were modded, decompiled or reverse-engineered (exact versions, route, engine facts, verification, gotchas). Use before starting work on a game ("has anyone modded X?"), when stuck on an engine quirk, and at the end of any modding or reverse-engineering session to write up what was learned and, with the human's OK, open a pull request so the next agent benefits
Generate a personalized SOUL.md through a warm, adaptive onboarding conversation. Trigger when the user wants to create, set up, or initialize their AI partner's identity — e.g., "create my SOUL.md", "bootstrap my agent", "set up my AI partner", "define who you are", "let's do onboarding", "personalize this AI", "make you mine", or when a SOUL.md is missing. Also trigger for updates: "update my SOUL.md", "change my AI's personality", "tweak the soul"
Interactively guides the design and implementation of custom deterministic orchestrator harnesses. Use when a user wants to build their own pipeline to wrap and run Mantis skills reliably. Don't use for executing the default pipeline directly.
Extracts learnings from execution trajectories at the end of a Mantis loop. Use to parse agent conversations, extract successes, failures, and false assumptions, and append them to workspace/learnings.jsonl. Don't use for analyzing source code or writing patches.
Adversarial code review using a cross-model approach. Spawns reviewers on the opposing model (Claude uses Codex, Codex uses Claude) to challenge work from distinct critical lenses. Produces a synthesized verdict with findings and lead judgment. Triggers: “adversarial review”.
Open the context-mode Insight dashboard in your default browser. Insight is the hosted analytics layer for AI-assisted engineering teams — per-engineer productive rate, retry waste, blocker detection, role-narrowed views. Trigger: /context-mode:ctx-insight
Entrypoint for all Fusion skill lifecycle operations. USE FOR: finding, installing, updating, syncing, or greenkeeping skills; setting up skill automation; creating or authoring a new skill; reporting a bug with a skill. DO NOT USE FOR: resolving GitHub issues, reviewing PRs, planning task breakdowns, or authoring GitHub issues — those are handled by other Fusion skills
Answer questions about the Paseo product and app, including setup, configuration, connectivity, providers, workspaces, updates, logs, and troubleshooting. Use when a user inside Paseo asks how Paseo works, how to configure it, or why something is broken; use the paseo skill instead to operate agents and workspaces through MCP or the CLI.
Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use this skill when: - Evaluating an agent system's security posture before production deployment - Running a compliance check against OWASP ASI 2026 standards - Mapping existing security controls to the 10 agentic risks - Generating a compliance report for security review or audit - Comparing agent framework security features against the standard - Any request like "is my agent OWASP compliant?", "check ASI compliance", or "agentic security audit"
Integration patterns for Mapbox MCP DevKit Server in AI coding assistants. Covers setup, style management, token management, validation workflows, and documentation access through MCP. Use when building Mapbox applications with AI coding assistance
Diagnoses the existing .claude/ setup (CLAUDE.md, Agents, Rules, Skills, hooks), presents the gaps against the ideal setup, and enhances it after user approval. Use for requests such as "improve .claude", "improve CLAUDE.md", "organize Agents", "update the claude setup", or "add Rules". Use init-claude for new setups. Features include filling gaps with npx skills add, checking prerequisites for implement-issue-tree, and updating by diff without destroying existing assets
Use when building features with **Codex** (OpenAI Codex CLI) in any codebase and the work should go through a disciplined build → review → test → fix loop. Triggers on "run the build loop", "build the next task", "continue the plan", "build this feature properly", or any request to implement work from a plan file or a direct feature prompt. Builds from the plan (or the prompt if no plan exists), runs Codex's `/review` on uncommitted changes and fixes every issue found, tests and verifies the feature end to end, fixes anything testing surfaces, and reports back once complete. Repeats until all plan tasks are checked off.
Convert a supplied HTML page or generated HTML reference into a screenshot-backed article containing multiple reusable interaction prompts. Use when the user provides an HTML file, exported page, generated-page.html, or local/live reference and asks to extract animation/interactions, create prompts, capture screenshots for each prompt, add them to an article, or commit the resulting article/assets.
Drives a running Unity Editor or dev Player through the unity-pipeline package — recompile, run tests, run C# scripts, method-reload code at runtime and audit the project. Use when an agent must control a live Unity instance or automate its tests.
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.