Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Install themed spinner verb packs for Claude Code. Fetches spinner packs directly from the awesome-claude-spinners repository and installs them into the user's settings. Use when the user wants to customize their Claude Code spinner, install spinner verbs, or change spinner themes.
Automatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting them into logical folders. Turns hours of manual bookkeeping into minutes of automated organization.
Use for TikTok Shop market data: trending products, top creators, shop/product sales and revenue, viral videos, livestreams, category rankings, product selection, creator commerce, shop/product sales, viral videos, livestream commerce, and TikTok Shop data. Answers come from KaloData via the bundled `kalo` CLI (Python, zero install). Use whenever the user researches TikTok Shop, even if they never say "kalodata"
Guide users from their own agent code or recorded traces through Kitaru setup, session import or recording, human review, an accepted behavior, a versioned cohort, and evaluator selection, then hand one bounded change to the replay-experiment skill. Use when a user wants to connect or inspect an existing agent, import real traces from files or provider APIs, follow up on a post-import insight, investigate a known bad or surprising session, discover recurring failure modes, learn the evidence-led review flow, resume an investigation, create a cohort from reviewed evidence, or author an evaluator for an accepted behavior. To have models read many sessions and save recurring patterns as insight cards without human review first, use the `kitaru-insights` skill instead. When a first-time user has no agent or evidence and wants a fast demonstration with the PydanticAI returns agent example, use the `kitaru-guided-tour` skill instead.
Ask the Amazon storefront's Alexa shopping assistant questions in natural language to get relevant shopping advice, recommended product groups, ASIN lists, and suggested follow-up questions. Each call supports only 1 prompt. For follow-up questions, the agent must summarize the context and combine it with the new question before making another request. Use url to add Amazon page context. Triggers for scenarios involving Amazon Alexa, the Alexa shopping assistant, Amazon's smart assistant, AI shopping guidance, conversational product discovery, natural-language shopping, Amazon chat Q&A, Amazon Alexa shopping, conversational shopping, AI shopping assistant, follow-up questions, product recommendation conversations, or context-based follow-ups. Also triggers when the user wants to ask for product recommendations in natural language on the Amazon storefront, even without explicitly mentioning “Alexa.”
Query TikTok video rankings, obtaining top video charts by daily, weekly, or monthly ranking as well as by region and video ranking metrics. Returns metrics such as views, likes, comments, shares, favorites, video sales, and GMV, covering 16 TikTok Shop sites. Trigger this skill when the user mentions TikTok video ranking, TikTok top videos chart, TikTok video leaderboard, TikTok daily chart, TikTok weekly chart, TikTok monthly chart, TikTok带货 video ranking, TikTok video sales ranking, TikTok video GMV ranking, EchoTik video ranking, TikTok video ranking, TikTok top videos chart, TikTok video leaderboard, or TikTok viral video ranking. Even if the user does not explicitly mention "EchoTik" or "video ranking", trigger this skill whenever their request involves obtaining TikTok video charts or video rankings by date.
DEPRECATED — superseded by tree-sitting. This skill generated persistent _MAP.md files; tree-sitting does the same AST extraction at runtime (~700ms for 250 files) with no artifact to write, commit, or keep in sync. Use tree-sitting for "map this codebase", "explore repo", "understand structure", or any code navigation task. The final working version is archived at release mapping-codebases-v0.8.0.
Guide the creation of high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when the user wants to build an MCP server to integrate an external API or service, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Generate images and videos through the currently installed Media.io CLI. Use for text-to-image, image-to-image, text-to-video, image-to-video, reference-to-video and published workflows. Select the model from the bundled static catalog (`references/model-catalog.md`), which is generated from the production registry; only fall back to `mediaio model list` on the triggers listed in the discovery guardrail. Copy every `job_type` byte for byte — some contain a literal space, and display names often do not match the identifier. Effects may be used only when their parameters have been independently verified because the current CLI exposes `effect list` but not `effect get`. Always confirm the parameter schema with `model get` before submission. Submitting spends the user's credits, but the CLI stays quiet about the amount unless asked; surface the cost with `--show-credit`, and get an explicit approval first, only when the user is cost-sensitive or has raised credits, price or balance. When the balance runs short, or the user wants their task history or their uploaded files, hand over the product-page link printed by `mediaio link get` — never write or edit a media.io URL yourself. Use the human-readable discovery output, upload local files before generation, submit with `generate create`, wait with the separate `generate wait` command, and retrieve result files with `generate download` instead of reproducing signed result URLs. On hosts that sandbox local command networking, the first networked `mediaio` or `curl` Shell/Bash tool call must request host approval before process launch. Never probe network availability by running it in the default sandbox.
Manage notes and memos in self-hosted Memos service. Use when the user asks to "save this to memos", "create a memo", "search my memos", "find notes about X", "what did I write about", "add a note", "capture this", "remember this", "save this thought", or mentions note-taking, knowledge management, or personal notes.
Plan and execute safe cross-system migrations, including service extraction from monoliths. Use when moving data, schemas, interfaces, infrastructure, or service ownership through compatibility windows, dual-running, reconciliation, cutover, recovery, or deprecation. Do not use for deciding whether decomposition is justified, designing a target architecture, or implementing one named technology; route those to the relevant architecture or specialist skill.
Plan, direct, and produce code-drawn 2D/3D motion graphics and edited videos (reels, hooks, SaaS/product explainers, talking-head edits) on the user's local machine through any coding agent that has terminal + file access (Claude Code, Codex, Cursor, Claude Desktop, VS Code agents, etc.). Workflow: explain the process → user gives references + story → write a paste-ready ElevenLabs voiceover script → user generates and returns the MP3 → build, preview, render. Uses Canvas/SVG/p5.brush/Three.js/GSAP rendered in headless Chrome, Motion Canvas/Revideo, ffmpeg, small local AI models (cutout, transcription), plus LottieFiles, Freesound, Pexels/Pixabay, Firecrawl and ElevenLabs MCPs, and the Playwright MCP to browse any website visually (Pinterest, Behance, Dribbble, brand sites) and grab image/video assets by itself. Use when the user asks to make, edit, animate, caption, voice, or sound-design a video
ModelScope unified operations entrypoint. Covers model/dataset search, download, and upload; repository management; Studio deployment; MCP service search, deployment, and configuration; and Skills Center search, install, and publish. Use this skill whenever the user mentions ModelScope or any platform operation. Use ms-studio-deploy for complex Studio deployment workflows; see this skill's references for the expanded MCP and Skills Center details.
Synchronize footage from a multi-camera / multi-recorder shoot — several cameras plus separate audio recorders covering one session, imported as loose clips — and make a speaker-follow draft by default unless the user explicitly asks for sync only. Use when a user drops in multiple clips from the same recording and wants them aligned, asks for multicam / 多机位 / multi-angle sync, wants a "cut to whoever is talking" edit, or refers to camera A/B, angles, or separate lav or field recordings that need to line up with picture.
Multidisciplinary analytical engine using Charlie Munger's latticework of mental models. Applies cross-disciplinary thinking (math, physics, biology, psychology, economics) to dissect life and business decisions. Use when user presents a decision problem, investment question, or complex analysis request requiring deep rational analysis.
Designing and reviewing the semantic layer of a Materialize SQL code base as a canonical ontology — a shared raw database, a shared core database, and one database per use case. Use this skill when a user asks how to structure or organize Materialize schemas and databases, wants to define canonical semantic objects (entities, events, measurements, relationship objects), needs identity resolution or temporal semantics for public objects, is deciding what belongs in a shared layer versus a consumer-specific one, is building or validating a relationship registry (core.public.relationships, reference edges, cardinality, optionality), or mentions ontology, semantic layer, semantic model, semantic objects, context graph, raw/core/use-case boundaries, grain, or enforceable layer dependencies. Also trigger when reviewing an existing Materialize code base for leaked private schemas, duplicated concepts, or undocumented public objects.
Create, refine, or fix NVIDIA voice agents (Cascaded or Omni) with Pipecat or LiveKit. Use when building, scaffolding, or iterating on a real-time voice-agent pipeline, including speech (ASR/TTS) customization and cloud or local deployment. Not for offline/batch speech-to-text, text-only chat or RAG, or generic Docker or CUDA work unrelated to a voice agent
CLI tool to fetch trending news and hot topics from 66 sources across 44 platforms. Returns structured news items with titles, URLs, and metadata. USE FOR: - Fetching trending/hot news from Chinese and international platforms - Monitoring hot topics across social media, tech, finance, and news sites - Getting structured news data as JSON for further processing - Listing available news sources Requires npm install. Some sources need env vars (PRODUCTHUNT_API_TOKEN). Some sources may be blocked by Cloudflare (linuxdo).
Austrian rail travel planner (ÖBB Scotty). Use when planning train journeys in Austria, checking departures/arrivals at stations, or looking for service disruptions. Covers ÖBB trains, S-Bahn, regional trains, and connections to neighboring countries.
Provides natural, readable, fluent and clear writing guidelines for Chinese or English copy. Use when drafting, rewriting or polishing articles, spoken scripts, speeches, PPT copy, website and product introductions, personal bios, WeChat official account and social posts; also use when the user explicitly specifies oil-tone. Applies to style editing, not to pure research or factual and technical edits that do not involve expression.
Always use this skill when the user wants to explore Openfort documentation, browse SDK source code, or use Openfort MCP tools. This is the general-purpose Openfort platform skill — use it for documentation lookup, source code navigation, and CLI operations. For building with embedded wallets, use the openfort-embedded-wallet skill. For backend wallets, use the openfort-backend-wallets skill. Trigger on: "Openfort docs", "search Openfort", "Openfort source code", "openfort CLI", "MCP tools", "Openfort SDK source", or general Openfort platform questions.
Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", "orca artifacts", "share HTML/Markdown", "public artifact link", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.
Packages and distributes Python libraries using modern pyproject.toml, build backends (setuptools, hatchling), PyPI publishing with trusted publishing, and wheel building. Use when packaging libraries for distribution, publishing to PyPI, or troubleshooting packaging issues.
Extract structured JSON from URLs, files, videos, PDFs with entity extraction and batch support. USE WHEN parse, extract, URL, transcript, entities, JSON, batch, content, YouTube, PDF, article, newsletter, Twitter, browser extension, collision detection, detect content type, extract article, extract newsletter, extract YouTube, extract PDF, parse content.
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.