Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Vite frontend build tool and dev server. Fast HMR and optimized builds. USE WHEN: user mentions "Vite", "vite config", "vite.config", asks about "Vite setup", "Vite dev server", "Vite build", "fast HMR" DO NOT USE FOR: Webpack projects (use webpack skill), Next.js (uses its own bundler), Create React App (uses Webpack), library builds with Rollup only
Vite build optimization expert with deep knowledge of ESM-first development, HMR optimization, plugin ecosystem, production builds, library mode, and SSR configuration. Use PROACTIVELY for any Vite bundling issues including dev server performance, build optimization, plugin development, and modern ESM patterns. If a specialized expert is a better fit, I will recommend switching and stop.
Review content files against a project's voice and style guidelines. Use when reviewing written content (MDX, markdown, copy) for tone, sentence structure, word choice, and bilingual policy compliance before committing. Triggers on "review voice", "check tone", "voice review", "content review", "does this match our voice", or after writing loop/ritual/article content.
Use when the user wants to transact on any Volcengine commercial product — purchase/provision it, ask what it costs, or unsubscribe from it. Covers three actions: buy (purchase, subscribe, provision, open, place an order; Chinese "开通 / 购买 / 下单 / 买 / 售卖 / 订购"), price (how much does it cost, quote, billing rules, estimated spend; Chinese "多少钱 / 价格 / 报价 / 费用 / 怎么收费 / 如何计费 / 预估费用"), and unsubscribe (cancel a subscription, refund a prepaid instance; Chinese "退订 / 退款 / 取消订阅"). Trigger even when the user does not mention "sale" but expresses a clear purchase, pricing, or cancellation intent toward a Volcengine product. Only handles these three transaction actions; anything outside them is out of scope.
Fetch web page content via Chrome DevTools Protocol (CDP). Full JS rendering, handles redirects (including Google News). Use when you need to read the text content of a web page, scrape articles, or extract information from URLs. Zero dependencies — Python 3 stdlib only. Cross-platform (Mac, Windows, Linux).
Build modern full-stack web applications with Next.js (App Router, Server Components, RSC, PPR, SSR, SSG, ISR), Turborepo (monorepo management, task pipelines, remote caching, parallel execution), and RemixIcon (3100+ SVG icons in outlined/filled styles). Use when creating React applications, implementing server-side rendering, setting up monorepos with multiple packages, optimizing build performance and caching strategies, adding icon libraries, managing shared dependencies, or working with TypeScript full-stack projects.
Use when you are unsure what to do next in the agent-toolkit pipeline. Reads all active change manifests, interprets the current state, and tells you exactly what skill to run next and why. Also handles edge cases like kickbacks in progress, multiple concurrent changes, and epic child ordering. Invoke with phrases like "what now", "what should I do next", "where are we", or "what's the status".
Excavate why a piece of code is the way it is, from the repo's own record. Use when the user questions existing code — "why is this like this?", "why is this hardcoded?", "what's the story behind this?", "왜 이렇게 돼 있어?", "이거 왜 이래?", "이 코드 배경이 뭐야" — or whenever you are about to explain the rationale of code you did not write. Never guess the why; dig it out of blame → commits → PRs → issues and answer with evidence.
Automatically checks word counts of documents when the user mentions word count in relation to a file. Triggers on phrases like "Check the word count of X", "Stop when the word count is N", or similar references to document word counts. Use this skill proactively whenever word count is mentioned with a document reference.
Process Microsoft Word documents (.docx/.doc/.rtf): conversion (PDF/Markdown/HTML/TXT), extraction (text/tables/images), batch replace, merge/split, unified layout/template application, format validation/reporting. Use when the user mentions Word, docx, doc, thesis formatting, format checking, table extraction, or exporting to PDF.
Author and review Cloudflare Workers code against production best practices. Use when writing a Worker, reviewing Worker code, configuring wrangler.jsonc, or checking for Workers anti-patterns — streaming, floating promises, global state, secrets, bindings, observability.
Define your Climax — the specific transformation you promise your audience. This is the second element of the World Code framework. Use when someone says "define my climax", "transformation promise", "what change do I create", "what do I promise", or "climax element".
Define your Method — the unique methodology you use to deliver your transformation. This is the third element of the World Code framework. Use when someone says "define my method", "my methodology", "how I solve problems", "unique approach", or "method element".
Complete reference for WoW Retail Combat, Damage Meter, Threat, Loss of Control, Combat Text, Combat Audio Alert, Secret Values, and Spectator APIs. Covers the 12.0.0 combat log removal (CLEU no longer available to addons), C_DamageMeter built-in damage meter, C_Secrets secret predicates, C_CurveUtil/C_DurationUtil for secret value visualization, C_LossOfControl, C_CombatText, C_CombatAudioAlert, ENCOUNTER_STATE_CHANGED, threat functions, and the new COMBAT_LOG_MESSAGE event. Use when working with combat data, damage meters, threat, loss of control, combat text, encounter events, or any combat-related addon functionality
Complete reference for WoW Retail Chat, Social, Club/Community, Friend List, Voice Chat, BattleNet, Ping, Social Queue, and Addon Messaging APIs. Covers C_ChatInfo, C_Club, C_ClubFinder, C_FriendList, C_BattleNet, C_VoiceChat, C_SocialRestrictions, C_SocialQueue, C_RecentAllies, C_PingManager, C_TTSSettings, ChatFrame functions, chat filters, addon message system, and 12.0.0 instance restrictions (SendAddonMessage blocked, chat messages may be secret). Use when working with chat output, chat channels, communities, friend lists, voice chat, BattleNet friends, addon communication, social features, or ping system
Write or critique prose that ships with a codebase — READMEs, developer guides and runbooks, CLI text, code comments, agent guides, and commit or PR descriptions. Use when drafting, improving, or reviewing these artifacts. Do NOT use for blog posts (use blog-review), design docs, or internal wikis.
This skill should be used when a designer wants to produce a holistic design for a full feature before Traces are cut — for example "design feature #X", "create the Figma flow for this feature", "map the UX for this feature", "design the full user journey for feature #X", "create a feature design handoff", or "add design coverage to feature #X". Covers the full feature journey (all user stories, all screens, cross-screen states) and writes the Design Handoff section back into the Feature issue, fulfilling the Definition of Ready gate. Not applicable to individual Traces — use `wtf.design-trace` for per-trace coverage of the claimed scenarios.
When an application needs to store config, data, cache, or state files. When designing where user-specific files should live. When code writes to ~/.appname or hardcoded home paths. When implementing cross-platform file storage with platformdirs.
A collection of Xianyu automation skills. Supports authentication and login, product listing, product search and discovery, product details, message interactions, favorites/wants, product operations, and competitor analysis. Triggers when the user asks to operate Xianyu, list products, search Xianyu products, analyze competitors, view messages, reply to inquiries, favorite products, or run Xianyu product operations.
Use xlsx binary for Excel file manipulation including viewing, SQL-like filtering, cell editing, conversion to/from CSV, and data analysis operations. Use this instead of Python (openpyxl, pandas, xlrd) or Node.js libraries for ALL .xlsx file operations — reading, writing, filtering, conversion, and analysis. Trigger on any request involving .xlsx or Excel files.
Fetch live financial data from Yahoo Finance. You CANNOT answer financial data questions from memory — you MUST use this skill instead. Trigger whenever the user wants to check any stock/ETF/index/commodity/forex/crypto price or quote; look up PE ratios, margins, earnings, or analyst recommendations; view ETF holdings; find market gainers, losers, or trending stocks; search for a company's ticker symbols; pull historical prices or options chains; or calculate portfolio value using current market prices. Covers all global exchanges (US, Hong Kong, China, etc.) and works in any language. Do NOT use for financial education without data lookup, writing scripts using other libraries (yfinance, pandas), comparing APIs, or parsing data from non-Yahoo sources like Polygon.io.
Create expert-level learning reports and tutorials from any domain, industry, technology, role, market, product idea, or vague field question. Use when the user wants to quickly build domain expertise, understand an industry, generate a structured expert study report, build a keyword library, design Feynman self-tests, or export the result as Markdown, DOCX, PDF, and HTML. Do not use for short factual answers, pure business model diagnosis, standalone beginner tutorials with no domain-structure research, simple file conversion, or unsourced opinion writing.
Transform external reference text provided by the user into their own Xiaohongshu copy. Use when the user explicitly says to use this as a reference, rewrite it in their style, or has entered a reference-draft conversion workflow; analyze and verify the original, then reuse their activated DNA, existing copy frameworks, writing, headline, and review capabilities. Pasting material alone does not trigger rewriting. Does not download videos or create transcripts, spoken scripts, or storyboards.
Generates business-oriented work reports for managers. Triggered when the user says "生成工作报告", "写工作报告", "汇总工作", or "生成工作总结". Not for generating technical changelogs, developer-facing commit summaries, project handover documents, or code review reports.
Zed editor configuration expert. Assists with settings.json, keymap.json, tasks.json, AI/agent panel setup, LLM provider configuration, language server tuning, themes, fonts, appearance, git integration, tool permissions, rules files, and MCP servers. Knows Zed's JSON config format, context system for keybindings, task variables, and agent profiles. Use when configuring Zed, setting up keybindings, adding LLM providers, customizing appearance, configuring language servers, setting up tasks, or troubleshooting Zed settings. Keywords: zed, zed editor, settings.json, keymap.json, tasks.json, keybinding, theme, font, appearance, agent panel, LLM provider, language server, LSP, formatter, linter, git panel, tool permissions, MCP, rules, inline assistant, task runner
Must follow when configuring a type-safe environment variable management module: based on .env.example, use Zod to generate the env schema and standardized management tooling. Trigger words: zod environment variables, type-safe env configuration, environment variable schema.
Use when building business objects with the ABAP RESTful Application Programming Model (RAP): CDS view entity, behavior definition BDEF, behavior implementation ABAP class, managed RAP, unmanaged RAP, validation, determination, action, draft-enabled, service definition, service binding, OData V4, projection view, business object BO, S/4HANA BTP ABAP environment cloud development.
This skill provides screenplay action and description writing techniques. Covers present tense formatting, visual storytelling, action sequences, and paragraph structure for scene descriptions. Use when: writing scene descriptions, crafting action sequences, describing visual storytelling, or formatting action paragraphs in Fountain format.
Guide writing clear, enforceable Architectural Decision Records (ADRs) that work with AI-powered review systems and human teams alike. Use this skill whenever a user wants to create, improve, review, or learn about ADRs — including when they mention "architecture decision", "ADR", "document a decision", "tech decision record", or want to make an existing ADR more specific and enforceable. Also use when reviewing PRs that reference ADR compliance or when someone asks how to write decisions that automated tools can check.
Structures web copy to be cited by AI search engines — ChatGPT, Perplexity, Gemini, Google AI Overviews, Claude — instead of just ranked by traditional search. Use whenever writing or editing website content, blog posts, FAQ pages, product pages, or landing page copy where AI citation, AI visibility, AEO, GEO, answer engine optimization, or being mentioned by name in an AI-generated answer is a goal.
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.
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.