Skills
99,448 packaged capabilities and playbooks for agents. Install any of them with one command.
All
A one-shot skill that generates a fun short video about "my claw's first reaction after getting a FluxA card". Uses Kling video generation via FluxA Agent Wallet x402 payment — no Kling API key required. The agent guides the user to choose a scenario, generates a 4-act storyboard prompt, pays for Kling via x402, and saves the video locally.
Use when debugging TypeScript/JavaScript bugs by tracing call chains, understanding unfamiliar codebases quickly, making architectural decisions, or reviewing code quality. Extract function signatures and JSDoc without full file reads, trace call hierarchies up/down, detect code smells, and follow data flow. Triggers on debugging, understanding codebase, architectural analysis, signature extraction, call tracing.
Set type like it was chosen, not defaulted. Typeface selection, size scales for product versus reading UI, line height and tracking by size, measure, hierarchy through weight and colour rather than size, tabular numerals, OpenType features, text wrapping, truncation, mono for data, font loading. Use when choosing fonts, building a type scale, fixing hierarchy, or when an interface looks "generic", "off" or "like a template" and the cause is text.
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.
TypeScript best practices for FiveM resources and their NUI. Use when reading or editing any .ts or .tsx file or a .svelte file with <script lang="ts">, or when the user asks how to type net events, callbacks, exports, NUI messages or state bags.
Use when reproducing defects as failing tests, testing template or rendered output changes, confirming changes on a running TYPO3 instance, or setting up TYPO3 extension tests: unit/functional/E2E, PHPUnit 11-13, mutation testing, final-class mocks (v14), CI matrix across TYPO3 12/13/14.3 LTS, typo3-ci-workflows meta-package, CI failures. Also: transaction rollback, worker crashes, competing requests, testing-framework setup, test matrix, integration/e2e testing, coverage, test generation.
Guide tasteful UI animation with easing, springs, layout animations, gestures, and accessibility. Covers Tailwind and Motion patterns. Use when: (1) Implementing enter/exit animations, (2) Choosing easing curves, (3) Configuring springs, (4) Layout animations and shared elements, (5) Drag/swipe gestures, (6) Micro-interactions, (7) Ensuring prefers-reduced-motion accessibility. Triggers: animate, animation, easing, spring, transition, motion, layout, gesture, drag, swipe, reduced motion, framer motion.
Generation of production-ready C# Unity code from functional specifications. Analyzes the existing codebase, chooses the right architectural pattern, generates code and tests. Triggers: /unity-code-gen, 'generer script Unity', 'creer composant', 'nouveau MonoBehaviour', 'creer ScriptableObject', 'generer code Unity', 'nouveau systeme Unity', 'ajouter feature Unity'. Use when the user asks to create a new script, component, system or feature in Unity. Produces C# files that follow the project's conventions, with associated NUnit tests.
Incremental and safe refactoring of Unity C# code. Detects code smells, proposes a plan prioritized by risk, and executes changes one by one with compilation verification. Triggers: /unity-refactor, 'refactor', 'code smell', 'clean code', 'dette technique', 'refactoring unity'. Produces restructured code without changing behavior.
Monitor and control an Unraid server via the Unraid Management Agent's MCP server (126 tools, 5 resources, 6 diagnostic prompts) and REST API. Use when: connecting an AI client (Claude, ChatGPT, Cursor, Copilot, Gemini CLI) to Unraid; checking system, array, disk, Docker, VM, GPU, UPS, ZFS, or network status; starting/stopping containers, VMs, the array, or parity checks; diagnosing disk health, performance, or array state; managing alerts, health checks, fan/CPU/tuning, or updates; or choosing between MCP, REST, and WebSocket. Corrects: inventing Unraid tool names or REST paths; running destructive actions (stop array, reboot, delete snapshot) without confirm=true; polling REST in a loop instead of using WebSocket/MCP; dumping full lists instead of search_/get_ tools; and assuming auth the agent lacks by default
Use when the user is hitting Claude usage limits, burning through tokens fast, running a long conversation, or asks how to use Claude Code more efficiently. Triggers on phrases like "hit my limit", "running out of tokens", "usage limit", "save tokens", "reduce usage", "am I wasting tokens", "this chat is getting long", "which model should I use". Diagnoses the current session, runs a real token-usage report from local JSONL logs, and applies Dubi's 11 rules for reducing Claude usage.
Use when finishing a ticket, feature branch, or pull request and the user asks to validate, demo, verify, sign off, show that it works, run UAT, provide acceptance evidence, or decide whether work is ready to merge. This skill gathers tangible evidence that completed work functions as intended, with videos, screenshots, terminal recordings, JSON responses, output files, logs, and a concise human test guide. Use for web apps, CLI and TUI apps, APIs and SDKs, and native apps including Electron-type apps. Trigger on phrases like "UAT", "verify", "show me it works", "demo this", "walk me through", "ready to merge", "can we merge?", "acceptance test", "validate the changes", "sign off", or any request for proof that a feature branch or PR works.
Synthesises user interview transcripts into structured research findings. Use when asked to analyse interview notes, synthesise qualitative research, identify themes from interviews, or turn raw interview data into actionable product insights. Produces a themed synthesis with supporting quotes per theme, 'so what' implications, and recommended next steps. For mixed sources beyond interviews (surveys, tickets, feedback) use user-research-synthesis instead.
Russian-language UX copy: buttons, forms, errors, empty states, onboarding, confirmations, notifications, pushes, and microcopy. Use this skill whenever the user asks to write, rewrite, review, choose, or improve interface copy, product messages, UI strings, transactional emails, push notifications, toasts, snackbars, forms, empty states, onboarding, errors, confirmations, labels, tooltips, or button text. Triggers: «текст для кнопки», «сообщение об ошибке», «текст в форму», «пустое состояние», «подпись к полю», «текст тоста», «снекбар», «онбординг», «пуш-уведомление», «микрокопия», «UX-текст», «что написать на экране…», «лейбл поля», «тултип», «подтверждение удаления», «письмо-уведомление». For articles and posts, see the statya and redaktura skills; for a project glossary — redpolitika.
Map user journeys, screen flows, and interaction sequences for web applications. Use this skill when the user wants to plan how users move through screens, define multi-step workflows, map user journeys, design navigation structures, or think through interaction flows. This includes onboarding flows, checkout processes, CRUD workflows, settings management, error recovery paths, or any multi-screen user experience. Also trigger when the user mentions 'user flow', 'screen flow', 'journey map', 'interaction design', or 'workflow'
Generate comprehensive knowledge graph reports for Obsidian vaults. Combines multiple graph queries (vault-stats, hubs, bridges, orphans-rich) to produce a structured 4-module analysis report with data summary tables. Requires obsidian-graph-query skill installed. Use for: vault report, knowledge report, vault analysis, vault health, knowledge graph report, 知識圖譜報告, vault 分析.
Velt Comments implementation patterns and best practices for React, Next.js, and web applications. Use when adding collaborative commenting features, comment modes (Freestyle, Popover, Stream, Text, Page), rich text editor comments (TipTap, SlateJS, Lexical), Apryse WebViewer (PDF/docx) comments, media player comments, chart comments, comments sidebar setup and customization (embed mode, floating mode, focused thread, V2 sidebar), sidebar filtering with accessModes for privacy, isAnnotationPrivate() visibility routing, CommentDialogActionService.isSubmitInFlight() for duplicate-submit guards, VeltCommentDialogAgentSuggestion primitives for AI suggestion accept/reject UIs, agent comment annotations via REST API (agent block with agentSource/agentId/executionId, agent-specific GET filters, suggestionAccepted/suggestionRejected client events, sourceType "agent" UI rendering), or binding Comment Bubble / Comment Dialog / Comment Tool wireframe slots via template variables (velt-data, velt-if, velt-class).
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Run Chain-of-Verification (CoVe) on a draft or a block of text with factual claims. Spawns the `claim-verifier` agent in a fresh context (never a conversation fork) so it never sees the draft — then reports which claims are supported, contradicted, or unverifiable. Use when user says "verify these citations", "check the claims in X", "did I hallucinate anything", "fact-check this draft", "run CoVe on this", or after any text generation that asserts facts about papers, datasets, or numerical results. NOT for style/grammar review (use `/proofread`) or substance review (use `/review-paper`).
Fact-check LLM-drafted technical content against primary sources — source hierarchy, programmatic existence probes for tool and plugin names, class-before-instance error triage, the truncated-negative trap, adversarial re-checking, and the verified-stamp discipline. Use when auditing a SKILL.md for factual errors, before stamping a skill verified, when a command or artifact claim needs confirming against upstream documentation, or when reviewing any drafted content whose specifics were written from model memory.
Transform an AI agent into a disciplined software development partner with strong judgment, transparent decisions, proportionate verification, and craftsmanship. Use for software implementation, feature work, bug fixing, refactoring, optimization, migrations, and sustained collaboration inside a codebase. Do not use merely because a task involves an AI agent; use a dedicated agent-design skill when the primary problem is agent architecture.
AI video maker that generates and edits videos entirely through conversation. Describe a video concept and the AI creates it from scratch — or upload existing footage and edit by chatting. Handles the complete video production workflow: generate scenes from text prompts, arrange clips on a timeline, add background music and sound effects, insert titles and lower thirds, apply color grading, overlay subtitles, and export as MP4. Built for content creators, marketers, and anyone who needs video content without learning editing software. Create product demos, social media clips, educational content, promotional videos, and personal projects through natural language. The AI video maker understands context — say "make it shorter" or "add energy" and it knows what to change. Supports mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav.
AI agent visual feedback loop for any web app. Use when iterating on visual code (UI, canvas, 3D, SVG, charts, animations) and you need to SEE the rendered result to evaluate quality. Covers: dev-screenshot API pattern (GET trigger → SSE → client capture → POST back → file saved), parameterized rendering, metadata sidecars, visual regression with pixel diff, WebMCP tool registration, and console fallbacks. Activate on: 'take a screenshot', 'show me the render', 'visual QA', 'compare before/after', 'pixel diff', or any iterative visual work where the agent needs to inspect rendered output.
Configure and optimize Vite 7 for React projects. Covers build tooling, dev server, plugins, HMR, chunk splitting, Environment API, and Rolldown integration. Use when setting up Vite, configuring builds, optimizing bundles, managing plugins, or troubleshooting dev server. Triggers on vite, vite config, vite plugin, HMR, dev server, build optimization, chunk splitting, rolldown, vite proxy, environment api, rolldown-vite.
Use when writing, reviewing, or refactoring vitest tests. Load when you see *.test.ts or *.spec.ts files, nested describe blocks, loose assertions (toBeTruthy), over-mocking, slow tests, or async testing needs. Covers AAA pattern, parameterized tests, test doubles hierarchy, mock cleanup, test isolation, and performance optimization. Keywords include vitest, testing, TDD, assertions, mocks, stubs, fakes, spies, beforeEach, describe, it, expect, vi.mock, it.each.
Voice calibration before writing — before rewriting, first figure out which real me is hidden in this text. By default it outputs a voice anchor card (can be passed directly to humanize-ai / editor-revisor as a protected zone); deep mode outputs a full voice map plus follow-up questions. It does not rewrite. Triggers: dissolve the AI taste, find my real voice, what did I actually want to say here, get the real me back in the text, AI smoothed away my edge, doesn't sound like me. Not for: direct rewriting (→ humanize-ai / editor-revisor), content checkup (→ chinese-write-checker), title/layout/punctuation polishing (→ packaging-workshop).
Volcengine compliance best-practices assistant: (1) based on the user's needs (compliance standards to meet, keywords, risk levels of concern), recommend which built-in Volcengine conformance pack templates to enable and flag which are already enabled; (2) summarize the account's current compliance posture, aggregating the evaluation results of active rules/conformance packs (built-in + user-defined) by category (regulatory / best practice / custom) and severity into a compliance overview report; (3) when the official baseline does not cover a case, guide the user in writing a Rego policy as a custom compliance rule and registering the evaluation. Can deploy recommended templates as conformance packs after user confirmation. Use when the user wants to do "compliance check / compliance inspection / security compliance / compliance best practices / which compliance rules to enable / MLPS compliance / is my Volcengine account compliant / what is non-compliant / help me write a custom compliance rule", or mentions Volcengine "Config / conformance pack / Rego policy". Trigger on the keywords 火山 / 火山引擎 / volcengine combined with compliance scenarios. Deploying conformance packs / registering custom rules are write operations and require user confirmation; compliance reports and resource remediation are strictly separated.
Vue bindings for TanStack Router: RouterProvider, useRouter, useRouterState, useMatch, useMatches, useLocation, useSearch, useParams, useNavigate, useLoaderData, useLoaderDeps, useRouteContext, useBlocker, useCanGoBack, Link, Navigate, Outlet, CatchBoundary, ErrorComponent, Html, Body. Vue-specific patterns with Ref<T> returns, defineComponent, h() render functions, provide/inject, and computed refs.
Remote wake-up computers on a local network via Wake-on-LAN (Magic Packet). Manage host configurations (add, edit, remove, list) and send wake-up signals by host name or MAC address. Triggered whenever the user mentions "开机", "远程开机", "唤醒主机", "wake on lan", "WOL", "远程唤醒", "帮我把XX电脑打开", "服务器关了帮我开一下", "把电脑开着", or asks to start a computer on the local network. Also use for managing wake-up host lists.
Strip multi-vendor AI provenance marks from text and files using the guillaumemeyer/watermarks-remover Python toolkit: invisible Unicode/space homoglyphs (Layer A, deterministic), statistical token-sampling watermarks via agent-guided rewrite (Layer B, best-effort), and C2PA/EXIF/XMP/doc-props metadata on PNG, JPEG, SVG, PDF, DOCX, ODT, HTML, and Markdown. Covers Claude, Gemini/SynthID-Text, OpenAI provenance surfaces, and open-LLM Kirchenbauer-style marks, plus optional external backends for SynthID pixel scoring and CtrlRegen pixel-domain removal. Use when the user wants to strip AI watermarks, remove C2PA / Content Credentials, clean AI metadata from a file, remove invisible Unicode / zero-width characters from AI-generated text, or audit a directory/website for AI provenance signals. Triggers on: "remove watermark", "strip C2PA", "remove AI metadata", "clean invisible unicode", "remove-ai-marks", "SynthID removal", "audit_dir.py", "Layer A / Layer B watermark removal".
Use when iterating on a skill's prompt with the waxa CLI (https://github.com/mizchi/skills/tree/main/tools/waxa) — authoring scenarios, choosing graders, interpreting unclear-points, advancing a ledger, and judging convergence. Encodes the four-stage iteration pattern observed in real iter loops (structural fix → grader breadth → surface-form coverage → residual unclear) and the scenario-design pitfalls (blank-slate executor's network limit, prompt expectation explicitness, regex coverage of Japanese/English surface forms). Meta-skill: do NOT auto-invoke for routine skill edits; fires only when the user explicitly runs waxa or asks for a skill-quality eval.
End-to-end writing assistant for WeChat Official Account articles. Supports trending topic selection, article writing, AI de-flavoring polish (removing the machine feel), image suggestions, and one-click publishing to the Official Account drafts folder. Suited to technical bloggers, self-media creators, and corporate Official Account operations. Use this skill when users need to write Official Account articles, polish content, find images, or publish to WeChat.
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.