Skills
98,284 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Convert an article, tutorial, or prompt pack into focused reusable AgentSkills, one independent capability per skill, with portable instructions, example prompts, working demos, preview screenshots, validation, gallery updates, and a narrow commit. Use when the user asks to turn an article's prompts, tutorial sections, design patterns, interactions, or workflow ideas into complete skills rather than leaving them as prose.
Professional music creation with Suno AI V5 and Suno Studio. Use this skill when users want to create songs, playlists, corporate anthems, jingles, workout music, ambient soundscapes, or any AI-generated music. Triggers on requests mentioning Suno, music creation, playlist generation, song composition, or specific music projects like "create a track", "make a playlist", "compose music for", "corporate anthem", "workout mix", or any music production task.
Use when the user's task involves Ant Design (antd) — writing antd components, debugging antd issues, querying antd APIs/props/tokens/demos, migrating between antd versions, or analyzing antd usage in a project. Triggers on antd-related code, imports from 'antd', or explicit antd questions.
Verify reality-grounded claims against external sources in both directions before they ship — could the “absurd” be real, could the “obvious” be false or long-established? Use whenever an artifact, or the sentence you are about to write, asserts something as plausible, realistic, absurd, novel, or impossible from intuition rather than a checked source; before relying on a factual claim in prose, a design rationale, a research claim, or a plan. Fires on metacognitive doubt — when you can't actually know, verify instead of trusting the feeling. Scans read-only, then fixes the clear errors or flags the judgment calls; leaves deliberate fiction alone.
Create award-winning, cinematic frontend interfaces that feel ALIVE. Combines 10+ years of creative frontend experience with technical excellence. Specializes in WebGL, custom shaders, premium animations, and distinctive aesthetics that would win on Awwwards. Use when building landing pages, dashboards, platforms, or any interface where "generic AI slop" is unacceptable.
React Email renderer for json-render that turns JSON specs into HTML or plain-text emails using @react-email/components and @react-email/render. Use when working with @json-render/react-email, building transactional or marketing emails from JSON, creating email catalogs, rendering AI-generated email specs, or when the user mentions react-email, HTML email, or transactional email.
Implements OAuth 2.0/2.1 authorization flows in Fastify applications — configures authorization code with PKCE, client credentials, device flow, refresh token rotation, JWT validation, and token introspection/revocation endpoints. Use when setting up authentication, authorization, login flows, access tokens, API security, or securing Fastify routes with OAuth; also applies when troubleshooting token validation errors, mismatched redirect URIs, CSRF issues, scope problems, or RFC 6749/6750/7636/8252/8628 compliance questions.
Create and manage Shopify products via the Admin GraphQL API or CSV import. Workflow: gather data, choose method, execute, verify. Use whenever the user wants to add products to Shopify, bulk-import a catalog from CSV/spreadsheet/URL, update variants or prices, manage inventory quantities, upload product images, or assign products to collections.
Analyzes the founder's business context to deliver the 3 highest-impact next moves for growth (marketing or sales). Asks up to 10 diagnostic questions when needed to uncover bottlenecks, struggles, and opportunities. Use when user needs strategic guidance, next steps, growth planning, or actionable business strategy.
Download video and audio from YouTube and 1000+ sites using yt-dlp. No API keys needed. Use when: (1) Downloading a video from YouTube or other sites, (2) Extracting audio from a video URL, (3) Downloading subtitles/captions from a video, (4) Getting video metadata without downloading.
Author or revise readable, flat-world Three.js game levels. Use for movement and camera routes, collision and navigation, encounter zones, landmarks, objectives, pickups, motivated lighting, visibility, deterministic level data, or desktop and mobile playthrough verification.
Apply a prompt-agnostic execution and verification loop to any substantial task while preserving the original request. Use when the user asks to fan out work, use subagents or independent reviewers, loop until done, benchmark against references, apply a harsh critic, compare candidates blind, improve an existing prompt with verification, or continue until explicit quality gates pass.
Refresh an existing artifact into the current best v0. Use when the user asks to clean up, sync up, dedupe, de-noise, smooth, rewrite, or update an artifact after iteration; when nearby artifacts may have drifted; or when changes in one place should be reflected across related artifacts while keeping the result minimal.
React Testing Library: user-centric component testing with queries, user-event simulation, async utilities, and accessibility-first API. Use when writing React component tests, selecting elements by role/label/text, simulating user events, or testing async UI behavior. Keywords: React Testing Library, @testing-library/react, user-event, queries, render.
Cross-version symbol migration and binary diff. Use when you have symbols or reverse-engineering results from an older version and need to migrate them quickly to a new version. Use cases: infer kernel symbols from an older version when PDBs are missing, batch-migrate function names after a program update, or quickly locate new offsets after an app update. Core method: use an LLM for structured diffing with programmatic input and output at very low cost (~1 RMB for 200 functions). Triggers: symbol migration, bindiff, cross-version, missing PDB, function offset migration, symbol migration, binary diff, version comparison.
Analyze unit economics for PE targets — ARR cohorts, LTV/CAC, net retention, payback periods, revenue quality, and margin waterfall. Essential for software/SaaS, recurring revenue, and subscription businesses. Use when evaluating revenue quality, building a cohort analysis, or assessing customer economics. Triggers on "unit economics", "cohort analysis", "ARR analysis", "LTV CAC", "net retention", "revenue quality", or "customer economics".
Plan, create, integrate, or audit a hybrid asset pipeline for a Three.js or web game. Use when choosing among imported meshes, procedural 3D geometry, AI-generated reference art, 2D UI media, sprites, VFX, and performance-ready runtime asset delivery.
Create, redesign, validate, preview, package, and prepare cohesive themes for the official Codex desktop app from a visual brief or reference image. Use when a user asks for a new Codex theme, wants to preserve or adapt the native Codex layout, wants artwork on the home or conversation page, reports inconsistent themed surfaces, or needs a portable .codex-theme submission for CodexThemes.
Use when creating, refreshing or repairing `.agents/ue-project-context.md`, the project document every other UE skill reads first. Also use when the user says 'project context', 'set up context', 'UE context', 'scan my project', 'onboard the agent to my project', 'update project context', 'configure project', 'what engine version is this project on', 'which plugins do we have enabled', or complains that UE advice keeps coming out generic. For Build.cs and Target.cs mechanics, see ue-module-build-system; for naming and API-macro conventions, see ue-cpp-foundations; for GAS specifics, see ue-gameplay-abilities.
Use when user asks to setup endorctl, install endorctl, run endorctl scan, scan for vulnerabilities, run endor scan or run Endor Labs scan or when any endorctl command fails with 'command not found', 'no such file or directory', authentication errors, 'unauthorized', '403', 'tenant not found', EOF error, or namespace/access errors.
Put a cursor-tracking mascot on a page—a chibi character that turns its head toward the pointer and reacts when clicked. Pick one of the fifty-two drawn characters and wire up the React component, or draw a new one (with your own image tool, the OpenAI images API, or from a photo of the user), build its two sprite sheets into aligned atlases, and verify they do not jump. Use when the user asks for a mascot, a character that watches the cursor, a portfolio head, wants one of the existing characters on their page, or wants a new character drawn
Draft and review professional emails that match your personal writing style. Analyzes your sent emails for tone, greeting, structure, and sign-off patterns via WorkIQ, then generates context-aware drafts for any recipient. USE FOR: draft email, write email, compose email, reply email, follow-up email, analyze email tone, email style.
Firmware / IoT penetration testing chain. Starting with a .bin / .img file, it completes the full cycle of reverse engineering → extraction → emulation → exploitation. The methodology follows the nine OWASP FSTM stages; the toolchain centers on binwalk v3, unblob, EMBA, Firmadyne, and AFL++. Use cases: router/camera/smart-home firmware audits, firmware update package reverse engineering, IoT CVE reproduction, and embedded 0day discovery. Trigger keywords: firmware, IoT, binwalk, unblob, UART, JTAG, squashfs, UBI, JFFS2, Firmadyne, full-system QEMU emulation, EMBA, firmware penetration testing, router firmware, embedded exploitation, bootloader, NVRAM, FAT, firmware analysis toolkit.
Use when writing or running Unreal Engine tests, adding logging, or profiling a build. Also use when the user mentions 'UE_LOG', 'log category', 'DEFINE_LOG_CATEGORY', 'UE_LOGFMT', 'verbosity', 'check', 'ensure', 'ensureMsgf', 'verify', 'IMPLEMENT_SIMPLE_AUTOMATION_TEST', 'automation test', 'TEST_CLASS', 'CQTest', 'AFunctionalTest', 'latent command', 'Unreal Insights', 'TRACE_CPUPROFILER_EVENT_SCOPE', 'TRACE_BOOKMARK', 'stat unit', 'SCOPE_CYCLE_COUNTER', 'memreport', 'DrawDebugLine', 'UE_VLOG', 'gameplay debugger', 'ShowDebug', 'console command', 'CVar', or 'why is my frame time bad'. For module and target wiring, see ue-module-build-system; for editor tooling, see ue-editor-tools.
Translates Figma motion and animations into production-ready application code. Use when implementing animation/motion from a Figma design — user mentions "implement this motion", "add animation from Figma", "animate this component", provides a Figma URL whose node is animated, or when `get_design_context` returns motion data or instructs you to call `get_motion_context`
Creates, updates, or optimizes an AGENTS.md file for a repository with minimal, high-signal instructions covering non-discoverable coding conventions, tooling quirks, workflow preferences, and project-specific rules that agents cannot infer from reading the codebase. Use when setting up agent instructions or Claude configuration for a new repository, when an existing AGENTS.md is too long, generic, or stale, when agents repeatedly make avoidable mistakes, or when repository workflows have changed and the agent configuration needs pruning. Applies a discoverability filter—omitting anything Claude can learn from README, code, config, or directory structure—and a quality gate to verify each line remains accurate and operationally significant.
Triage new issues in the Sentry `javascript` project by archiving non-actionable noise. Use when asked to "triage issues", "triage the javascript project", "archive non-actionable issues", "triage new frontend issues", or "clean up the sentry/javascript queue". Operates only on the sentry/javascript project, only archives (never resolves), and always archives with `untilEscalating`.
Upgrade Prisma Next in your app. Bumps every `@prisma-next/*` dependency from the version pinned in the lockfile to the requested target (or npm `latest`), applies any required code-translation steps from the per-transition upgrade instructions, validates with the project's own typecheck + tests, and commits each minor step on its own. Use when the user asks to "upgrade Prisma Next", "bump Prisma Next", "move to Prisma Next X.Y", or asks an agent to deal with an `@prisma-next/*` minor bump in their app
When the user wants to set up, optimize, or manage TikTok Ads. Also use when the user mentions "TikTok Ads," "TikTok for Business," "TikTok Pixel," "Events API," "TikTok Spark Ads," or "TikTok video ads." For organic TikTok, use tiktok-captions.
Guides the agent through setting up and using push notifications in Capacitor apps using Firebase Cloud Messaging via the @capacitor-firebase/messaging plugin. Covers Firebase project setup, plugin installation, platform-specific configuration (Android, iOS, Web), APNs certificate setup, requesting permissions, retrieving FCM tokens, listening for notifications, topic subscriptions, notification channels, and testing. Do not use for local notifications, non-Firebase push providers, migrating Capacitor apps or plugins, or non-Capacitor mobile frameworks.
Audit any eval, metric, experiment, or benchmark for leakage: does external ground truth enter independently, or are the model, scorer, and designer just confirming a result no outside truth ever produced? Use before trusting any 'how we'll know it worked' — an A/B, a holdout, a score, a validation — and whenever a result feels too clean or self-confirming. Walks an 8-pattern leakage taxonomy and returns only the patterns that fire, each with an independence fix. Read-only.
Salesforce architecture diagrams using Mermaid with ASCII fallback. Trigger when the user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. Do not trigger when the user wants PNG/SVG image output (use sf-diagram-nanobananapro), or asks about non-Salesforce systems.
Detect and remove AI-generated markers from Hungarian text, making it sound like a native Hungarian speaker wrote it. Use when asked to "humanize", "naturalize", or "remove AI feel" from Hungarian text, or when editing .md/.txt files containing Hungarian content. Identifies 26 patterns (12 Hungarian-specific + 14 universal) and 4 style markers.
Report local Claude, Codex, Cursor, GitHub Copilot, Grok, Kimi, Z.AI, Alibaba, OpenCode Go, Antigravity, Command Code, MiniMax, MiMo, DeepSeek, OpenRouter, ElevenLabs, Devin, Muse, and Higgsfield quota windows via the quota-axi CLI - remaining effective usable runway, percentages, reset times, cycle-average pace vs the reset clock, a per-scope selection signal, and provider status read from local auth sources, with no routing, no credential minting, and no default ordering preference. Use before deciding whether it is safe to keep spending a provider's quota, when the user asks about usage, rate limits, pace, or remaining quota, or when comparing local provider headroom.
Use when the user asks to "track rankings" or "查排名"; measures keyword and SERP-position deltas over time from provided exports or connected tools, including AI-response checks. Not for multi-metric stakeholder reports or setting alerts — use performance-monitor (report or alert mode). 排名追踪/SERP监控
When the user wants to analyze competitors for SEO, content, backlinks, or positioning. Also use when the user mentions "competitor analysis," "competitor research," "competitor keywords," "competitor backlinks," "link gap," "content gap," "competitor content," "competitive analysis," or "competitor comparison." For content roadmap, use content-strategy.
When the user wants to plan content for SEO, create content calendar, or build topic clusters. Also use when the user mentions "content strategy," "content plan," "topic clusters," "pillar content," "pillar page," "cluster articles," "editorial calendar," "content hub," "content planning," "content clusters," "topic cluster strategy," "content strategy for SEO," or "content calendar." For editorial mix, use content-marketing.
Use when auditing domain authority, trust, or citation credibility; runs a peer-relative 40-item CITE profile with evidence coverage and verified manipulation/penalty veto checks. Not for page-level content quality — use content-quality-auditor; not for backlink profiling alone — use offsite-signal-analyzer. Domain authority/website trustworthiness
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.