Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Analyze LinkedIn profiles in target accounts to identify potential internal champions. Evaluates role, career path, mutual connections, interests, and suggests personalization approach. Use when you need to find who will champion your solution internally.
Command-line interface for Pioneer Rekordbox 6/7 - DJ library and live-deck control via guarded SQLCipher master.db access (pyrekordbox) + virtual MIDI mapping. Provides library inspection, playlist creation/add/clear, and live-deck mixing (play/sync/crossfade/EQ). Pioneer ships no playback REST API; this harness combines the only two real surfaces (encrypted DB + MIDI) into one agent-native CLI.
Build stateful Durable Objects for real-time apps, WebSocket servers, coordination, and persistent state. Prevents 20 documented errors. Use when: implementing chat rooms, multiplayer games, rate limiting, session management, WebSocket hibernation, or troubleshooting class export, migration, WebSocket state loss, boolean binding, RPC streams, or binding errors.
Agent 1 of the video editing pipeline. Removes silences and dead air from a talking-head recording. Use when asked to cut silences, trim pauses, remove dead air / gaps, or tighten the pacing of a raw video, given a word-level transcript. Produces an edit list (EDL), a re-timed transcript for downstream agents, and optionally the cut video via ffmpeg. Does NOT cut mistakes, repeats, or false starts — that is the cut-mistakes agent.
Use when the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," or "lifecycle emails." For in-app onboarding, see onboarding-cro.
Operate Firebase from the terminal with `firebase-tools`: install/auth the CLI, bootstrap `firebase.json` / `.firebaserc`, run the Emulator Suite, deploy Hosting / Functions / rules / App Hosting, manage preview channels, and handle Firebase admin tasks like auth import/export, Remote Config, App Distribution, and Extensions. Use when the job is Firebase platform/project operation through the CLI. Triggers on: firebase deploy, firebase init, firebase emulators, firebase hosting, firebase functions, firebase firestore, firebase database, firebase auth import, firebase remote config, firebase app distribution, firebase extensions, firebase apphosting, firebase dataconnect, firebase cli, firebase-tools, deploy firebase, firebase preview channel, firebase login, firebase use, firebase target apply. Route backend AI workflow orchestration to `genkit` and direct in-app SDK integration to `genkit` (`client-ai-logic` mode).
Design game concepts from a novel. From SOURCE_BIBLE and PRODUCT_BRIEF, compare meaningful alternatives on the dimensions still unlocked, then select a playable direction using hard vetoes and explicit trade-offs. Use to decide what game a novel should become, compare game concepts, choose a game direction for a book, or decide whether a novel should become an interactive story. 小说游戏概念设计。根据 SOURCE_BIBLE 与 PRODUCT_BRIEF 对比尚未确定维度上的可行方案，通过硬性淘汰与关键取舍选定可玩方向。用于判断小说适合做成什么游戏、该不该做成互动叙事、比较游戏方案等需求。
Query, audit, and optimize Google Ads campaigns. Use an attached browser or the Google Ads API for campaign, keyword, budget, conversion-tracking, and wasted-spend analysis, or when the user explicitly requests a reviewed account change. Defaults to read-only reporting; account mutations require a bounded preview and action-time approval.
Growth strategy for product-led and loop-driven growth systems. Use when building growth strategy, designing growth loops, planning acquisition channels, evaluating network effects, deciding when to scale, or coordinating product, engineering, data, and marketing around growth. For SEO audits use seo-and-aeo-strategy; for page/form CRO use conversion-rate-optimization; for A/B test design use ab-test-setup.
A skill for hunting GraphQL vulnerabilities, built from 12 public bug bounty reports. Covers IDOR via node() / GID, mutation IDOR including AI/LLM features, cross-tenant IDOR, SSRF via arguments, batching DoS, query cost bypass, SQLi via arguments, broken object-level authorization, auth bypass via unscoped mutations, and PII exposure from missing field-level authorization. Use when hunting GraphQL vulnerabilities on any target.
Direct and produce Chinese-first cinematic motion videos with HyperFrames. Use this skill when the user wants a rendered promo film, article-to-video piece, product launch film, website-to-video piece, keynote reveal, kinetic typography sequence, text/icon transition promo, music-synced motion graphic, HTML/CSS/SVG/GSAP video, short-form vertical video, or a landing page/product story turned into motion. Default to Simplified Chinese, vertical 9:16, and 1080x1920 unless the user or platform clearly requires another format. The skill enforces a two-phase workflow: brief first, confirmation second, then assets, composition, validation, snapshots, render, and review report
Generate images, short videos, enhance/upscale, train LoRAs, and run campaign workflows through Krea. Intent-first workflow prefabs route common asks to hard recipes for social video, key visuals, image generation, product photography, archviz, enhancement, LoRA training, and ad campaigns. For professional animation, anime series, storyboard-to-video, asset bibles, or shotlist-to-sequence production, use the sibling krea-animation skill.
Review localized UI, translations, message catalogs, and pull requests for ICU syntax, placeholder integrity, glossary compliance, locale-aware formatting, accessibility, and translation readiness. Use for explicit localization reviews or changed user-facing text; report evidence-backed findings without modifying files or external systems.
Analyze meeting transcripts to extract decisions, action items, blockers, sentiment, and generate follow-up emails. Use when the user provides meeting notes, transcripts, or recordings and needs structured summaries or action tracking.
Migrates Honcho Python SDK code from v1.6.0 to v2.1.1. Use when upgrading the honcho package, fixing breaking changes after an upgrade, or when errors mention AsyncHoncho, observations, the Representation class, the .core property, or get_config methods.
Design and implement automated tests for current Minecraft 26.x or legacy 1.21.x mods and plugins using JUnit, MockBukkit, NeoForge Game Tests, or Fabric Game Tests. Use for test code and test execution, not release publishing or gameplay implementation.
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
NocoBase 2 only; never use in a NocoBase 3 project. INTERNAL CONTINUATION ONLY. Never select this skill from a raw user UI request. Use it only after nocobase-portal-manage has already resolved exactly one enabled Portal and confirmed portalType=no-code, or has proved the runtime has capabilities.multiPortal === false. Portal count or `isDefault` marker alone never enables this skill. It authors NocoBase Modern UI pages, blocks, menu items, fields, actions, layouts, reactions, and AI employee placements through backend flow-surfaces via nb api. Unresolved UI requests go to nocobase-portal-manage first; a sole AI Portal is handed off automatically for source-code implementation. Hand off AI employee lifecycle work to nocobase-ai-employee and explicit DSL, YAML, git, or cli push workflows to nocobase-dsl-reconciler. It does not handle ACL, data modeling, workflow orchestration, browser reproduction, page error postmortems, Portal lifecycle, AI Portal source-code UI, or non-Modern page navigation
Use this as the main Claude Scholar skill for a vault-first, project-scoped Obsidian research knowledge base rooted at Research/{project-slug}/. It owns bootstrap, routing, daily logging, hub/plan/index maintenance, registry updates, lifecycle actions, and lint orchestration.
Secure OpenClaw deployments with preflight hardening checks, CI/CD guardrails, container runtime restrictions, and post-deploy verification. Use when shipping OpenClaw with Docker, Kubernetes, or automated release pipelines
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
Write the touch, grounded in a real signal. Every cold email, call script, LinkedIn note, reply, and sequence is built on ONE specific, recent, dated signal pulled from Crustdata — their post, their raise, their new exec, their job listing — never a generic template and never an invented reference. 7 modes: cold email, call script, LinkedIn touches, reply handler, objection talk-tracks, multi-touch sequence builder, signal-triggered drafts. Use for "write a cold email to <person>", "what do I say", "they replied saying <X>", "handle the <objection> objection", "build a sequence", "draft outreach for these accounts", "write my follow-up", "give me a call script for <company>".
Expert sales strategy and operations guidance for B2B SaaS companies. Use when designing sales processes, implementing qualification frameworks (MEDDIC, BANT, SPICED), territory planning, forecasting, quota setting, compensation design, or optimizing pipeline velocity. Covers sales methodology, org structure, tech stack selection, win rate analysis, and deal acceleration strategies.
Run a comprehensive technical SEO audit covering crawlability, indexability, rendering, site architecture, structured data, page experience, security, and internationalization. Use this skill whenever the user asks about technical SEO, crawl issues, indexing problems, sitemaps, robots.txt, canonical tags, schema markup, page speed, Core Web Vitals, hreflang, redirects, or site-wide search performance. Triggers on technical SEO, site audit, crawlability, indexability, sitemap, robots.txt, canonical, redirect chain, schema, JSON-LD, Core Web Vitals, page speed, hreflang, mobile usability, HTTPS, security headers, render-blocking, JavaScript SEO. Also triggers when a site has indexing problems, traffic drops, or migration concerns, even if 'technical SEO' is not said explicitly.
Opening and structure. For a chosen topic or real-world footage, design the first line, the evidence shot that follows, the middle progression, and the ending. Explain what viewers are thinking at each step and why the sequence works. Also use after filming to determine the edit order from the available footage. Use when the user has a topic and wants to plan the opening and shooting approach, revise an opening, or figure out how to edit after filming.
Incrementally upgrade React Native Storybook across the supported migration paths. Use when upgrading `@storybook/react-native` projects from 5.3.x to 6.5.x, 6.5.x to 7.6.x, 7.6.x to 8.3.x, 8.x to 9.x, or 9.x to 10.x. Detect the currently installed Storybook version, choose only the next migration step, update dependencies and config, regenerate `storybook.requires`, convert remaining `storiesOf` stories to CSF during the `6.5.x -> 7.6.x` upgrade, and stop after a single version hop instead of jumping multiple major versions at once.
Apply a Korean brand's published DESIGN.md from the ko-design-md catalog (getdesign.kr) — colors, typography, spacing, radius, components, do's & don'ts — to the UI you are building in the CURRENT project. Use this skill whenever the user wants UI built or restyled in the *style of* a catalogued Korean service — "토스 디자인으로 만들어줘", "당근 스타일로 이 화면 다시 꾸며줘", "getdesign 카탈로그에서 배민 디자인 가져와서 적용", "KRDS 톤으로 폼 잡아줘", "make this look like Toss". Works in any repository over the network. Do NOT use it to add or edit catalog entries (that is the separate `design-md` producer skill), to explain the DESIGN.md format itself — there is no UI to restyle there — or to build a quiz or exam page that only borrows a brand's tone.
Use when verifying the codebase against the UX scenario base (batched, evidence-backed, report in docs/ux/audits/). Triggers: “ux audit” / “UX-аудит,” “run the scenarios” / “прогони по сценариям.” Not for a whole-project audit (project-audit) or editing scenarios (ux-scenarios)
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta, remote egress requires explicit consent, and unavailable reranking falls back deterministically
System-level input polling, player movement control, platform and language detection, and mobile on-screen controls in Decentraland. Covers inputSystem, InputModifier, PointerLock, PrimaryPointerInfo, getPlatform/getPlayerLanguage, and TouchScreenControls. Use when the user wants continuous key polling, WASD-controlled entities, to freeze the player during a cutscene, FPS-style cursor lock, multi-key combo patterns, mobile-specific behavior, localized text in the player's language, or to hide/customize the mobile joystick, crosshair, or on-screen buttons. For event-driven clicks and hover on entities see add-interactivity.
Create and refine OpenCode agents through guided Q&A. Use proactively for agent creation, performance improvement, or configuration design. Examples: - User: “Create an agent for code reviews” → ask about scope, permissions, tools, and model preferences; generate AGENTS.md frontmatter - User: “My agent ignores context” → analyze description clarity, allowed-tools, and permissions; suggest improvements - User: “Add a database expert agent” → gather requirements, set convex-database-expert in subagent_type, and configure permissions - User: “Make my agent faster” → suggest smaller models, fewer allowed-tools, and tighter permissions
Animate entities in Decentraland: play GLB clips with Animator, tween position/rotation/scale, chain TweenSequences, scroll textures. Use for moving platforms, doors, spinning or bobbing props, animated models, texture scrolling. Not for player emotes (player-avatar / avatar-animations), audio/video (audio-video) or physics (player-physics).
Sound and video in Decentraland scenes with AudioSource, AudioStream and VideoPlayer. Use when the user wants sound effects (including UI click sounds), music, ambience, radio, live streams or video screens, needs audio clips sourced or sound designed (real recordings, REAPER), or wants a soundscape with silences and stingers. For emotes see player-avatar; for audio-reactive visuals see audio-analysis.
Plan, deploy, operate, and troubleshoot multi-rack (rack scale) deployments of Azure Local — preintegrated racks scaling to hundreds of machines, built on Network Fabric Controller, Cluster Manager, SAN storage, and managed network fabric. Use for the Microsoft.NetworkCloud and Microsoft.ManagedNetworkFabric control plane. NOT for standard 1-16 node Azure Local, and NOT for rack-aware clusters (two racks as availability zones, up to 8 nodes, synchronous replication) — those are standard scale. WHEN: multi-rack, rack scale Azure Local, aggregation rack, compute rack, Network Fabric Controller, NFC, Cluster Manager, network fabric, isolation domain, az networkcloud, az networkfabric, multi-rack logical network, multi-rack Arc VM.
Analyze meeting notes to find action items and create Jira tasks for assigned work. When an agent needs to: (1) Create Jira tasks or tickets from meeting notes, (2) Extract or find action items from notes or Confluence pages, (3) Parse meeting notes for assigned tasks, or (4) Analyze notes and generate tasks for team members. Identifies assignees, looks up account IDs, and creates tasks with proper context.
Verify that every reference in a manuscript really exists and matches its metadata, catching hallucinated, corrupted or mismatched citations before submission. Use when checking a .bib file or reference list, after an AI assistant drafted citations, when a DOI may point to the wrong paper, when adding missing DOIs, or before camera-ready. Queries Crossref, OpenAlex and arXiv; zero dependencies.
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.