Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when users say "create a skill", "make a new skill", "build a skill", "skill for X", "audit this skill", "review this skill", "check skill quality", "fix this skill", "improve this skill", "refactor this skill", "update this skill", or "optimize this skill", or when creating, refactoring, or auditing domain expertise into agent skills with specialized knowledge, workflows, or tool integrations.
AI voice generation, text-to-speech, and voice synthesis via inference.sh CLI. Models: Inworld TTS-2 (100+ languages, emotion/non-verbal steering), Inworld TTS 1.5 (ultra-low latency), ElevenLabs (22+ premium voices, 32 languages), Kokoro TTS, DIA, Chatterbox, Higgs, VibeVoice for natural speech. Capabilities: multiple voices, emotions, accents, long-form narration, conversation, voice transformation, delivery mode control, character voices. Use for: voiceovers, audiobooks, podcasts, video narration, accessibility, gaming NPCs, avatar audio, UGC. Triggers: voice cloning, tts, text to speech, ai voice, voice generation, voice synthesis, voice over, narration, speech synthesis, ai narrator, elevenlabs, eleven labs, natural voice, realistic speech, voice ai, voice changer, inworld, inworld tts, character voice, npc voice
Use when orienting, onboarding, or planning before a concrete task — the entry point for building a customized Workfront UI on Adobe App Builder. Use whenever the user is new to Workfront UI extensions and asks where to start or what the process looks like; describes a Workfront customization idea and asks how to build it; asks for the end-to-end roadmap (set up → scaffold → build → test → deploy → publish); or asks how the React/Spectrum SPA, serverless Runtime actions, and Workfront extension points fit together. This umbrella routes each stage to its skill: workfront-ui-extension (front-end SPA + extension points), workfront-actions (Runtime actions + Workfront Public API v21), workfront-local-testing (previewing a build inside Workfront); machine setup and aio app init are covered by appbuilder-project-init. Skip it and go straight to the matching sub-skill when the user already has one specific task.
Arco Design React UI component library reference (@arco-design/web-react). Use this skill whenever the user asks to build a page, create a UI, write frontend code, develop a web application, design a dashboard, or implement any React interface — especially when they mention Arco, arco-design, @arco-design/web-react, or any Arco component name (Button, Table, Form, Modal, Select, Menu, etc.). Covers all 70 components with full API, code examples, import patterns, theming, i18n, layout, forms, tables, modals, navigation, data entry, data display, feedback, responsive design, and best practices.
This skill should be used when the user asks to "translate", "翻译", "精翻", "translate article", "translate to Chinese", "translate to English", "改成中文", "改成英文", "convert to Chinese", "localize", "本地化", "refined translation", "精细翻译", "proofread translation", "快速翻译", "快翻", "这篇文章翻译一下", or provides a URL/file with translation intent. Supports three modes (quick/normal/refined) with custom glossary support.
Bilibili AI information feed — scans AI-related Bilibili accounts daily, finds viral videos by likes, intelligently clusters topics, and generates an HTML daily report with cover images, engagement data, and subscription support. It also conducts AI intelligence investigations based on trending topics, using multi-engine search and cross-validation to produce structured investigation reports. Supports user-defined keyword searches. ⚠️ Data for the previous day is updated daily before 15:00. If data for the target date is unavailable, you must inform the user first and wait for confirmation before calling the API; automatic retrieval is prohibited. Use when users need a Bilibili AI daily report, viral Bilibili videos, AI-Bilibili trends, Bilibili AI content or videos, Bilibili intelligence, or custom keyword searches.
Generate working code that routes HTTP requests through Bright Data proxy networks (Datacenter, ISP, Residential, Mobile) and help users decide which network and IP pool type to use (shared pool, shared IPs, or dedicated IPs). Use this skill whenever the user mentions Bright Data, brightdata.com, BD proxies, brd.superproxy.io, geo.brdtest.com, a brd-customer- proxy username, a Bright Data zone, the superproxy host, or wants to scrape or route requests through Bright Data—including questions about proxy URL format, country or session or IP or sticky-session targeting, SSL certificate setup for residential or mobile proxies, KYC verification, ignoring SSL errors, choosing between shared pool and shared IPs and dedicated IPs, or integrating Bright Data into Python requests/httpx/aiohttp, Node fetch/axios, Playwright, Puppeteer, Selenium, or Scrapy.
Use this skill whenever work that spans several steps, people, or systems must run reliably — approvals, hand-offs, escalations, deadlines, retries, or compensation — even if Camunda or BPMN isn't mentioned. Load it before recommending an approach or tool for running such work. Designs, edits, and lints executable BPMN processes for Camunda 8. Not for one-step jobs or CI pipelines.
Deploy ERC20 tokens on Base, Ethereum, Arbitrum, and other EVM chains using the Clanker SDK. Use when the user wants to deploy a new token, create a memecoin, set up token vesting, configure airdrops, manage token rewards, claim LP fees, or update token metadata. Supports V4 deployment with vaults, airdrops, dev buys, custom market caps, vanity addresses, and multi-chain deployment.
Current Claude AI and Claude Code capabilities, features, and limits. Consult before making claims about what Claude can or cannot do, what features exist, model availability, pricing, or environment differences. Use when answering “Can Claude do X?”, comparing Claude AI vs. Code, checking current model specs, or advising on which environment suits a task.
Plans new DataHub connectors by classifying the source system, researching it using a dedicated agent or inline research, and generating a _PLANNING.md blueprint with entity mapping and architecture decisions. Use when building a new connector, researching a source system for DataHub, or designing connector architecture. Triggers on: “plan a connector,” “new connector for X,” “research X for DataHub,” “design connector for X,” “create planning doc,” or any request to plan, research, or design a DataHub ingestion source.
Author, save, and edit email templates in the PostHog workflows library—compose email design JSON with Liquid personalization and create and round-trip edit templates over MCP. Use when asked to design, build, update, or fix an email template for workflows, broadcasts, or campaigns
Use when the user wants the GitNexus engineering pipeline run end-to-end on a task: gitnexus-plan (plan depth chosen up front), a blocking gate to execute with gitnexus-work or stop, finishing with a gitnexus-review of the result. Examples: "/gitnexus-lfg Add retry support to the ingestion pipeline", "run the gitnexus pipeline on this", "plan, build and review this feature".
Godot expert auditor: Aurelius. Exhaustive never-list enforcement and architectural slap-down for Godot 4.7 projects. Use when auditing signal decay, ObjectDB orphans, typed Array/Dictionary slop, material.duplicate batch breaks, export case-sensitivity, Expression.execute risks, or sector never-lists. Keywords: auditor, Aurelius, never-list, signal decay, ObjectDB orphans, typed Array, export case-sensitivity, instance uniforms, PackedScene.get_state.
Create, improve, or audit README.md documents for GitHub projects. Use only when the user explicitly asks for a README, README quality/readability, README accuracy, or README examples. Do not use for full docs sites, API-reference-only work, general repo launch/readiness audits, topics/homepage metadata, or broad repository review.
Use when the user requests writing, editing, rewriting, final polishing, style review, or structurally faithful translation in a specific author's Chinese style, especially when emphasizing substantial paragraphs, long sentence chains, facts first, sharp judgments, erudite commentary, or reducing meaningless decorative adverbials and complements.
Score and diagnose Google Ads landing pages. Use when asked to audit a landing page, check landing page quality, diagnose high-CTR but low-conversion-rate ad groups, improve Quality Score's Landing Page Experience component, or compare an ad group's messaging against its landing page. Trigger on "landing page audit", "landing page score", "landing page quality", "why is my conversion rate low", "LPX", "landing page experience", "ad to page match", or when `/google-ads-audit` surfaces a high-CTR / low-CVR ad group.
TRIGGER: before putting UI / layout / screen / component mockups into `AskUserQuestion` `preview:` chips, invoke this skill and ask the user "quick inline chips, or a real HTML grid?" — no exception for "simulate", "demo", "mock up", "quick decision". Generates side-by-side HTML grids of 3–6 distinctly different approaches for the GENERATIVE phase, when candidates are NOT yet named. If candidates ARE named ("compare X, Y, Z"), hand off to html-comparison-matrix.
Build HTML data explorers for CSV, JSON, log, and event data — filterable tables, faceted search, inline charts, timeline scrubbing, A/B test result dashboards. Use whenever the user has a dataset to explore, browse, filter, chart, facet, or analyze — especially for ad-hoc analysis where opening a heavy BI tool is overkill. Reach for this when the user pastes data, mentions a CSV/JSON/log file, or asks to "look at" or "analyze" a dataset. Always runs a secret-redaction pass before embedding data — credential-shaped values (API keys, tokens, cookies, passwords) are replaced with placeholders unless the user explicitly opts in to embedding them.
This skill has instructions to setup a Envio HyperIndex indexer to capture onchain smart contract events. Use when user wants a historical feed or activity feed or some similar tracking feed or feature in their app or wants to capture onchain smart contracts events as a trigger to perform some other actions in their app. Also use this skill when the user wants to debug, restart, promote or delete and existing Envio indexer deployed on Envio Cloud
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Investigates a single PostHog error tracking issue end-to-end. Use when the user provides an issue ID or pastes an issue URL (`/error-tracking/<id>`) and wants to understand the error — who it affects, what triggers it, when it started, whether it correlates with a release, browser, OS, or feature flag, and what the next step should be. Pulls aggregated metrics, sample exception events, segment breakdowns, linked replays, and synthesizes a hypothesis-grade summary in one pass
A complete workspace for structured job description (JD) analysis, role-fit diagnosis, ATS readability audits, and targeted résumé customization. Use when the user mentions “JD,” “job description,” “role fit,” “analyze this JD,” “Am I a fit?”, “tailor my résumé for…,” “applying,” “hiring requirements,” “ATS screening,” or saving different application versions. Supports JD-only analysis with a diagnostic report, or an end-to-end tailored HTML/PDF résumé for the role, a match report, and version history.
Search and retrieve Japanese National Diet (国会) meeting minutes via the official NDL Kokkai API (no auth required). Covers all Diet sessions since 1947, supports keyword search, speaker lookup, meeting-level retrieval, and date/session/issue filtering. Useful for political research, legislative tracking, speech analysis, and any task involving Japanese parliamentary records. 国会発足（1947 年）以降の日本の国会議事録を NDL 国会会議録検索システム API 経由で検索・取得するスキル。発言・会議・キーワード検索および期間/回次/会派による絞り込みに対応。Use this skill when researching Japanese Diet debates, MP statements, or parliamentary records. Not for the Imperial Diet (帝国議会（貴族院を含む）, before 1947-05), which is served by the separate NDL Imperial Diet API.
Atomic skill for extracting brand style DNA. Uses product images and user-provided brand parameters (primary colors, fonts, platform, region, language) to extract a unified brand visual language (Brand DNA) and outputs structured brandGeneJson for downstream atomic skills. Brand gene extraction, brand DNA, brand visual definition, brand tone extraction, brand style extraction, visual identity extraction. Called in step three by the image-set orchestration layer (linkfox-aigc-imagegen-cloth / product image-set orchestration path); triggered when the user says “extract brand genes,” “define brand style,” “brand gene,” or “brand visuals.”
Deeply analyze Amazon niche markets by keyword, covering monopoly level, brand concentration, new product success rate, and market opportunity scores. Trigger this skill when the user mentions niche market analysis, keyword market research, monopoly assessment, brand concentration analysis, new product success rate, market demand score, competitive landscape, Amazon submarket exploration, niche market analysis, keyword market, monopoly level, brand concentration, new product success rate, market opportunity score, competitive landscape, or Jiimore data. Trigger it even if the user does not explicitly mention "niche market," as long as their request involves evaluating Amazon market competition, brand density, or opportunity potential for a keyword.
Detect graphic trademarks in product images and search for similarities. Trigger this skill when the user mentions trademark detection, graphic trademark search, Logo infringement checks, trademark similarity analysis, image trademark risk assessment, product image trademark screening, graphic trademark detection, logo infringement, trademark similarity, trademark risk, image trademark screening, or Ruiguan. Even if the user does not explicitly say “trademark detection,” trigger this skill whenever they need to compare product images with registered graphic trademarks or assess trademark infringement risk.
Seerfar Ozon product report search: filters Ozon products by multiple metrics, including sales volume, revenue, sales/revenue growth rate, add-to-cart conversion, order conversion, price, rating, review count, QA count, variant count, views, gross margin, return/cancellation rate, advertising cost share, weight/volume, listing time, brand, seller, fulfillment method, and tags. Returns a complete product-level report for each item, including SKU, title, price (rubles), sales, revenue, lost revenue, conversion rate, rating, reviews, brand, seller, fulfillment method, and listing days/months. Use for Ozon product selection, competitor analysis, best-seller discovery, and filtering by price or conversion ranges. Triggers when the user mentions Ozon product reports, Ozon product selection, Ozon product filtering or analysis, Ozon best sellers, Ozon competitor analysis, Ozon product report, Ozon product screener, filtering Ozon products by sales, Ozon best-seller mining, or Seerfar Ozon product reports. Trigger even if “Seerfar” is not explicitly mentioned when the intent is to filter Ozon products by multiple metrics and view product-level reports.
Seerfar Ozon store product search: Retrieve a store’s product list by Ozon store (seller) ID. Returns each product’s sales over the past 30 days, price, rating, weight, shipping method (FBO/FBS), seller type (local/cross-border), return and cancellation rate, and the store’s total sales over the past 30 days. Use for competitor store product analysis, finding bestsellers, and breaking down a seller’s product mix. Trigger when the user mentions Ozon store products, Ozon seller product lists, competitor store analysis, Ozon store bestsellers, Ozon seller analysis, Seerfar Ozon store search, Ozon shop search, Ozon seller products, competitor shop analysis, or Ozon store products. Trigger even if the user does not explicitly mention “Seerfar,” as long as they intend to view product and sales data for an Ozon store or seller.
Shopee store discount promotions (part of the same series as linkfox-shopee-store-auth). Forwards all 12 endpoints in the Shopee Open API Discount module via /shopee/developerProxy, including add_discount, get_discount_list, update_discount, add_discount_item, end_discount, and SIP discounts. Trigger when the user mentions Shopee discounts, Discount, promotions, limited-time discounts, add_discount, discount_id, or discount campaigns. Even if they do not explicitly mention “discounts,” trigger this skill whenever they need to create or manage discount campaigns for an authorized Shopee store.
Shopee store Video (same series as linkfox-shopee-store-auth), forwarding all 15 endpoints in the Shopee Open API Video module through /shopee/developerProxy, including get_cover_list, post_video, get_video_list, get_video_detail, edit_video_info, get_overview_performance, and get_video_detail_performance. Trigger when the user mentions Shopee videos, store videos, uploading videos, post_video, video covers, video performance, video performance, or get_video_list. Trigger even without an explicit mention of “video” if the request involves publishing videos or analyzing their performance for an authorized Shopee store.
Shopee store vouchers (part of the same series as linkfox-shopee-store-auth). Forwards all 6 endpoints in the Shopee Open API Voucher module via /shopee/developerProxy: add_voucher, get_voucher_list, get_voucher, update_voucher, end_voucher, and delete_voucher. Trigger when the user mentions Shopee vouchers, Voucher, store coupons, add_voucher, voucher_id, spend-and-save coupons, or discount codes. Even if they do not explicitly mention “vouchers,” trigger this skill whenever they need to manage Voucher campaigns for an authorized Shopee store.
Multidimensional Amazon product search and filtering based on Sorftime data, covering 14 marketplaces and historical monthly snapshots. Trigger when the user mentions Sorftime product search, Amazon product filtering, competitor research, category analysis, brand bestsellers, seller analysis, seasonal products, historical snapshots, product search, monthly sales volume or revenue, finding products with ABA keywords, price-range filtering, new product discovery, multi-criteria filtering, product search, competitor research, category analysis, brand bestsellers, seller analysis, seasonal products, or historical snapshot. Trigger even if the user does not explicitly mention “Sorftime,” as long as they want to search, filter, compare, or explore Amazon products by category, brand, or seller.
Download full-text patent PDF documents from the PatSnap patent database using a patent ID or publication number. Trigger this skill when the user mentions patent PDF downloads, patent full text, obtaining patent files, publication number lookup, patent family PDF alternatives, bulk patent PDF export, patent PDF download, patent full-text document, patent file download, PatSnap, or patent PDF. Even if the user does not explicitly mention “PatSnap,” trigger this skill whenever they need to download or view patent PDF documents.
Inspects URL paths and proposes, tests, orders, and applies project-level path cleaning rules so dynamic segments (numeric IDs, UUIDs, slugs, dates) collapse into readable aliases. Use when the user says "clean the paths", "normalize URLs", "group similar pages", "too many distinct paths", "/users/123 and /users/456 are the same page", "set up path cleaning", or asks why a Web analytics or Paths breakdown is fragmented across thousands of nearly-identical URLs. Covers regex syntax (re2), alias placeholder convention, rule ordering, the test workflow, and applying rules via the path-cleaning-rules-update MCP tool.
Integrate markstream-vue into a Vue 3 app. Use when Codex needs to add the Vue 3 renderer, import CSS in the right order, choose renderer and DOM modes, choose built-in, plain, or custom code-block paths, choose between `content` and `nodes`, coordinate long AI timelines with `MarkstreamVirtualTimeline`, `useMarkstreamVirtualAdapter`, or `vue-virtual-scroller`, enable optional peers such as stream-diffs, Mermaid, KaTeX, D2, or Infographic, or wire scoped custom components in a non-Nuxt Vue repository.
Comprehensive mobile app UI/UX design skill covering iOS HIG, Android Material 3, accessibility standards, React Native best practices, touch targets, thumb zones, and adaptive patterns, with detailed reference documents, examples and audit scripts.
Generate images with Google Gemini native image models via inference.sh CLI. Models: Gemini 3 Pro Image, Gemini 2.5 Flash Image. Capabilities: text-to-image, image editing, multi-image input. Triggers: nano banana, gemini image, gemini 3 pro image, gemini 2.5 flash image, google image generation, native image generation, gemini native image
Nuxt Content v3 Git-based CMS for Markdown/MDC content sites. Use for blogs, docs, content-driven apps with type-safe queries, schema validation (Zod/Valibot), full-text search, navigation utilities. Supports Nuxt Studio production editing, Cloudflare D1/Pages deployment, Vercel deployment, SQL storage, MDC components, content collections
Active Directory attack methodology for internal network red team engagements. Covers reconnaissance (BloodHound, PowerView, ADExplorer), credential abuse (Kerberoasting, ASREProasting, NTLM relay, LLMNR/NBT-NS poisoning), privilege escalation (ACL abuse, GPO abuse, unconstrained/constrained delegation), lateral movement (Pass-the-Hash, Pass-the-Ticket, Overpass-the-Hash, WMI/WinRM/PsExec), persistence (Golden/Silver/Diamond Tickets, DCSync, DCShadow, AdminSDHolder, Skeleton Key), forest trust attacks, ADCS abuse (ESC1-ESC15), and modern MDI/Defender for Identity evasion. Use when assessing on-prem AD, hybrid AD/Entra ID environments, or ADCS deployments.
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.