Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Create a fixed full-screen WebGL laser background effect with a thin white-hot vertical core, restrained brand-colored halo, and soft smoky fog around the beam. Use only for laser background effects, not full page layout, copy, generic hero scenes, particles, or unrelated motion systems
Convert Markdown articles to WeChat Official Account compatible HTML format. Use when users need to convert Markdown files to WeChat articles, apply themed styling for WeChat formatting, generate inline CSS HTML compatible with WeChat editor, process technical articles with code blocks and tables for WeChat, or apply professional WeChat-style layouts with headers and footers.
Build and modernize WPF applications on .NET with correct XAML, data binding, commands, threading, styling, and Windows desktop migration decisions. USE FOR: working on WPF UI, MVVM, binding, commands, or desktop modernization; migrating WPF from .NET Framework to .NET; integrating newer Windows capabilities into a WPF app. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Search for and install community Mini Program AI Skills. Triggered when users want to add AI capabilities to an existing Mini Program project but are unsure which community Skills are available, or do not want to build from scratch. Search, view details, and install from repositories such as TencentCloudBase/awesome-miniprogram-skills.
Use when building with the yahoo-finance2 TypeScript/Deno/npm library, using its Yahoo Finance data modules, CLI, or MCP server, or contributing to the yahoo-finance2 repository including modules, validation schemas, cached fixtures, and npm/JSR build output.
Manage Yandex Direct campaigns, ads, keywords, bids, reports via API v5. Use when the user needs to work with Yandex Direct API — campaign management, ad groups, ads, keywords, bids, targeting, reports, statistics, dictionaries, or any other Yandex Direct API operation. Triggers: Yandex Direct, Direct API, campaigns API, ad management API, keyword bids, Yandex advertising API, Direct reports, Direct statistics.
Agent-callable YouTube tools — search and read videos, update and delete videos, manage playlists and playlist items, read and post comments, rate videos, manage subscriptions, and read channel and caption metadata. Use when the user mentions YouTube or wants to find, comment on, or organize YouTube videos and playlists, even if they don't name YouTube explicitly.
Read and parse the contents of PDF files, extracting text, tables and structured information. Use when the user needs to read a PDF file, extract PDF content, or analyze a PDF document's structure. Not for editing or creating PDFs, merging/splitting PDFs, OCR on scanned PDFs, or reading other document formats such as Word or Excel.
Make a 30-45 second enrollment-driving trailer for an academy or LMS course - who it's for, three fast "you'll learn" highlights, the outcome promise, and an enroll CTA, with energetic branded motion scenes interleaved with brief product peeks. Use when the user says "make a course trailer", "promo video for our academy course", "enrollment video", "teaser for this course", or "advertise this course to our customers".
Append one branded end card to an existing video with a single clear next action - a link, trial, docs page, or contact - and a clean close. Use when the user says "add a CTA at the end", "add an end card", "close the video with a call to action", "add an outro with our link", or "end this with 'start your trial'".
Add a persistent, unobtrusive corner logo watermark to an existing video - one corner, low opacity, present for the full runtime without covering any action. Use when the user says "add our logo to this video", "watermark this video", "put our logo in the corner", or "brand this video with our logo".
Python style and codebase conventions for ADK (Agent Development Kit): private-by-default file visibility, imports, type hints, Pydantic v2 models, formatting, docstrings, logging, async I/O, file and test layout, and unit test structure. Use when writing or editing ADK source or tests, deciding whether a new file or symbol should be public or private, naming or placing a test file, fixing a formatter, linter, or type-check failure (pyink, isort, ruff, mypy, addlicense, compliance-checks), or asking whether code matches house style. Don't use for reviewing a whole changeset (use adk-review), writing a developer guide or design doc for a code unit (use adk-unit-guide or adk-unit-design), building or configuring agents (use adk-agent-builder), or installing the toolchain (use adk-setup).
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad budget,' 'cost per click,' 'ad spend,' or 'should I run ads.' Use this for campaign strategy, audience targeting, bidding, and optimization. For bulk ad creative generation and iteration, see ad-creative. For landing page optimization, see cro.
Operate an evaluated agent with tools and authority in production through a runtime control plane covering versioning, staged rollout, fallback, cost and latency budgets, tool health, human escalation, disablement, and trace-to-eval feedback. Do not use for building agents, designing evals, or general release, SRE, security, or platform engineering — those methods stay with their specialist skills.
Reviews agentic AI systems against the OWASP Top 10 security risks for autonomous AI agents. Auto-invoked when reviewing multi-agent architectures, AI agent deployments, or systems where LLMs have tool access and act autonomously. Covers permission models, tool security, memory integrity, trust boundaries, and human oversight. Produces a structured assessment with risk ratings and architectural recommendations.
Design and operate AI governance: principles, decision rights, risk tiers, lifecycle gates, fairness, transparency, privacy, security, compliance mapping, maturity and board reporting across SaaS, API, self-hosted and agentic systems. Use to admit, update or retire Agent Skills, MCP servers and A2A capabilities; approve an agent for production actions; or decide earned-autonomy promotion, reduction or revocation. Cover GxP, ALCOA+, data integrity, electronic records, assurance and QMS interfaces for life sciences. Do not use for legal interpretation (legal-strategy), data-platform mechanics (data-architect/data-engineering), security implementation (secure-software-engineering), skill package inspection (agent-skills), or executing runtime changes (agent-production-operations).
Turn Amazon Brand Analytics reports into decisions. Reads Search Query Performance, Search Catalog Performance, Market Basket, Repeat Purchase, and Top Search Terms exports, and converts them into ranked actions. Use when a user pastes or describes Brand Analytics data, asks about Search Query Performance, SQP, market basket analysis, search frequency rank, click share, conversion share, repeat purchase behavior, or wants to know what their Brand Analytics is telling them. Trigger phrases: \"brand analytics\", \"SQP\", \"search query performance\", \"market basket\"、\"click share\"、\"conversion share\"、\"repeat purchase\". Works with zero tools. the user pastes the report data.
Guide a seller through Amazon Brand Registry enrollment and turn the benefits into action. Covers trademark requirements, the enrollment steps, and how to use Brand Registry tools once approved (A+ Content, Stores, Sponsored Brands, Brand Analytics, Project Zero, Transparency, brand protection). Use when a user asks about Brand Registry, enrolling a brand, trademark requirements for Amazon, protecting a brand, or unlocking brand-only features. Trigger phrases: \"brand registry\", \"enroll my brand\", \"trademark for amazon\", \"brand protection\", \"gated brand features\". Works with zero tools.
Diagnose why a listing is losing the Amazon Buy Box (Featured Offer) and build a plan to win it back. Covers seller-health signals, pricing relative to the competing offer, fulfillment method, stock, and account metrics. Use when a user asks why they lost the Buy Box, how to win the Featured Offer, why a reseller is beating them, or why their own listing shows another seller's offer. Trigger phrases: \"buy box\", \"featured offer\", \"lost the buy box\"、\"win the buy box\"、\"buy box percentage\"、\"another seller has my listing\". Works with zero tools. the user describes the offer and account state.
Forecast cash flow under Amazon's DD+7 (Delivery-Date-Based Reserve) payout policy. Models when funds clear, sizes the working-capital buffer the seller needs, and stress-tests scenarios for slow shipping or refund spikes. Use when a user asks about DD+7, Delivery-Date-Based Reserve, payout delays, working capital, cash flow under the new reserve policy, or how much cash they need to keep on hand. Trigger phrases: \"DD+7\", \"payout reserve\", \"delivery date reserve\", \"working capital\", \"cash flow\", \"Amazon holds my money\". Works with zero tools. the user provides sales velocity, fulfillment mix, and seasonality.
Detect and fix silent Amazon category re-noding. When Amazon quietly moves listings to incorrect browse-tree nodes, sales drop sharply because the listing now ranks against the wrong queries. This skill audits the nodes, identifies the wrong placements, and writes the browse-node correction case for Seller Central. Use when a user notices a sudden sales drop with flat ad spend, a listing in the wrong browse category, or wonders why their product is not showing up for the right keywords. Trigger phrases: \"category\", \"browse node\", \"wrong category\", \"re-noded\", \"sales dropped no reason\", \"browse tree\". Works with zero tools.
Decide which Amazon deal type to run, when, and whether it will pay off. Compares Lightning Deals, Best Deals, Prime-exclusive discounts, and coupons, checks the deal fee against the expected lift, and times the deal to an event. Use when a user asks about running a deal, Lightning Deals, Best Deals, Prime Day or event deals, deal fees, or whether a deal is worth it. Trigger phrases: \"lightning deal\", \"best deal\", \"should I run a deal\", \"deal fee\", \"prime day deal\", \"deal strategy\". Works with zero tools. the user provides price, cost, and goal.
Compare Amazon inbound shipment placement options (minimal-split vs Amazon-optimized split, partial-split, optional unified inventory) given SKU dimensions, units, and destination forecast. Returns the lowest landed cost per unit. Use when a user asks about STA (Send to Amazon), inbound placement fees, shipment splits, fulfillment center routing, or inbound shipping optimization. Trigger phrases: \"STA\", \"inbound placement\", \"shipment split\", \"placement fee\", \"fulfillment center routing\". Works with zero tools.
Find and manage Amazon PPC negative keywords to cut wasted ad spend without blocking converting traffic. Reads a search term report, flags the terms draining budget, decides negative-exact versus negative-phrase, and protects valuable terms from being blocked by accident. Use when a user asks about negative keywords, wasted ad spend, search term reports, irrelevant clicks, high-ACoS terms, or cleaning up a PPC campaign. Trigger phrases: "negative keywords", "wasted ad spend", "search term report", "irrelevant clicks", "high ACoS terms", "clean up campaign". Works with zero tools. the user pastes the search term report.
Check an Amazon product for compliance and safety requirements before and after listing. Covers required certifications, labeling and warning requirements, restricted-substance rules, documentation Amazon may demand, and category-specific safety rules. Use when a user asks about product compliance, safety requirements, certifications, required labels or warnings, a compliance document request from Amazon, or whether a product is allowed. Trigger phrases: "product compliance", "safety requirements", "certifications", "compliance documents", "required labels", "is this product allowed". Works with zero tools.
Builds a week-by-week Q4 restock plan from August through November with FBA inbound delay buffers, peak velocity multipliers, and FBM fallback triggers. Q4 is 30-40% of annual revenue and FBA receiving takes 2-3 weeks during peak. Standard restock math stocks out at the worst possible moment. Use when a user asks about Q4 planning, Black Friday inventory, or Prime Big Deal Days restock. Trigger phrases: "Q4 restock plan", "Black Friday inventory", "Prime Big Deal Days restock", "Christmas Amazon inventory", "FBM fallback for FBA". Works with zero tools.
Set up Amazon keyword rank tracking and interpret the movements. Defines which keywords to track, how to read a rank change, separates organic rank from ad placement, and turns ranking shifts into actions. Use when a user asks about rank tracking, keyword rankings, why a ranking dropped, organic position, tracking search position, or how to improve a keyword rank. Trigger phrases: "rank tracker", "keyword ranking", "rank dropped", "organic rank", "search position", "improve my ranking", "track rankings". Works with zero tools. the user provides their rank observations.
Decide per SKU whether to remove, liquidate, dispose, or keep aging FBA inventory. Breaks the math: base storage plus the monthly aged-inventory surcharge over the holding horizon vs removal fees vs recoverable resale value. Use when a user asks about aged inventory, aged-inventory surcharge, long-term storage fees, removal orders, liquidation, or what to do with slow movers. Trigger phrases: "aged inventory", "aged-inventory surcharge", "long-term storage", "removal order", "liquidate", "slow movers", "dispose", "old stock". Works with zero tools. the user provides unit cost, age, storage rate, and current price.
Estimate Amazon monthly sales and revenue from a Best Seller Rank, and size a niche or competitor from observable signals. Explains the BSR-to-sales relationship, adjusts by category and price, and returns a sales range with a confidence note. Use when a user asks how many units a product sells, to estimate sales from BSR, size a market or niche, gauge a competitor's volume, or judge demand. Trigger phrases: "sales estimate", "how many units", "estimate from BSR", "best seller rank", "market size", "competitor sales", "monthly sales". Works with zero tools. the user provides BSR, category, and price.
Produces a 30-day day-by-day recovery plan after an Amazon stockout. Aggressive PPC, external traffic, review velocity, A+ refresh, in the right sequence. A structured sequence recovers BSR far faster than doing nothing, which can leave a listing depressed for a quarter. Use when a user mentions stockout, ranking lost, BSR recovery, or post-stockout. Trigger phrases: "Amazon stockout recovery", "ranking lost after stockout", "BSR recovery", "post-stockout playbook". Works with zero tools.
Plan an Amazon Subscribe and Save strategy for consumable and replenishable products. Decides if a product fits, sets the discount tier, and builds a plan to convert one-time buyers into subscribers and keep them. Use when a user asks about Subscribe and Save, SnS, recurring revenue on Amazon, subscription discounts, converting buyers into subscribers, or retention. Trigger phrases: "subscribe and save", "SnS", "subscription", "recurring revenue", "repeat buyers", "retention", "replenishment". Works with zero tools.
Calculate import tariffs, duties, and landed cost for products imported to sell on Amazon. Covers HS code classification, duty rates, additional tariffs, freight and customs fees, and the true per-unit landed cost. Use when a user asks about import tariffs, customs duty, landed cost, HS codes, import taxes, duty rates, or the cost of importing a product. Trigger phrases: "tariff", "import duty", "customs", "landed cost", "HS code", "import tax", "duty rate", "cost to import". Works with zero tools. the user provides the product, the route, and the costs.
Spot and evaluate trending product opportunities on Amazon, and tell a real trend from a fad. Reads trend signals, judges where a trend is in its curve, and decides whether a seller can enter in time to profit. Use when a user asks about trending products, hot products, viral products, jumping on a trend, trend spotting, or whether a product is a fad. Trigger phrases: "trending products", "hot products", "viral product", "is this a trend or a fad", "trend spotting", "should I jump on this trend". Works with zero tools.
Plan Amazon parent-child variation listings. Decides what to merge into one listing, what to keep separate, how to structure the variation theme, and how to avoid the common variation policy traps. Use when a user asks about variations, parent-child listings, merging listings, color or size variations, whether to combine products, or a variation that got flagged. Trigger phrases: "variations", "parent child", "merge listings", "variation theme", "combine products", "color variations", "size variations". Works with zero tools.
Annotate every screenshot in a help article - zoom, crop, blur, and arrows - so each image points at exactly the control its step describes. Use when the user says "annotate the screenshots", "add arrows to the images in this article", "zoom the screenshots in on the right buttons", "blur the sensitive bits in the doc images", or "make the article's screenshots clearer".
Publish, review, organize, and share work with Artifact Server, or operate an installation when the user explicitly requests administrator work. Use for Artifact Server links, files or sites to upload, project, artifact, version, tag, sharing, or comment work, connection help, and explicit install, deploy, upgrade, backup, restore, or repair requests. Do not use for unrelated package publishing or for building software that the user did not ask to store in Artifact Server.
Use when authoring a data model document — the persistence/domain model of stored data: typed entities, relationships + cardinality, keys/constraints, indexes, normalization, the storage choice, and lifecycle. Guides the producer through the METHOD, not the outline: deriving entities from the feature-spec's nouns + access patterns, detecting the paradigm and modeling in it (relational, document/NoSQL access-pattern-first, graph, wide-column, key-value), making integrity rules explicit (keys, constraints, cardinality + referential rule), justifying each index by an access pattern, and amending an approved model as a versioned, migration-planned delta — so an engineer can build + query the schema. Composes with a data-model template tool + a deep-research capability. Assumes the upstream feature-spec (+ architecture-doc) — never a blank page. Not the API wire contract (the api-spec references these entities downstream, one-directional), not the implementation/DDL, and not reviewing a finished data model.
Automates Apple Keynote using JXA with AppleScript dictionary discovery. Use when asked to "create Keynote presentations", "automate slide decks", "JXA Keynote scripting", or "generate presentations programmatically". Covers document lifecycle, slides, text, shapes, images, tables, charts, transitions, and UI scripting fallback.
Use when preparing ANY app for App Store submission, responding to App Review rejections, or running a pre-submission audit. Covers privacy manifests, metadata requirements, IAP review, account deletion, SIWA, age ratings, export compliance, first-time developer setup.
Language-specific best practices, code quality standards, and framework detection rules. Use when executing refactoring workflows, applying code quality rules, detecting frameworks, or checking language-specific patterns for TypeScript, Python, Go, Swift, or React.
Build or substantially refine reproducible Blender models through Python and the Blender CLI. Use for user requests to create meshes, props, hard-surface assets, stylized objects, assemblies, procedural geometry, game-ready GLB assets, or to iterate on a scripted Blender model from visual feedback.
Use this skill when a CFO, VP Finance, Controller, or Head of Finance needs to orchestrate the full financial operations of a company — from strategic financial planning and investor reporting to day-to-day control of accounts payable, accounts receivable, payroll, tax compliance, and revenue operations. This is the top-level financial orchestrator that commissions all finance sub-skills, maintains the single source of truth for all company numbers, drives budget allocation, manages cash flow, ensures regulatory compliance, and produces board-ready financial reports. Trigger this skill when anyone needs a comprehensive view of company finances, a board pack, a fundraising data room, or needs to coordinate across invoicing, payroll, commissions, procurement, taxes, and expenses simultaneously.
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.
